Data Mining for Wearable Sensors in Health Monitoring Systems: A Review of Recent Trends and Challenges

Banaee, Hadi; Ahmed, Mobyen; Loutfi, Amy

doi:10.3390/s131217472

Cited by 460Non-Invasive Vital Sign MonitoringTime Series Analysis and ForecastingContext-Aware Activity Recognition Systems

Data Mining for Wearable Sensors in Health Monitoring Systems: A Review of Recent Trends and Challenges

Open access

Banaee, Hadi, Ahmed, Mobyen, Loutfi, Amy·2013·Sensors

DOI 10.3390/s131217472PMC PMC3892855

Open this paper in CoChat — free account Open PDF

Abstract

The past few years have witnessed an increase in the development of wearable sensors for health monitoring systems. This increase has been due to several factors such as development in sensor technology as well as directed efforts on political and stakeholder levels to promote projects which address the need for providing new methods for care given increasing challenges with an aging population. An important aspect of study in such system is how the data is treated and processed. This paper provides a recent review of the latest methods and algorithms used to analyze data from wearable sensors used for physiological monitoring of vital signs in healthcare services. In particular, the paper outlines the more common data mining tasks that have been applied such as anomaly detection, prediction and decision making when considering in particular continuous time series measurements. Moreover, the paper further details the suitability of particular data mining and machine learning methods used to process the physiological data and provides an overview of the properties of the data sets used in experimental validation. Finally, based on this literature review, a number of key challenges have been outlined for data mining methods in health monitoring systems.

AI snapshot

Written from the paper’s full text.

TL;DR

This review surveys data mining and machine learning methods applied to wearable sensor data for health monitoring, focusing on vital-sign time series. It identifies anomaly detection, prediction, and diagnosis/decision making as the predominant tasks and outlines key challenges for real-world deployment.

Key findings

Based on a review of more than eighty papers from the last four years, three data mining tasks predominate: anomaly detection, prediction, and diagnosis/decision making.
ECG is predominantly used across all tasks; ECG, HR, SpO2, and RR are described as the most complex health parameters where several data mining techniques have been applied.
SVM, neural networks, decision trees, and frequency/wavelet methods are commonly used for wearable sensor data processing, though they have been seen more often only on ECG.
The paper reports that decision trees have been used for heat stress risk prediction with 95% accuracy, and that GMM provided the highest accuracy in one coronary artery disease detection study.

Methods

Design: literature review of data mining and pattern recognition methods for wearable sensors in health monitoring systems.
Data/sample: papers filtered to the last four years, limited to more than eighty selected papers; scope covered vital signs ECG, SpO2, HR, PPG, BG, RR, and BP, while accelerometer-based activity monitoring, gait research, and rehabilitation were excluded.
Analysis: literature organized by data mining tasks, algorithms, and data set properties such as time horizon, scale, labeling, continuous/discrete, and single/multi-sensor data.

Limitations

Stated field challenges include need for large-scale monitoring in non-clinical contexts, dealing with annotated data sets, exploiting multiple measurements, using contextual information, reliability/trust in automated systems, discovering unseen features, and post-processing/representation.
Evident from the review’s scope: the survey is limited to selected vital-sign parameters and excludes activity monitoring via accelerometers; it covers only the last four years and more than eighty papers, so it is not a systematic review of all available literature.
The paper states that there is no tailored work considering preprocessing issues such as data formatting, normalization, and synchronization in detail for real-life scenarios.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.3390/s131217472

Cites

108 of 108 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Claims the paper makes

0 of 163 cited sources checked · 0 supported · 0 flagged

Findingreasoning
ECG is predominantly used for all tasks in comparison to other sensor types.
“ECG, which provides mostly the rich data, is predominantly used for all tasks in comparison to the other types of sensors.”
Quote in the paperNot a substantial claim
Findingreasoning
For heart rate and blood glucose, the percentage of tasks dedicated to prediction is higher.
“However, for health parameters such as heart rate and blood glucose, the percentage of the tasks dedicated to predication is higher.”
Quote in the paperNot a substantial claim
Findingcitation
For health monitoring typically including healthy individuals, prediction and anomaly detection are used.
“For health monitoring which typically include healthy individuals who want to ensure the maintenance of good health, prediction and anomaly detection are used in the literature [22].”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [22] Mukherjee, A., Pal, A., and Misra, P. (2012, January 12–14). Data Analytics in Ubiquitous Sensor-Based Health Information Systems. Paris, France. source
  Not checked in the free run.
Findingown data
Based on the selected literature, three data mining tasks are predominant: prediction, anomaly detection (including raising alarms), and diagnosis/decision making.
“Based on the selected literature, three types of data mining tasks are predominant. These three tasks are: prediction, anomaly detection which may include the subtask of raising alarms, and diagnosis where a decision making process is made to often categorize the data into different groups depending on the diseases.”
Quote in the paperSubstantial claim
- Rests on an assumption: The selected set of more than eighty papers is representative of recent research in data mining for wearable health monitoring.
Findingcitation
Most papers using anomaly detection usually deal with short-term and multivariate data sets to characterize entire data to find discords.
“According to our review, most of the papers using the anomaly detection approach usually deal with short term [30] and multivariate data sets [31] in order to characterize the entire the data to find discords.”
Quote in the paperNot a substantial claim0 of 2 sources checked
- cites [30] Huang, G., Zhang, Y., Cao, J., Steyn, M., and Taraporewalla, K. (2013). Online mining abnormal period patterns from multiple medical sensor data streams. World Wide Web. source
  Not checked in the free run.
- cites [31] Clifton, 2013, Gaussian processes for personalized e-health monitoring with wearable sensors, IEEE Trans. Biomed. Eng. source
  Not checked in the free run.

Findingcitation
SVM, Markov models, and Wavelet analysis are used in health monitoring systems for anomaly detection.
“For example, support vector machines [27], Markov models [28] and Wavelet analysis [29] are used in health monitoring systems for anomaly detection.”
Quote in the paperNot a substantial claim0 of 3 sources checked
- cites [27] Lee, 2012, Low-energy formulations of support vector machine kernel functions for biomedical sensor applications, J. Signal Process. Syst. source
  Not checked in the free run.
- cites [28] Zhu, 2011, Automatic detection of anomalies in blood glucose using a machine learning approach, J. Commun. Netw. source
  Not checked in the free run.
- cites [29] Nikita, 2012, Identifying Chronic Disease Complications Utilizing State of the Art Data Fusion Methodologies and Signal Processing Algorithms, Wireless Mobile Communication and Healthcare source
  Not checked in the free run.
Findingcitation
Few papers use domain knowledge and predefined information to detect anomalies for decision making, such as sleep episodes and hazardous stress levels.
“Few of the papers have used domain knowledge and predefined information to detect anomalies for decision making such as anomaly detection in sleep episodes [34,35], and finding hazardous stress levels [36].”
Quote in the paperNot a substantial claim0 of 3 sources checked
- cites [34] Adnane, 2009, Detecting specific health-related events using an integrated sensor system for vital sign monitoring, Sensors source
  Not checked in the free run.
- cites [35] Adnane, M., Jiang, Z., Mori, N., and Matsumoto, Y. (2011, January 9–11). An Automated Program for Mental Stress and Apnea/Hypopnea Events Detection. Tipaza, Algeria. source
  Not checked in the free run.
- cites [36] Singh, R.R., Conjeti, S., and Banerjee, R. (2011, January 5–). An Approach for Real-Time Stress-Trend Detection Using Physiological Signals in Wearable Computing Systems for Automotive Drivers. Washington, DC, USA. source
  Not checked in the free run.
Findingcitation
Some papers find irregular patterns in vital signs time series such as abnormal episodes in ECG pulses, SpO2 signal, and blood glucose level, mostly discovering unusual temporal patterns in continuous data.
“Some of the papers considered finding irregular patterns in vital signs time series such as abnormal episodes in ECG pulses [31,32], SpO2 signal [33] and blood glucose level [28], which mostly discover unusual temporal patterns in continuous data.”
Quote in the paperNot a substantial claim0 of 4 sources checked
- cites [31] Clifton, 2013, Gaussian processes for personalized e-health monitoring with wearable sensors, IEEE Trans. Biomed. Eng. source
  Not checked in the free run.
- cites [32] Thakker, 2011, Support vector machine for abnormal pulse classification, Int. J. Comput. Appl.
  Not checked in the free run.
- cites [33] Charbonnier, 2009, On-line adaptive trend extraction of multiple physiological signals for alarm filtering in intensive care units, Int. J. Adapt. Control. Signal. Process. source
  Not checked in the free run.
- cites [28] Zhu, 2011, Automatic detection of anomalies in blood glucose using a machine learning approach, J. Commun. Netw. source
  Not checked in the free run.
Findingcitation
Anomaly detection techniques are often developed based on classification methods to distinguish normal class and outliers.
“Anomaly detection techniques are often developed based on a classification methods to distinguish the data set into normal class and outliers [26].”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [26] Gaura, E., Kemp, J., and Brusey, J. (2013). Leveraging knowledge from physiological data: On-body heat stress risk prediction with sensor networks. IEEE Trans. Biomed. Circuits Syst., in press. source
  Not checked in the free run.
Findingcitation
Predictive models have been used to predict further stress levels.
“As the common examples of the predictive models, authors in [38,39] presented a method which predicts the further stress levels of a subject.”
Quote in the paperNot a substantial claim0 of 2 sources checked
- cites [38] 2013, Experimental Study of the Stress Level at the Workplace Using an Smart Testbed of Wireless Sensor Networks and Ambient Intelligence Techniques, Natural and Artificial Computation in Engineering and Medical Applications source
  Not checked in the free run.
- cites [39] Gris, 2012, Activity-Aware Mental Stress Detection Using Physiological Sensors, Mobile Computing, Applications, and Services source
  Not checked in the free run.
Findingreasoning
Diagnosis systems do not necessarily use abnormal patterns in vital signs to make decisions.
“However, a distinction is that diagnosis systems are not necessarily using abnormal patterns in vital signs to make decisions.”
Quote in the paperNot a substantial claim
Findingcitation
Several new prediction works have used experimental wearable sensor data to perform non-clinical health monitoring.
“However, there are several new prediction works which have used experimental wearable sensor data to perform non clinical health monitoring [26,42].”
Quote in the paperNot a substantial claim0 of 2 sources checked
- cites [26] Gaura, E., Kemp, J., and Brusey, J. (2013). Leveraging knowledge from physiological data: On-body heat stress risk prediction with sensor networks. IEEE Trans. Biomed. Circuits Syst., in press. source
  Not checked in the free run.
- cites [42] Choi, 2012, Development and evaluation of an ambulatory stress monitor based on wearable sensors, IEEE Trans. Inf. Technol. Biomed. source
  Not checked in the free run.
Findingcitation
Diagnosis/decision making is related to anomaly detection in data mining to extract useful information from sensor data such as events, outliers, and alarms meaningful for decision.
“The diagnosis/decision making is related to the anomaly detection in data mining in order to extract useful information of sensor data such as events, outliers, and alarms which are meaningful for decision [8].”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [8] Pantelopoulos, 2010, A survey on wearable sensor-based systems for health monitoring and prognosis, Trans. Syst. Man Cyber. Part C source
  Not checked in the free run.
Findingcitation
Other parameters such as expert knowledge, historical data measurements, electronic health records, and stable parameters (e.g., sex, age) are important in data mining and machine learning methods.
“It should be noted that other parameters on data mining and machine learning methods are important such as expert knowledge, historical data measurements, electronic health records, and stable parameters (e.g., sex, age).”
Quote in the paperNot a substantial claim
Findingcitation
Papers working with large-scale and continuous data necessarily employed a preprocessing step because gathered sensor data is often unreliable and massive.
“Since the gathered sensor data is often unreliable and massive, the papers working with large scale and continuous data necessarily employed a preprocessing step [45].”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [45] Giri, 2013, Automated diagnosis of Coronary Artery Disease affected patients using LDA, PCA, ICA and Discrete Wavelet Transform, Know. Based Syst. source
  Not checked in the free run.
Findingcitation
Since wearable sensor data for vital sign parameters tend to be continuous time series readings, most considered features are related to properties of time series signals.
“Since Wearable sensor data which provide monitoring of vital sign parameters tend to be continuous time series readings, most of the considered features are related to the properties of time series signals [42].”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [42] Choi, 2012, Development and evaluation of an ambulatory stress monitor based on wearable sensors, IEEE Trans. Inf. Technol. Biomed. source
  Not checked in the free run.
Findingcitation
In the time domain, extracted features usually include basic waveform characters and statistical parameters such as mean, variance, pick counts.
“In the time domain, the extracted features usually include basic waveform characters and statistical parameters related to the visible attributes in data stream such as mean, variance, pick counts, etc. [36,61].”
Quote in the paperNot a substantial claim0 of 2 sources checked
- cites [36] Singh, R.R., Conjeti, S., and Banerjee, R. (2011, January 5–). An Approach for Real-Time Stress-Trend Detection Using Physiological Signals in Wearable Computing Systems for Automotive Drivers. Washington, DC, USA. source
  Not checked in the free run.
- cites [61] Apiletti, 2009, Real-time analysis of physiological data to support medical applications, Trans. Info. Tech. Biomed. source
  Not checked in the free run.
Findingcitation
In physiological data, time-domain features are common because traditional decision-making frameworks on vital signs are based on observable trends in the signal.
“In physiological data, the time-domain features are common, because the traditional decision making frameworks on vital signs are based on the observable trends in the signal [33].”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [33] Charbonnier, 2009, On-line adaptive trend extraction of multiple physiological signals for alarm filtering in intensive care units, Int. J. Adapt. Control. Signal. Process. source
  Not checked in the free run.
Findingcitation
For extra knowledge about periodic behavior of time series, medical research has given more attention to features from frequency domains such as power spectral density, low-pass/high-pass filters, spectral energy, and wavelet coefficients.
“However, for extra knowledge about the periodic behavior of time series, research in the medical field has given more attention to the features acquired from frequency-domains such as power spectral density, low-pass/high-pass filters, spectral energy, and wavelet coefficients of the signal [29,45].”
Quote in the paperNot a substantial claim0 of 2 sources checked
- cites [29] Nikita, 2012, Identifying Chronic Disease Complications Utilizing State of the Art Data Fusion Methodologies and Signal Processing Algorithms, Wireless Mobile Communication and Healthcare source
  Not checked in the free run.
- cites [45] Giri, 2013, Automated diagnosis of Coronary Artery Disease affected patients using LDA, PCA, ICA and Discrete Wavelet Transform, Know. Based Syst. source
  Not checked in the free run.
Findingcitation
An SVM classifier identified bad notch in subjects of chronic gastritis and arthritis with binary classifications of normal and abnormal radial pulses of ECG.
“This work identified the bad notch in the subjects of chronic gastritis and arthritis with binary classifications of normal and abnormal radial pulses of ECG using the SVM algorithm.”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [32] Thakker, 2011, Support vector machine for abnormal pulse classification, Int. J. Comput. Appl.
  Not checked in the free run.
Findingnone given
Neural networks have been applied for multi-sensor networks to handle sophisticated analysis of multivariate data.
“NN has also been applied for multi-sensor networks in order to handle the sophisticated analysis of multivariate data.”
Quote in the paperNot a substantial claim
Findingreasoning
GMM has been rarely used for prediction tasks.
“it has been rarely used for prediction tasks.”
Quote in the paperNot a substantial claim
Findingcitation
In most research in health monitoring systems, simple statistical parameters or statistical functions are adequate to formulate the data and retrieve expected information.
“In the most of research in health monitoring systems, dealing with the simple statistical parameters (e.g., mean, variance etc.) or statistical functions e.g., risk function [61], factor analysis [68]) would be adequate to formulate the data and retrieve the expected information [38].”
Quote in the paperNot a substantial claim0 of 3 sources checked
- cites [61] Apiletti, 2009, Real-time analysis of physiological data to support medical applications, Trans. Info. Tech. Biomed. source
  Not checked in the free run.
- cites [68] Pradhan, G.N., Chattopadhyay, R., and Panchanathan, S. (2010, January 29–31). Processing Body Sensor Data Streams for Continuous Physiological Monitoring. Philadelphia, PA, USA. source
  Not checked in the free run.
- cites [38] 2013, Experimental Study of the Stress Level at the Workplace Using an Smart Testbed of Wireless Sensor Networks and Ambient Intelligence Techniques, Natural and Artificial Computation in Engineering and Medical Applications source
  Not checked in the free run.
Findingnone given
Statistical tools have been used in clinical conditions with short term data to monitor principal changes in the data stream.
“they have been used in clinical conditions with short term data in order to monitor the principal changes in the data stream.”
Quote in the paperNot a substantial claim
Findingnone given
Experimental studies usually do not provide precise annotations and meaningful labels on physiological signals.
“but usually these studies do not provide the precise annotations and meaningful labels on physiological signals.”
Quote in the paperNot a substantial claim
Findingcitation
Several studies in this area have used stored clinical data sets.
“several studies in this area have used the stored clinical data sets [31,89].”
Quote in the paperNot a substantial claim0 of 2 sources checked
- cites [31] Clifton, 2013, Gaussian processes for personalized e-health monitoring with wearable sensors, IEEE Trans. Biomed. Eng. source
  Not checked in the free run.
- cites [89] Salem, O., Liu, Y., and Mehaoua, A. (2013, January 7–10). A Lightweight Anomaly Detection Framework for Medical Wireless Sensor Networks. Shanghai, China. source
  Not checked in the free run.
Findingcitation
Papers that have developed health monitoring systems have mostly used their own data gathering experiments to design, model and test the data analysis step.
“The papers which have developed the health monitoring systems have mostly used their own data gathering experiments to design, model and test the data analysis step [26,38,88].”
Quote in the paperNot a substantial claim0 of 3 sources checked
- cites [26] Gaura, E., Kemp, J., and Brusey, J. (2013). Leveraging knowledge from physiological data: On-body heat stress risk prediction with sensor networks. IEEE Trans. Biomed. Circuits Syst., in press. source
  Not checked in the free run.
- cites [38] 2013, Experimental Study of the Stress Level at the Workplace Using an Smart Testbed of Wireless Sensor Networks and Ambient Intelligence Techniques, Natural and Artificial Computation in Engineering and Medical Applications source
  Not checked in the free run.
- cites [88] Scully, 2012, Physiological parameter monitoring from optical recordings with a mobile phone, IEEE Trans. Biomed. Eng. source
  Not checked in the free run.
Findingcitation
Most works used categorized and complex multivariate data sets with formal definitions and annotations by domain experts to evaluate quantitatively and test the performance of output decisions.
“the most of the works used categorized and complex multivariate data sets with formal definitions and annotations by domain expert [30,40,45].”
Quote in the paperNot a substantial claim0 of 3 sources checked
- cites [30] Huang, G., Zhang, Y., Cao, J., Steyn, M., and Taraporewalla, K. (2013). Online mining abnormal period patterns from multiple medical sensor data streams. World Wide Web. source
  Not checked in the free run.
- cites [40] Marlin, B.M., Kale, D.C., Khemani, R.G., and Wetzel, R.C. (, January January). Unsupervised Pattern Discovery in Electronic Health Care Data Using Probabilistic Clustering Models. Miami, FL, USA.
  Not checked in the free run.
- cites [45] Giri, 2013, Automated diagnosis of Coronary Artery Disease affected patients using LDA, PCA, ICA and Discrete Wavelet Transform, Know. Based Syst. source
  Not checked in the free run.
Findingcitation
Few works have designed and tested their data mining methods through simulated physiological data.
“For the sake of having a wide controlled analysis system, few works have designed and tested their data mining methods through shapely simulated physiological data [49].”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [49] Vu, 2010, Online discovery of Heart Rate Variability patterns in mobile healthcare services, J. Syst. Softw. source
  Not checked in the free run.
Findingcitation
Some data analysis systems in healthcare were designed to process short signals such as few minutes of ECG data, a few hours of heart rate or oxygen saturation, and measurement of blood pressures for a day.
“Some data analysis systems in healthcare were designed to process short signals such as few minutes of ECG data [74,92], a few hours of heart rate or oxygen saturation [60,61] and the measurement of blood pressures for a day [56].”
Quote in the paperNot a substantial claim0 of 5 sources checked
- cites [74] Jin, Z., Sun, Y., and Cheng, A.C. (2009, January 3–6). Predicting Cardiovascular Disease From Real-Time Electrocardiographic Monitoring: An Adaptive Machine Learning Approach on a Cell Phone.
  Not checked in the free run.
- cites [92] Patel, 2012, Real time ECG feature extraction and arrhythmia detection on a mobile platform, Int. J. Comput. Appl.
  Not checked in the free run.
- cites [60] Mao, Y., Chen, W., Chen, Y., Lu, C., Kollef, M., and Bailey, T. (2012, January 16–18). An Integrated Data Mining Approach to Real-Time Clinical Monitoring and Deterioration Warning. Beijing, China. source
  Not checked in the free run.
- cites [61] Apiletti, 2009, Real-time analysis of physiological data to support medical applications, Trans. Info. Tech. Biomed. source
  Not checked in the free run.
- cites [56] Ahmad, N.F., Hoang, D.B., and Phung, M.H. (2009, January 16–18). Robust Preprocessing for Health Care Monitoring Framework. Sydney, Australia. source
  Not checked in the free run.
Findingreasoning
Another group of papers focused on small scale of subjects (maybe one or at most 10 persons) to investigate the accuracy and correctness of results in the proposed model.
“Due to the type of data mining tools, another group of papers focused on small scale of subjects (maybe one or at most 10 persons) in order to investigate the accuracy and correctness of results in proposed model [27,53].”
Quote in the paperNot a substantial claim0 of 2 sources checked
- cites [27] Lee, 2012, Low-energy formulations of support vector machine kernel functions for biomedical sensor applications, J. Signal Process. Syst. source
  Not checked in the free run.
- cites [53] Naraharisetti, K.V.P., Bawa, M., and Tahernezhadi, M. (2011, January 15–17). Comparison of Different Signal Processing Methods for Reducing Artifacts from Photoplethysmograph Signal. Mankato, MN, USA. source
  Not checked in the free run.
Findingcitation
Some research has been done on unlabeled data to consider uncontrolled situations, especially for experimental data sets.
“Some researches have been done on unlabeled data in order to consider uncontrolled situations for especially experimental data sets [39,44,88].”
Quote in the paperNot a substantial claim0 of 3 sources checked
- cites [39] Gris, 2012, Activity-Aware Mental Stress Detection Using Physiological Sensors, Mobile Computing, Applications, and Services source
  Not checked in the free run.
- cites [44] Nikita, 2012, A Support Vector Machine Approach for Categorization of Patients Suffering from Chronic Diseases, Wireless Mobile Communication and Healthcare source
  Not checked in the free run.
- cites [88] Scully, 2012, Physiological parameter monitoring from optical recordings with a mobile phone, IEEE Trans. Biomed. Eng. source
  Not checked in the free run.
Findingcitation
Usually single sensor data have been used for specific analysis on individual physiological data such as ECG signal analysis or blood glucose monitoring.
“Usually single sensor data have been used for specific analysis on individual physiological data such as ECG signal analysis [32,54,92] or blood glucose monitoring [23,28].”
Quote in the paperNot a substantial claim0 of 5 sources checked
- cites [32] Thakker, 2011, Support vector machine for abnormal pulse classification, Int. J. Comput. Appl.
  Not checked in the free run.
- cites [54] Ding, H., Sun, H., and mean Hou, K. (2011, January 9–11). Abnormal ECG Signal Detection Based on Compressed Sampling in Wearable ECG Sensor. Nanjing, China. source
  Not checked in the free run.
- cites [92] Patel, 2012, Real time ECG feature extraction and arrhythmia detection on a mobile platform, Int. J. Comput. Appl.
  Not checked in the free run.
- cites [23] Chatterjee, S., Dutta, K., Xie, H.Q., Byun, J., Pottathil, A., and Moore, M. (2013, January 7–10). Persuasive and Pervasive Sensing: A New Frontier to Monitor, Track and Assist Older Adults Suffering from Type-2 Diabetes. Grand Wailea, Maui, HI, USA. source
  Not checked in the free run.
- cites [28] Zhu, 2011, Automatic detection of anomalies in blood glucose using a machine learning approach, J. Commun. Netw. source
  Not checked in the free run.
Findingown data
More attention has been given to short term data sets, which can be easily recorded and analyzed for straightforward solutions in both experimental and clinical conditions.
“As can be seen from Figure 5, more attention has been given to short term data sets which can be easily recorded and analyzed for straightforward solutions in both experimental and clinical conditions.”
Quote in the paperNot a substantial claim
Findingreasoning
In a clinical setting and online databases, data is mostly characterized as continuous and labelled.
“In a clinical setting and online databases, data is mostly characterized as continuous and labelled (as access to the experts and other health profiles is readily available).”
Quote in the paperNot a substantial claim
Findingcitation
Most research has used several sensors to have global reasoning in health monitoring.
“Besides the works focusing on physiological data mining gathered from a single sensor, most of the researches have used several sensors [30,40,44,67] to have global reasoning in health monitoring.”
Quote in the paperNot a substantial claim0 of 4 sources checked
- cites [30] Huang, G., Zhang, Y., Cao, J., Steyn, M., and Taraporewalla, K. (2013). Online mining abnormal period patterns from multiple medical sensor data streams. World Wide Web. source
  Not checked in the free run.
- cites [40] Marlin, B.M., Kale, D.C., Khemani, R.G., and Wetzel, R.C. (, January January). Unsupervised Pattern Discovery in Electronic Health Care Data Using Probabilistic Clustering Models. Miami, FL, USA.
  Not checked in the free run.
- cites [44] Nikita, 2012, A Support Vector Machine Approach for Categorization of Patients Suffering from Chronic Diseases, Wireless Mobile Communication and Healthcare source
  Not checked in the free run.
- cites [67] Li, X., and Porikli, F. (2010, January 23–26). Human State Classification and Predication for Critical Care Monitoring by Real-Time Bio-signal Analysis. Istanbul, Turkey. source
  Not checked in the free run.
Findingreasoning
Large scale data sets are more popular than small scale for most health parameters, except ECG and BG due to the high frequency of available data sets in online databases.
“For the scale property, the large scale data sets are more popular than the small scale for most of the health parameters, except ECG and BG due to the fact that they contain the high frequency of available data sets in online databases.”
Quote in the paperNot a substantial claim
Findingnone given
For anomaly detection tasks, SVM, HMM, statistical tools and frequency analysis are more commonly applied.
“According to the considered data mining tasks in Section 3, for anomaly detection task, SVM, HMM, statistical tools and frequency analysis are more commonly applied.”
Quote in the paperSubstantial claim
Findingnone given
Neural networks have not been addressed to detect anomalies.
“Nevertheless, NN has not been addressed to detect anomalies.”
Quote in the paperSubstantial claim
Findingnone given
Prediction tasks have often used decision tree methods as well as other supervised techniques.
“Prediction tasks on the other hand, have often used decision tree methods as well as other supervised techniques.”
Quote in the paperNot a substantial claim
Findingnone given
Few benchmark data sets are available in the area of data mining for wearable sensors in health monitoring.
“Still however in this area few benchmark data sets are available.”
Quote in the paperSubstantial claim
- Rests on an assumption: The literature study performed here is sufficient to identify general challenges in the field of health monitoring.
Findingcitation
Works [101,102] have demonstrated the possible uses of systems combining classical data mining techniques with natural language generation in both clinical and experimental contexts.
“Works such as [101,102] have demonstrated the possible uses of such systems in both clinical and experimental contexts.”
Quote in the paperNot a substantial claim0 of 2 sources checked
- cites [101] Banaee, H., Ahmed, M.U., and Loutfi, A. (2013, January 13–16). A Framework for Automatic Text Generation of Trends in Physiological Time Series Data. Manchester, UK. source
  Not checked in the free run.
- cites [102] Hunter, 2012, Automatic generation of natural language nursing shift summaries in neonatal intensive care: BT-Nurse, Artif. Intell. Med. source
  Not checked in the free run.
- Rests on an assumption: The literature study performed here is sufficient to identify general challenges in the field of health monitoring.
Interpretationreasoning
These issues lead to investigation of data mining tasks such as data cleaning, noise removing, data filtering, and compressing as part of any physiological data monitoring framework.
“Considering these issues leads to investigate some data mining tasks such as data cleaning, noise removing, data filtering and compressing as a part of any physiological data monitoring frameworks.”
Quote in the paperNot a substantial claim
Interpretationcitation
These kinds of tasks appeared because real-world health monitoring systems usually deal with unlabeled and continuous data.
“These kinds of tasks appeared due to this fact that of real-world health monitoring systems are usually dealing with unlabeled and continuous data [17].”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [17] Chan, 2012, Smart wearable systems: Current status and future challenges, Artif. Intell. Med. source
  Not checked in the free run.
Interpretationreasoning
Due to noise, motion artifacts, and sensor errors in any wearable sensor network, preprocessing of raw data is necessary.
“Due to the occurrence of noise, motion artifacts, and sensor errors in any wearable sensor networks, a preprocessing of the raw data is necessary.”
Quote in the paperSubstantial claim
Premisecitation
Neural networks can model highly nonlinear systems such as physiological records where the correlation of input parameters is not easily detectable.
“The ability of the NN is to model highly nonlinear systems such as physiological records where the correlation of the input parameters is not easily detectable [71].”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [71] Amato, 2013, Artificial neural networks in medical diagnosis, J Appl. Biomed. source
  Not checked in the free run.
Interpretationreasoning
Neural networks are not a portable technique to easily apply for diverse data sets.
“So, NN is not counted as a portable technique to easily apply for diverse data sets.”
Quote in the paperNot a substantial claim
Interpretationreasoning
Applying GMM in real-time frameworks is not affordable because the computation time of constructing the models is high.
“Since the computation time of constructing the models is high, applying GMM in real-time frameworks is not affordable.”
Quote in the paperNot a substantial claim
Interpretationreasoning
Rule-based methods cannot handle complex physiological data in real-world experiments with unexpected patterns.
“Moreover, they could not handle complex physiological data in real world experiments with unexpected patterns.”
Quote in the paperNot a substantial claim
Premisecitation
Analysis of time series data in the frequency domain enables extraction of unseen patterns and trends across data.
“Analysis of time series data in the frequency domain enables to extract unseen patterns and trends across data [87].”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [87] Chaovalit, 2011, Discrete Wavelet transform-based time series analysis and mining, ACM Comput. Surv. source
  Not checked in the free run.
Interpretationreasoning
Frequency domain techniques are not appropriate for real-time decision making systems because computational times are high.
“However, since the computational times in these techniques are high, it is not an appropriate to use these tools for real-time decision making systems.”
Quote in the paperNot a substantial claim
Interpretationcitation
Another reason to create and use simulated data is the lack of long term and large scale data sets.
“Another reason to create and use simulated data is the lack of long term and large scale data sets [28] which helps the proposed data mining systems to deal with huge amount of data.”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [28] Zhu, 2011, Automatic detection of anomalies in blood glucose using a machine learning approach, J. Commun. Netw. source
  Not checked in the free run.
Interpretationreasoning
Rule-based methods, GMM, and frequency analysis are not the most appropriate methods for prediction due to shortcomings in modeling data behaviors.
“It was shown that rule-based methods, GMM, and frequency analysis are not the most appropriate methods for predication due to the shortcoming in modeling the data behaviors.”
Quote in the paperSubstantial claim
Interpretationreasoning
The selected data mining technique is highly dependent on the data mining task to be performed.
“The selected data mining technique is highly dependent on the data mining task to be performed.”
Quote in the paperSubstantial claim
Interpretationreasoning
NN, GMM, and frequency analysis are not efficient for real-time health monitoring systems because of their computational complexity.
“To design a real-time health monitoring system, such methods like NN, GMM, and frequency analysis are not efficient for the sake of their computational complexities.”
Quote in the paperNot a substantial claim

May combine two claims. 50
Classified as probably not a substantial claim. 110

May combine two claims.
Findingnone given
Equal emphasis is placed on anomaly detection and diagnosis and less attention on prediction.
“Equal emphasis is placed on anomaly detection and diagnosis and less attention put on prediction.”
Quote in the paperNot a substantial claim
May combine two claims.
Findingcitation
All three tasks have been addressed both online and offline, with more alarm-related tasks used in online and continuous monitoring.
“For all three tasks data has been addressed both in an online and offline manner, with more alarm related tasks being naturally used in the context of online and continuous monitoring [1].”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [1] Aggarwal, C.C. (2013). Managing and Mining Sensor Data, Springer. source
  Not checked in the free run.
May combine two claims.
Findingreasoning
For patients with known medical records, diagnosis and raising alarms are key tasks.
“For patients with known medical records, both diagnosis and specifically the possibility to raise alarms are key tasks.”
Quote in the paperNot a substantial claim
May combine two claims.
Findingcitation
Most home or remote monitoring applications deal predominantly with prediction and anomaly detection, whereas clinical applications typically focus on diagnosis.
“Based on the literature, most monitoring applications which consider home settings or remote monitoring deal predominantly with prediction and anomaly detection whereas the applications in clinical settings are typically focused on diagnosis [10,21].”
Quote in the paperNot a substantial claim0 of 2 sources checked
- cites [10] Baig, 2013, Smart health monitoring systems: An overview of design and modeling, J. Med. Syst. source
  Not checked in the free run.
- cites [21] Stacey, 2007, Temporal abstraction in intelligent clinical data analysis: A survey, Artif. Intell. Med. source
  Not checked in the free run.
May combine two claims.
Findingcitation
Anomaly detection can use offline techniques to detect abnormal readings for each individual based on historical measurements, since abnormal patterns can differ per subject.
“However, anomaly detection task could use offline techniques in order to detect abnormal reading for each individual based on the historical measurements for the person [28], since the definition of the abnormal patterns can be different for each subject.”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [28] Zhu, 2011, Automatic detection of anomalies in blood glucose using a machine learning approach, J. Commun. Netw. source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Findingcitation
In online health monitoring systems, raising an alarm as soon as an anomaly in vital signs is detected triggers instant reaction, and such alarm systems are usually designed for monitoring patients in clinical units.
“In online health monitoring systems, raising alarm as soon as detecting any anomaly in vital signs will be triggered to have instant reaction and such alarm system are usually designed for monitoring patients in clinical units [33].”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [33] Charbonnier, 2009, On-line adaptive trend extraction of multiple physiological signals for alarm filtering in intensive care units, Int. J. Adapt. Control. Signal. Process. source
  Not checked in the free run.
May combine two claims.
Findingcitation
Predictive data mining is getting more interest from healthcare providers because it helps prevent further chronic problems and can lead to prognosis decisions.
“This approach is getting more and more interest for the healthcare providers in the medical domain since it helps to prevent further chronic problems [18] and could lead to a decision about prognosis [37].”
Quote in the paperNot a substantial claim0 of 2 sources checked
- cites [18] Bellazzi, 2011, Predictive data mining in clinical medicine: A focus on selected methods and applications, Wiley. Interdiscip. Rev.: Data. Min. Knowl. Discov.
  Not checked in the free run.
- cites [37] Bellazzi, 2008, Predictive data mining in clinical medicine: Current issues and guidelines, Int. J. Med. Inform. source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Findingcitation
Predictive models in healthcare include blood glucose level prediction, mortality prediction by clustering electronic health data, and a predictive decision making system for dialysis patients.
“A similar example of using predictive models in healthcare are: blood glucose level prediction [23], mortality prediction by clustering electronic health data [40], and a predictive decision making system for dialysis patients [41].”
Quote in the paperNot a substantial claim0 of 3 sources checked
- cites [23] Chatterjee, S., Dutta, K., Xie, H.Q., Byun, J., Pottathil, A., and Moore, M. (2013, January 7–10). Persuasive and Pervasive Sensing: A New Frontier to Monitor, Track and Assist Older Adults Suffering from Type-2 Diabetes. Grand Wailea, Maui, HI, USA. source
  Not checked in the free run.
- cites [40] Marlin, B.M., Kale, D.C., Khemani, R.G., and Wetzel, R.C. (, January January). Unsupervised Pattern Discovery in Electronic Health Care Data Using Probabilistic Clustering Models. Miami, FL, USA.
  Not checked in the free run.
- cites [41] Yeh, 2011, Using data mining techniques to predict hospitalization of hemodialysis patients, Decis. Support Syst. source
  Not checked in the free run.
May combine two claims.
Findingcitation
Recent works in diagnosis/decision making involve estimating severity of health episodes of patients with chronic disease, sleep issues such as polysomnography and apnea, estimation and classification of health conditions, and emotion recognition.
“Some examples of recent works in this area involve estimating the severity of health episodes of patients suffering chronic disease [44–46], sleep issues such as polysomnography and apnea [47,48], estimation and classification of health conditions [49,50], and emotion recognition [51].”
Quote in the paperNot a substantial claim0 of 7 sources checked
- cites [44] Nikita, 2012, A Support Vector Machine Approach for Categorization of Patients Suffering from Chronic Diseases, Wireless Mobile Communication and Healthcare source
  Not checked in the free run.
- cites [45] Giri, 2013, Automated diagnosis of Coronary Artery Disease affected patients using LDA, PCA, ICA and Discrete Wavelet Transform, Know. Based Syst. source
  Not checked in the free run.
- cites [46] Bellos, C., Papadopoulos, A., Rosso, R., and Fotiadis, D.I. (2012, January 5–7). Categorization of Patients' Health Status in Copd Disease Using a Wearable Platform and Random Forests Methodology. Shenzhen, China. source
  Not checked in the free run.
- cites [47] Bianchi, 2010, Processing of signals recorded through smart devices: Sleep-quality assessment, IEEE Trans. Inf. Technol. Biomed. source
  Not checked in the free run.
- cites [48] Xie, 2012, Real-time sleep apnea detection by classifier combination, IEEE Trans. Inf. Technol. Biomed. source
  Not checked in the free run.
- cites [49] Vu, 2010, Online discovery of Heart Rate Variability patterns in mobile healthcare services, J. Syst. Softw. source
  Not checked in the free run.
- cites [50] Pantelopoulos, 2010, Prognosis—a wearable health-monitoring system for people at risk: Methodology and modeling, IEEE Trans. Inf. Technol. Biomed. source
  Not checked in the free run.
May combine two claims.
Findingcitation
Decision making in diagnosis is one of the main tasks of clinical monitoring systems and is often based on retrieved knowledge using vital signs and other information such as electronic health records and metadata.
“Decision making in diagnosis is one of the main tasks of clinical monitoring systems which is often based on retrieved knowledge using vital signs, and also other information such as electronic health records and metadata [43].”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [43] Sneha, 2009, Enabling ubiquitous patient monitoring: Model, decision protocols, opportunities and challenges, Decis. Support Syst. source
  Not checked in the free run.
May combine two claims.
Findingcitation
Several data mining techniques are applied for these tasks: wavelet analysis for artifact reduction and data compression, rule-based methods for data summarizing and transmitting, and Gaussian process for secure authentication.
“In order to conduct these problems, several data mining techniques are applied such as wavelet analysis for artifact reduction [53] and data compression [54], rule-based methods for data summarizing and transmitting [55,56], and Gaussian process for secure authentication [57].”
Quote in the paperNot a substantial claim0 of 4 sources checked
- cites [53] Naraharisetti, K.V.P., Bawa, M., and Tahernezhadi, M. (2011, January 15–17). Comparison of Different Signal Processing Methods for Reducing Artifacts from Photoplethysmograph Signal. Mankato, MN, USA. source
  Not checked in the free run.
- cites [54] Ding, H., Sun, H., and mean Hou, K. (2011, January 9–11). Abnormal ECG Signal Detection Based on Compressed Sampling in Wearable ECG Sensor. Nanjing, China. source
  Not checked in the free run.
- cites [55] Yoon, J. (2013, January 23–28). Three-Tiered Data Mining for Big Data Patterns of Wireless Sensor Networks in Medical and Healthcare Domains. Rome, Italy.
  Not checked in the free run.
- cites [56] Ahmad, N.F., Hoang, D.B., and Phung, M.H. (2009, January 16–18). Robust Preprocessing for Health Care Monitoring Framework. Sydney, Australia. source
  Not checked in the free run.
May combine two claims.
Findingcitation
Most healthcare systems deal with data acquisition using adequate sensor set, transmission from subject to clinician, integration with other descriptive data, and data storage.
“According to [1,19], most healthcare systems are dealing with the following issues: (1) data acquisition using the adequate sensor set; (2) transmission of data from subject to clinician; (3) integration of data with other descriptive data; and (4) data storage.”
Quote in the paperNot a substantial claim0 of 2 sources checked
- cites [1] Aggarwal, C.C. (2013). Managing and Mining Sensor Data, Springer. source
  Not checked in the free run.
- cites [19] Nangalia, 2010, Health technology assessment review: Remote monitoring of vital signs—current status and future challenges, Crit. Care source
  Not checked in the free run.
May combine two claims.
Findingnone given
The main role of data mining in healthcare monitoring systems is retrieving information (anomaly detection, prediction, and diagnosis decision making), and there are several other tasks data mining methods can carry out with wearable sensors.
“The main role of data mining in healthcare monitoring systems is retrieving information (i.e., anomaly detection, prediction and diagnosis decision making), and there are several tasks considering wearable sensors that data mining methods are able to carry out.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing).
Findingnone given
The most standard and widely used approach to mining information from wearable sensors consists of data preprocessing, feature extraction and selection, and modelling data learning the input features to perform detection, prediction, and decision making.
“The main steps of the data mining approach consist (1) data preprocessing; (2) feature extraction and selection; and (3) modelling data learning the input features (considering expert knowledge and metadata) to perform the tasks such as detection, prediction, and decision making.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing).
Findingnone given
Most of these diagnosis researches used online databases with annotated episodes to have sufficient and trustable real-world disease labels to evaluate decision making.
“Most of these researches have used online databases with annotated episodes in order to have sufficient and trustable real-world disease labels to evaluate the decision making process.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.
Findingnone given
Data mining techniques applied to wearable sensor data in health monitoring systems have varied, and it is not uncommon that several techniques are used within the same architecture.
“Data mining techniques that have been applied to wearable sensor data in health monitoring systems have varied and it is also not uncommon that several techniques are used within the same architecture.”
Quote in the paperNot a substantial claim
May combine two claims.
Findingcitation
Metadata provides contextual analysis and improves the process of knowledge extraction.
“This metadata provides contextual analysis and improves the process of knowledge extraction [29,57].”
Quote in the paperNot a substantial claim0 of 2 sources checked
- cites [29] Nikita, 2012, Identifying Chronic Disease Complications Utilizing State of the Art Data Fusion Methodologies and Signal Processing Algorithms, Wireless Mobile Communication and Healthcare source
  Not checked in the free run.
- cites [57] Wang, 2011, Secure stochastic ECG signals based on gaussian mixture model for e-healthcare systems, IEEE Syst. J. source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Findingreasoning
Recent health monitoring systems have given more attention to the data processing phase to catch more valuable information based on expert user requirements.
“For this reason recent health monitoring systems have given more attention to the data processing phase in order to catch more valuable information based on the expert user requirements.”
Quote in the paperNot a substantial claim
May combine two claims.
Findingcitation
For filtering artifacts, designed modules have usually applied threshold-based methods or used statistical tools to interpolate missing data points.
“According to the literature, for filtering artifacts, designed modules have usually applied threshold-based methods to filter sensor data [36,60] or used statistical tools to interpolate the missing data points [61].”
Quote in the paperNot a substantial claim0 of 3 sources checked
- cites [36] Singh, R.R., Conjeti, S., and Banerjee, R. (2011, January 5–). An Approach for Real-Time Stress-Trend Detection Using Physiological Signals in Wearable Computing Systems for Automotive Drivers. Washington, DC, USA. source
  Not checked in the free run.
- cites [60] Mao, Y., Chen, W., Chen, Y., Lu, C., Kollef, M., and Bailey, T. (2012, January 16–18). An Integrated Data Mining Approach to Real-Time Clinical Monitoring and Deterioration Warning. Beijing, China. source
  Not checked in the free run.
- cites [61] Apiletti, 2009, Real-time analysis of physiological data to support medical applications, Trans. Info. Tech. Biomed. source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Findingcitation
In ECG data, several works have been done to improve signal quality for accurate analysis.
“For example in ECG data, several works have been done to improve the quality of signals for accurate analysis [29,32].”
Quote in the paperNot a substantial claim0 of 2 sources checked
- cites [29] Nikita, 2012, Identifying Chronic Disease Complications Utilizing State of the Art Data Fusion Methodologies and Signal Processing Algorithms, Wireless Mobile Communication and Healthcare source
  Not checked in the free run.
- cites [32] Thakker, 2011, Support vector machine for abnormal pulse classification, Int. J. Comput. Appl.
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Findingcitation
Preprocessing in healthcare involves filtering unusual data to remove artifacts and removing high-frequency noise.
“Preprocessing in the healthcare domain involves (1) filter unusual data to remove artifacts and (2) remove high frequency noise [1,13].”
Quote in the paperNot a substantial claim0 of 2 sources checked
- cites [1] Aggarwal, C.C. (2013). Managing and Mining Sensor Data, Springer. source
  Not checked in the free run.
- cites [13] Lara, 2013, A survey on ambient-assisted living tools for older adults, IEEE Commun. Surv. Tutor. source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Findingcitation
To remove frequency noise, methods in frequency domain such as PSD, FFT, and low-pass/high-pass filtering are common to remove fluctuations in sensor signals.
“To remove frequency noise, the other methods in frequency domain such as such as power spectral density (PSD) fast Fourier transforms (FFT), and low-pass/high-pass filtering tools are common to remove the fluctuations in sensor signals [51,62].”
Quote in the paperNot a substantial claim0 of 2 sources checked
- cites [51] Frantzidis, 2010, On the classification of emotional biosignals evoked while viewing affective pictures: An integrated data-mining-based approach for healthcare applications, Trans. Inf. Tech. Biomed. source
  Not checked in the free run.
- cites [62] Hu, 2008, medical ad hoc sensor networks (MASN) with wavelet-based ECG data mining, Ad Hoc Robust Netw. source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Findingnone given
There is no tailored work considering these preprocessing issues in detail for real-life scenarios.
“However, there is no tailored work considering these issues in detail for real life scenarios.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing).
Findingcitation
Reducing the amount of sensor network data is another task in feature extraction and feature selection phases, leading to an arranged vector of features as input to data mining techniques like classifiers.
“Moreover, reducing the amount of sensor network data is another task in feature extraction and feature selection phases which leads to have an arranged vector of features as an input of data mining techniques like classifier methods [45,60].”
Quote in the paperNot a substantial claim0 of 2 sources checked
- cites [45] Giri, 2013, Automated diagnosis of Coronary Artery Disease affected patients using LDA, PCA, ICA and Discrete Wavelet Transform, Know. Based Syst. source
  Not checked in the free run.
- cites [60] Mao, Y., Chen, W., Chen, Y., Lu, C., Kollef, M., and Bailey, T. (2012, January 16–18). An Integrated Data Mining Approach to Real-Time Clinical Monitoring and Deterioration Warning. Beijing, China. source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Findingcitation
Feature extraction provides a meaningful representation of wearable sensor data that can formulate the relation of raw data with expected knowledge for decision making.
“Especially in wearable sensor data, according to the magnitude and complexity of the raw data, feature extraction provides a meaningful representation of the sensor data which can formulate the relation of raw data with the expected knowledge for decision making [64].”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [64] Bellos, C.C., Papadopoulos, A., Rosso, R., and Fotiadis, D.I. (2010, January 3–5). Extraction and Analysis of Features Acquired By Wearable Sensors Network. Corfu, Greece. source
  Not checked in the free run.
May combine two claims.
Findingcitation
The main challenges of the preprocessing phase in healthcare systems include data formatting, data normalization, and data synchronization.
“The main challenges of the preprocessing phase in healthcare systems are addressed in [1] which includes data formatting, data normalization, and data synchronization.”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [1] Aggarwal, C.C. (2013). Managing and Mining Sensor Data, Springer. source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Findingcitation
Two main aspects of analyzing signals are time domain and spectral domain.
“Two main aspects of analyzing signals are time domain and spectral domain [14].”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [14] Avci, A., Bosch, S., Marin-Perianu, M., Marin-Perianu, R., and Havinga, P. (2010, January 22–23). Activity Recognition Using Inertial Sensing for Healthcare, Wellbeing and Sports Applications: A Survey. Hannover, Germany.
  Not checked in the free run.
May combine two claims.
Findingcitation
Three most popular approaches for dimension reduction in medical domain are PCA, ICA, and LDA, which statistically select the subset of most significant features.
“Three most popular approaches for dimension reduction in medical domain are PCA, ICA, and LDA [66] which are statistically selecting the subset of the most significant features [45,67].”
Quote in the paperNot a substantial claim0 of 3 sources checked
- cites [66] Widodo, 2007, Application of nonlinear feature extraction and support vector machines for fault diagnosis of induction motors, Expert Syst. Appl. source
  Not checked in the free run.
- cites [45] Giri, 2013, Automated diagnosis of Coronary Artery Disease affected patients using LDA, PCA, ICA and Discrete Wavelet Transform, Know. Based Syst. source
  Not checked in the free run.
- cites [67] Li, X., and Porikli, F. (2010, January 23–26). Human State Classification and Predication for Critical Care Monitoring by Real-Time Bio-signal Analysis. Istanbul, Turkey. source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Findingreasoning
For physiological data, using feature selection techniques leads to reducing the dimensions of input data.
“For physiological data, using feature selection techniques leads to reduce the dimensions of input data.”
Quote in the paperNot a substantial claim
May combine two claims.
Findingcitation
For ECG signals, although Bsoul et al. proposed dozens of features, the main focus of research is to consider R points and their properties such as R-R intervals and pick counts.
“As an example, for the works studying ECG signals, although Bsoul et al. [65] have proposed dozens of features, the main focus of research is to consider R points (the pick point of each beat), and its properties in ECG pulses such as R-R intervals, pick counts, etc. [39,64].”
Quote in the paperNot a substantial claim0 of 3 sources checked
- cites [65] Bsoul, 2011, Apnea medassist: Real-time sleep apnea monitor using single-lead ECG, IEEE Trans. Inf. Technol. Biomed. source
  Not checked in the free run.
- cites [39] Gris, 2012, Activity-Aware Mental Stress Detection Using Physiological Sensors, Mobile Computing, Applications, and Services source
  Not checked in the free run.
- cites [64] Bellos, C.C., Papadopoulos, A., Rosso, R., and Fotiadis, D.I. (2010, January 3–5). Extraction and Analysis of Features Acquired By Wearable Sensors Network. Corfu, Greece. source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Findingcitation
Besides time and frequency domain features, other considered features include heuristic and specific field features.
“Besides the features from these domains, there are other considered features which such as heuristic and specific field features [61].”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [61] Apiletti, 2009, Real-time analysis of physiological data to support medical applications, Trans. Info. Tech. Biomed. source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Findingcitation
Other tools for feature selection used in literature include threshold-based rules, ANOVA, and Fourier transforms.
“Other tools for feature selection used in the literature includes threshold-based rules [61], analysis of variance (ANOVA) [51], and Fourier transforms [52].”
Quote in the paperNot a substantial claim0 of 3 sources checked
- cites [61] Apiletti, 2009, Real-time analysis of physiological data to support medical applications, Trans. Info. Tech. Biomed. source
  Not checked in the free run.
- cites [51] Frantzidis, 2010, On the classification of emotional biosignals evoked while viewing affective pictures: An integrated data-mining-based approach for healthcare applications, Trans. Inf. Tech. Biomed. source
  Not checked in the free run.
- cites [52] Karlen, 2009, Sleep and wake classification with ECG and respiratory effort signals, IEEE Trans. Biomed. Circuits Syst. source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Findingcitation
An SVM method was developed for detecting arrhythmia and seizure episodes in ECG signals.
“Similarly, [27] developed an SVM method for detecting the arrhythmia and seizure episodes while ECG signals.”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [27] Lee, 2012, Low-energy formulations of support vector machine kernel functions for biomedical sensor applications, J. Signal Process. Syst. source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Findingnone given
When multiple sensors are used, the data is multivariate with possible dependencies.
“Further, when multiple sensors are used, this data is multivariate with possible dependencies.”
Quote in the paperNot a substantial claim
May combine two claims.
Findingreasoning
Although most proposed frameworks in healthcare contain feature extraction/selection phases, the main challenge is to balance between optimum feature extraction/selection methods and their costs for the system.
“Although most of the proposed frameworks in the healthcare domain contain feature extraction/selection phases, the main challenge still is to balance between the optimum feature extraction/selection methods and their costs for the system.”
Quote in the paperSubstantial claim
Classified as probably not a substantial claim.
Findingreasoning
The solution to balancing feature extraction/selection and costs is still to be addressed in recent research.
“However, its solution is still to be addressed in recent research.”
Quote in the paperSubstantial claim
Probably not a substantial claim: may not pass S3 (load-bearing).
Findingcitation
Hu et al. used SVM to find arrhythmia in ECG signals.
“Hu et al. [62] used SVM to find out arrhythmia in ECG signals.”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [62] Hu, 2008, medical ad hoc sensor networks (MASN) with wavelet-based ECG data mining, Ad Hoc Robust Netw. source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Findingnone given
When sensors are deployed in applications such as home monitoring, a large amount of data can be generated.
“When such sensors are deployed in applications such as home monitoring, a large amount of data can be generated.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing).
Findingcitation
Hu et al. applied a binary classifier version of SVM to categorize ECG signals into normal and arrhythmia classes.
“It applied a binary classifier version of SVM to categorize ECG signals into normal and arrhythmia classes.”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [62] Hu, 2008, medical ad hoc sensor networks (MASN) with wavelet-based ECG data mining, Ad Hoc Robust Netw. source
  Not checked in the free run.
May combine two claims.
Findingnone given
Common health parameters considered by SVM methods are ECG, HR, and SpO2, mostly used in short-term and annotated form.
“Common health parameters considered by SVM methods are ECG, HR, and SpO2 which are mostly used in the short term and annotated form.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Findingnone given
SVM has the ability to handle high-dimensional data using a minimal training set of features, and it is recently very popular for mining physiological data in medical applications.
“As the SVM has the ability to handle high dimensional data using minimal training set of features, it is recently very popular for mining physiological data in medical applications.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing).
Findingcitation
Several binary SVMs with different kernels such as RBF, polynomial, and sigmoid were combined to model input data from multi-sensor features based on expert labels on data episodes (4 levels of severity).
“Based on the expert's labels on data episodes (4 levels of the severity), several binary SVMs with different kernels such as RBF, polynomial, and sigmoid are combined to model the input data from multi sensor features.”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [44] Nikita, 2012, A Support Vector Machine Approach for Categorization of Patients Suffering from Chronic Diseases, Wireless Mobile Communication and Healthcare source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Findingcitation
The input of that method was reduced power spectral density features of pulse.
“The input of the method the reduced power spectral density features of pulse.”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [32] Thakker, 2011, Support vector machine for abnormal pulse classification, Int. J. Comput. Appl.
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Findingcitation
The SVM method with polynomial kernel leads to better results than other kernels for detecting arrhythmia and seizure episodes in ECG signals.
“This research showed that the SVM method with polynomial kernel leads to better result rather than other kernels.”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [27] Lee, 2012, Low-energy formulations of support vector machine kernel functions for biomedical sensor applications, J. Signal Process. Syst. source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Findingcitation
A one-against-all SVMs method was used to handle multi-label classification for detecting patient's condition.
“Detection of the patient's condition is the topic of [44] which used a one-against-all SVMs method in order to handle multi-label classification.”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [44] Nikita, 2012, A Support Vector Machine Approach for Categorization of Patients Suffering from Chronic Diseases, Wireless Mobile Communication and Healthcare source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Findingnone given
SVM techniques are often proposed for anomaly detection and decision making tasks in healthcare services.
“In general, SVM techniques are often proposed for anomaly detection and decision making tasks in healthcare services.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing).
Findingcitation
Due to admissible predictive performance, neural networks are presently the most popular data modeling method used in the medical domain.
“Due to the admissible predictive performance of NN, it is presently the most popular data modeling method used in the medical domain [37].”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [37] Bellazzi, 2008, Predictive data mining in clinical medicine: Current issues and guidelines, Int. J. Med. Inform. source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Findingnone given
Studies using GMM usually deal with annotated medical data to assess the performance of the model.
“Studies using GMM usually deal with annotated medical data in order to assess the performance of the model.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Findingnone given
More attention has been given to decision trees in the medical domain when short term data with few subjects has been used.
“More attention has been given to decision trees in medical domain when short term data with few numbers of subjects has been used.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.
Findingreasoning
All the tasks mentioned in Section 3 have been addressed in the literature with a decision tree solution because it is simple and easy to implement.
“However, all the mentioned tasks in Section 3 have been addressed in the literature with a decision tree solution, because it is simple and easy to implement.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Findingnone given
HMM is generally used for anomaly detection rather than any other tasks.
“In general, HMM is used for anomaly detection rather than any other tasks.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Findingnone given
HMM has not been applied to multi health parameters analysis and big data sets.
“Additionally, to the best of our knowledge, this method has not been applied to multi health parameters analysis and big data sets.”
Quote in the paperNot a substantial claim
May combine two claims.
Findingcitation
Bayesian networks, fuzzy state machines, logistic regression models, and association rules have been used for specific health monitoring tasks.
“Some other examples are mentioned here: Bayesian network for classifying stress level [26,39] or for predicting patient's state [72], Fuzzy state machine for estimating the health status to provide alerts [68], logistic regression models [42] and association rules [41] to predict stress level and hospitalization of hemodialysis patients, respectively.”
Quote in the paperNot a substantial claim0 of 4 sources checked
- cites [26] Gaura, E., Kemp, J., and Brusey, J. (2013). Leveraging knowledge from physiological data: On-body heat stress risk prediction with sensor networks. IEEE Trans. Biomed. Circuits Syst., in press. source
  Not checked in the free run.
- cites [39] Gris, 2012, Activity-Aware Mental Stress Detection Using Physiological Sensors, Mobile Computing, Applications, and Services source
  Not checked in the free run.
- cites [72] Li, 2012, Dynamic time warping and machine learning for signal quality assessment of pulsatile signals, Physiol. Meas. source
  Not checked in the free run.
- cites [68] Pradhan, G.N., Chattopadhyay, R., and Panchanathan, S. (2010, January 29–31). Processing Body Sensor Data Streams for Continuous Physiological Monitoring. Philadelphia, PA, USA. source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Findingcitation
Other general statistical parameters and probability functions have been used for data mining techniques in the literature.
“Aside from the above mentioned techniques, other general statistical parameters and probability functions have been used for data mining techniques in the literature [39,53].”
Quote in the paperNot a substantial claim0 of 2 sources checked
- cites [39] Gris, 2012, Activity-Aware Mental Stress Detection Using Physiological Sensors, Mobile Computing, Applications, and Services source
  Not checked in the free run.
- cites [53] Naraharisetti, K.V.P., Bawa, M., and Tahernezhadi, M. (2011, January 15–17). Comparison of Different Signal Processing Methods for Reducing Artifacts from Photoplethysmograph Signal. Mankato, MN, USA. source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Findingnone given
Three major data gathering approaches have been identified: experimental wearable sensor data, clinical or online databases of sensor data, and simulated sensor data.
“Here, three major data gathering approaches have been identified such as experimental wearable sensor data, clinical or online databases of sensor data, and simulated sensor data.”
Quote in the paperNot a substantial claim
May combine two claims.
Findingown data
SVM, NN, decision tree and frequency/wavelet are commonly used methods for wearable sensor data processing, though they have been seen more often only on the ECG health parameter.
“Considering the data mining methods, SVM, NN, decision tree and frequency/wavelet are commonly used methods for wearable sensor data processing though they have seen more often only on the ECG health parameter.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing).
Findingnone given
ECG, HR, SpO2 and RR are the most complex health parameters where researchers have applied several data mining techniques to analyze these vital signs.
“It can be seen that ECG, HR, SpO2 and RR are the most complex health parameters where researchers have applied several data mining techniques to analyze these vital signs.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing).
Findingnone given
Dealing with long term data is a significant portion of some data mining methods for handling and processing lengthy periods of sensor data.
“On the other hand, dealing with long term data is the significant portion of some data mining methods for handling and processing lengthy period of sensor data.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing).
Findingreasoning
Attention of most research is given to annotated data.
“Due to have significant data analysis step, attention of the most research is given to annotated data.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing).
Findingcitation
Blood pressure data has appeared in the literature in both continuous and discrete format.
“Blood pressure data is an example which has been appeared in the literature in both continuous and discrete format [30,75].”
Quote in the paperNot a substantial claim0 of 2 sources checked
- cites [30] Huang, G., Zhang, Y., Cao, J., Steyn, M., and Taraporewalla, K. (2013). Online mining abnormal period patterns from multiple medical sensor data streams. World Wide Web. source
  Not checked in the free run.
- cites [75] Ordonez, P., Armstrong, T., Oates, T., and Fackler, J. (2011, January 18–21). Classification of Patients Using Novel Multivariate Time Series Representations of Physiological Data. Honolulu, HI, USA. source
  Not checked in the free run.
May combine two claims.
Findingcitation
Although using several wearable sensors in health monitoring frameworks is common, few research has really performed multivariate data analysis to extract effective information through multi-sensor data.
“Although using several wearable sensors in health monitoring frameworks are common, but few researches have really performed the multivariate data analysis in order to extract effective information through multi sensor data [30].”
Quote in the paperSubstantial claim0 of 1 sources checked
- cites [30] Huang, G., Zhang, Y., Cao, J., Steyn, M., and Taraporewalla, K. (2013). Online mining abnormal period patterns from multiple medical sensor data streams. World Wide Web. source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Findingnone given
Large scale data is typically more available in clinical settings and online databases where more resources are available.
“Beside, large scale data is typically more available in clinical settings and online databases where more resources are available.”
Quote in the paperNot a substantial claim
May combine two claims.
Findingreasoning
Short term data sets have been more used than long term for most health parameters excluding BG and BP, which need naturally long term data to analyze.
“On considering time horizon, Since the short term data sets are easily acquired and processed, they have been more used than long term for the most of the health parameters excluding BG, BP which need naturally long term data to analyze.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Findingnone given
Wearable sensor data collected in other contexts are rather unlabeled.
“Wearable sensor data collected in other contexts are rather unlabeled.”
Quote in the paperNot a substantial claim
May combine two claims.
Findingnone given
In this field relatively little data is discrete and is usually collected in conjunction with other sensor modalities.
“In this field relatively little data is discrete and is usually collected in conjunction with other sensor modalities.”
Quote in the paperNot a substantial claim
May combine two claims.
Findingreasoning
Most health parameters used annotated data sets rather than unlabeled measurements excluding BG and RR, since there is no adequate predefined annotations to be marked on specific temporal data.
“Most of the health parameters are used the annotated data sets rather than the unlabeled measurements excluding BG and RR, Since there is no adequate predefined annotations to be marked on specific temporal data.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.
Findingnone given
Rule-based and decision tree methods have been used in clinical situations with controlled conditions and clear data sets, but their efficiency has not been tested in real experiments of healthcare services.
“Data mining methods (e.g rule-based, decision tree) have been used in clinical situation with controlled conditions and clear data sets, but the efficiency of them are not tested in real experiments of healthcare services.”
Quote in the paperNot a substantial claim
May combine two claims.
Findingnone given
Most studies have been conducted on ECG sensor signal, where all types of data have been used.
“Most studies have been conducted on ECG sensor signal, where all types of data has been used i.e., long/short term, large/small scale, and annotated/unlabeled data properties.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing).
Findingcitation
Some attention to exploiting multiple measurements of vital signs simultaneously has been given in the literature.
“Some attention to this issue has been given in the literature such as [30].”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [30] Huang, G., Zhang, Y., Cao, J., Steyn, M., and Taraporewalla, K. (2013). Online mining abnormal period patterns from multiple medical sensor data streams. World Wide Web. source
  Not checked in the free run.
- Rests on an assumption: The literature study performed here is sufficient to identify general challenges in the field of health monitoring.
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Findingnone given
Some studies in the literature have used NN, HMM, and frequency techniques to handle complex physiological data and discover unexpected patterns in real-world situations.
“In contrast, some studies in the literature have used NN, HMM, and frequency techniques in order to handle complex physiological data and discover the unexpected patterns in real world situations.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S4 (based).
Findingnone given
Many applications using larger data sets still consider monitoring in clinical contexts.
“One challenge is that still many applications using larger data sets and still consider monitoring in clinical contexts.”
Quote in the paperNot a substantial claim
- Rests on an assumption: The literature study performed here is sufficient to identify general challenges in the field of health monitoring.
Probably not a substantial claim: may not pass S3 (load-bearing).
Findingnone given
Data mining approaches are gaining increasing attention in the field of wearable sensors in health monitoring.
“Data mining approaches gain increasing attention in this field, open data sets as well as benchmark data sets become important in order to validate different approaches.”
Quote in the paperNot a substantial claim
- Rests on an assumption: The literature study performed here is sufficient to identify general challenges in the field of health monitoring.
Probably not a substantial claim: may not pass S4 (based).
Findingnone given
Experts using healthcare services do not sufficiently interact with the reactive and proactive decisions made by the developed system.
“However, it is still a big challenge that experts using healthcare services are not sufficiently interact with the reactive and proactive decisions made by the developed system.”
Quote in the paperNot a substantial claim
- Rests on an assumption: The literature study performed here is sufficient to identify general challenges in the field of health monitoring.
Probably not a substantial claim: may not pass S3 (load-bearing).
Interpretationcitation
The higher prediction percentage for heart rate and blood glucose is most likely because these parameters are associated with monitoring specific diseases such as diabetes where prediction is important.
“This is most likely due to the fact that these parameters are associated with monitoring of specific diseases e.g., diabetes whereby prediction is an important component [23].”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [23] Chatterjee, S., Dutta, K., Xie, H.Q., Byun, J., Pottathil, A., and Moore, M. (2013, January 7–10). Persuasive and Pervasive Sensing: A New Frontier to Monitor, Track and Assist Older Adults Suffering from Type-2 Diabetes. Grand Wailea, Maui, HI, USA. source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Interpretationreasoning
The role of predictive data mining with wearable sensors is nontrivial due to the requirement of modeling sequential patterns acquired from vital signs.
“The role of the predictive data mining considering wearable sensors is nontrivial due to requirement of modeling sequential patterns acquired from vital signs.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing).
Interpretationcitation
The complication of conditions, especially patient situations, needs more robust and global information rather than sensor abnormal patterns alone.
“Moreover, the complication of the conditions, especially about patient's situations, needs more robust and global information rather than sensor's abnormal patterns alone [43].”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [43] Sneha, 2009, Enabling ubiquitous patient monitoring: Model, decision protocols, opportunities and challenges, Decis. Support Syst. source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Interpretationreasoning
The difficulty of using predictive models is higher in environmental health monitoring (e.g., home) than in controlled positions such as clinical units.
“For the sake of the unexpected situations and conditions in environmental health monitoring (e.g., home), the difficulty of using predictive models is higher than controlled positions such as clinical units.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing).
Interpretationcitation
Every healthcare system using HR sensor data needs to investigate the effect of metadata such as age, sex, weight, and medicine to have meaningful reasoning for basic abnormal heart rates or to personalize critical pulses.
“An instance is every healthcare system using HR sensor data needs to investigate the effect of metadata such as age, sex, weight, and medicine in order to have meaningful reasoning to find i.e., basic abnormal heart rates or to personalize the critical pulses based on the mentioned metadata [58,59].”
Quote in the paperNot a substantial claim0 of 2 sources checked
- cites [58] Hjalmarson, 2007, Heart rate: An independent risk factor in cardiovascular disease, Eur. Heart J. Suppl. source
  Not checked in the free run.
- cites [59] Gellish, 2007, Longitudinal modeling of the relationship between age and maximal heart rate, Med. Sci. Sports Exerc. source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Interpretationnone given
When data is gathered from numerous wearable sensors, normalization and synchronization of sensor data is required.
“When the data is gathered from numerous wearable sensors, normalization and synchronization of sensor data is required.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Interpretationreasoning
It would be costly to use feature selection in real-time systems since modeling techniques can handle raw extracted features.
“For instance, it would be costly to use feature selection in real time systems since the modeling techniques can handle the raw extracted features.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Interpretationreasoning
In these cases, the framework has to deal with unnecessary redundancies which reduce the accuracy of results.
“In these cases, the framework has to deal with unnecessary redundancies which reduce the accuracy of results.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing).
Interpretationreasoning
The mentioned challenge is directly related to selected health parameters and data mining tasks or target of the health monitoring system.
“The mentioned challenge is directly related to considering (1) selected health parameters in the system and (2) data mining tasks or the target of the health monitoring system.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing).
Interpretationcitation
Appropriate data processing techniques are essential to make sense of the data.
“This means that in order to make sense of the data, appropriate data processing techniques are essential [1].”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [1] Aggarwal, C.C. (2013). Managing and Mining Sensor Data, Springer. source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation
Neural networks are widely used for classification and prediction.
“A Neural Network (NN) is an artificial intelligent approach which is widely used for classification and prediction [70].”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [70] Paliwal, 2009, Neural networks and statistical techniques: A review of applications, Expert. Syst. Appl. source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Interpretationnone given
SVM cannot be applied to find unexpected information from unlabelled data.
“Moreover, like other classifiers, SVM could not be applied to find the unexpected information from unlabelled data.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Interpretationnone given
SVM is not an appropriate method to integrate domain knowledge in order to use metadata or symbolic knowledge seamlessly with sensor measurements.
“However, SVM is not an appropriate method to integrate domain knowledge in order to use metadata or symbolic knowledge seamlessly with the measurements from the sensors.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation
The decision tree method provides an efficient representation of rule classification.
“To make an accurate discrimination for selected features, the decision tree method is one of the significant learning a technique which provides an efficient representation of rule classification [51].”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [51] Frantzidis, 2010, On the classification of emotional biosignals evoked while viewing affective pictures: An integrated data-mining-based approach for healthcare applications, Trans. Inf. Tech. Biomed. source
  Not checked in the free run.
May combine two claims.
Interpretationreasoning
Decision tree models are not usually applied to big and complex physiological data because the number of features can impact the efficiency of the method.
“Furthermore, since the number of features can impact on the efficiency of the method, decision tree models are not usually applied to big and complex physiological data.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing).
Interpretationreasoning
Decision trees are suitable for handling multivariate sensors due to the construction of independent levels in the decision tree.
“This method is also suitable for handling multivariate sensors due to construction of independent levels in the decision tree.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation
The C4.5 algorithm is used when dealing with complex and noisy data; it estimates the error rate of initial nodes and prunes the tree to make a more efficient sub-tree.
“Nowadays, upon dealing with complex and noisy data, the C4.5 algorithm is used which is estimating the error rate of initial nodes and pruning the tree to make a more efficient sub-tree [41,51].”
Quote in the paperNot a substantial claim0 of 2 sources checked
- cites [41] Yeh, 2011, Using data mining techniques to predict hospitalization of hemodialysis patients, Decis. Support Syst. source
  Not checked in the free run.
- cites [51] Frantzidis, 2010, On the classification of emotional biosignals evoked while viewing affective pictures: An integrated data-mining-based approach for healthcare applications, Trans. Inf. Tech. Biomed. source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Interpretationreasoning
Finding hidden information out of constricted features is not recognizable by decision tree methods.
“So, finding hidden information out of constricted features would not be recognizable.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Interpretationreasoning
Because learning progress in neural networks is complex, they are commonly used for decision making in clinical conditions with large and complicated data sets.
“In sum, since the progress of learning in NN would be complex, the method is commonly used for decision making in clinical conditions with large and complicated data sets.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Interpretationnone given
Decision tree methods are limited to the space of the constructed features used as inputs.
“Generally, decision tree methods are limited to the space of the constructed features as the inputs of the model.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.
Interpretationnone given
Because the modeling process in neural networks is a black box, the method needs to justify each input data.
“Additionally, as the modeling process in NN is a black box progress, NN method needs to justify for each input data.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Interpretationnone given
Neural networks cannot handle domain knowledge to enrich results.
“But same as SVM it could not handle domain knowledge to enrich the results.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation
Gaussian mixture model is a statistical model used for classification and pattern recognition.
“Gaussian mixture model (GMM) is another statistical model which used for classification and pattern recognition [57].”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [57] Wang, 2011, Secure stochastic ECG signals based on gaussian mixture model for e-healthcare systems, IEEE Syst. J. source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation
Decision trees are a reliable technique to use in different areas of the medical domain to make a right decision.
“Decision tree is a reliable technique to use in different areas of medical domain in order to make a right decision [76,77].”
Quote in the paperNot a substantial claim0 of 2 sources checked
- cites [76] Podgorelec, 2002, Decision trees: An overview and their use in medicine, J. Med. Syst. source
  Not checked in the free run.
- cites [77] Bohada, 2012, Improving medical decision trees by combining relevant health-care criteria, Expert Syst. Appl. source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation
Using HMM, hidden states can be inferred from other observations in a sequence of data.
“Using this model the hidden states can be inferred from the other observations in sequence of data [80].”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [80] Bae, 2011, Gait phase analysis based on a Hidden Markov Model, Mechatronics source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation
A domain-specific expert system is a common rule-based method that defines and applies expert conditions during data analysis.
“A domain-specific expert system is a common rule-based method that defines and applies the expert conditions during data analysis [83–85].”
Quote in the paperNot a substantial claim0 of 3 sources checked
- cites [83] He, J., Liu, X., Krupinski, E., and Xu, G. (2012). Health Information Science, Springer. source
  Not checked in the free run.
- cites [84] Fayyad, U.M., Piatetsky-Shapiro, G., Smyth, P., and Uthurusamy, R. (1996). Advances in Knowledge Discovery and Data Mining, American Association for Artificial Intelligence.
  Not checked in the free run.
- cites [85] Kalagnanam, J., and Henrion, M. (2013). A comparison of decision analysis and expert rules for sequential diagnosis. arXiv:1304.2362.
  Not checked in the free run.
Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing), S4 (based).
Interpretationreasoning
Based on the abilities of HMM to model unexpected behaviors of data, modified versions of HMM are applicable to more problems in healthcare domains.
“However, based on the abilities of HMM to model the unexpected behaviors of the data, it is applicable to use the modified versions of HMM in more problems in healthcare domains.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation
Hidden Markov model is a probabilistic model convenient for modeling sequential data.
“Hidden Markov model (HMM) is a probabilistic model which is convenient for modeling sequential data [78].”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [78] Rabiner, 1986, An introduction to hidden Markov models, IEEE ASSP Mag. source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Interpretationnone given
GMM is able to detect unseen information in physiological data.
“Despite GMM is able to detect unseen information in physiological data”
Quote in the paperNot a substantial claim
May combine two claims.
Interpretationreasoning
Rule-based methods are not adequate for decision making and prediction tasks as well as personalized systems with context-aware targets.
“The rule-based methods are not adequate for decision making and prediction tasks as well as the personalized system with context aware targets.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing).
Interpretationreasoning
Rule-based methods are biased to predefined rules in order to learn the features and behavior of the data itself.
“However, these methods are biased to the predefined rules in order to learn the features and behavior of the data itself.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing).
Interpretationcitation
The RBR phase is necessary to apply on any wearable sensor framework.
“Due to the basic task of the healthcare monitoring which is to find the obvious problem in physiological data, the RBR phase is necessary to apply on any wearable sensor framework [82].”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [82] Al-Hajji, A.A. (2012, January 12–14). Rule-Based Expert System for Diagnosis and Symptom of Neurological Disorders Neurologist Expert System (NES). Al-Madinah Al-Munawwarah, Saudi Arabia.
  Not checked in the free run.
- Rests on an assumption: The basic task of healthcare monitoring is to find the obvious problem in physiological data.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Interpretationreasoning
Because rule-based methods use provided rules by experts or domain knowledge, they are able to perform anomaly detection and deal with unlabeled data sets to find unusual patterns.
“Since rule-based methods are using a set of provided rules by experts or the domain knowledge, they are able to perform anomaly detection task and to deal with unlabeled data sets to find unusual patterns.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Interpretationreasoning
The initialization step in GMM does not necessarily enrich modeling due to the character of health parameters in real-world situations.
“Moreover, the initialization step in GMM does not necessarily enrich the modeling (as GMM approached assume data as a combination of Gaussian distinction) due to the character of health parameters in real world situations.”
Quote in the paperNot a substantial claim
- The authors state this as an assumption: GMM assumes that the input data are a linear combination of Gaussian distributions.
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Interpretationnone given
Statistical tools are not reliable for decision making tasks.
“Despite that these tools are not reliable for decision making tasks”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.
Interpretationnone given
Frequency domain analysis is able to model and find complex patterns and detect non-obvious anomalies in the data.
“Frequency domain analysis is able to model and find complex patterns and detect the non obvious anomalies in the data.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing).
Interpretationreasoning
Frequency domain models have not commonly been applied for prediction tasks due to the lack of domain knowledge in their models.
“Furthermore, these models have not commonly applied for predication task due to the lack of domain knowledge in their models.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Interpretationnone given
Domain knowledge and context metadata cannot be integrated with statistical models.
“Nevertheless, domain knowledge and context metadata cannot be integrated with the statistical models.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing).
Interpretationreasoning
Statistical models are able to detect types of anomalies that are not easily seen by the expert.
“Thus, these models are able to detect the types of anomalies which are not easily seen by the expert.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation
PhysioNet database consists of a wide range of physiological data sets with categorized and robust annotations for complex clinical signals.
“Very common example of online databases is PhysioNet [90,91] database which consists a wide range of physiological data sets with categorized and robust annotations for complex clinical signals.”
Quote in the paperNot a substantial claim0 of 2 sources checked
- cites [90] PhysioBank Archive Index. Available online: http://www.physionet.org/physiobank/database/.
  Not checked in the free run.
- cites [91] Goldberger, 2000, PhysioBank, physiotoolkit, and physionet: Components of a new research resource for complex physiologic signals, Circulation source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Interpretationcitation
Data simulation is useful when the focus of the data processing method is on efficiency and robustness of information extraction rather than handling real-world data including artifacts, errors, and conditions of the data gathering environment.
“Data simulation would be useful when the more focus of data processing method is on the efficiency and robustness of information extraction [28,57] rather than handling real-world data including the artifact, errors, conditions of data gathering environment, etc.”
Quote in the paperNot a substantial claim0 of 2 sources checked
- cites [28] Zhu, 2011, Automatic detection of anomalies in blood glucose using a machine learning approach, J. Commun. Netw. source
  Not checked in the free run.
- cites [57] Wang, 2011, Secure stochastic ECG signals based on gaussian mixture model for e-healthcare systems, IEEE Syst. J. source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Interpretationnone given
The scale of subjects in frameworks differs depending on the design of the sensor network, data gathering, and the goal of decision making.
“Depending on the design of sensor network, data gathering, and the goal of decision making, the scale of subjects in the frameworks would differ.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation
Blood glucose monitoring is an example of long term data analysis for the sake of right decision making.
“Blood glucose monitoring is an example of long term data analysis for the sake of right decision making [23,28].”
Quote in the paperNot a substantial claim0 of 2 sources checked
- cites [23] Chatterjee, S., Dutta, K., Xie, H.Q., Byun, J., Pottathil, A., and Moore, M. (2013, January 7–10). Persuasive and Pervasive Sensing: A New Frontier to Monitor, Track and Assist Older Adults Suffering from Type-2 Diabetes. Grand Wailea, Maui, HI, USA. source
  Not checked in the free run.
- cites [28] Zhu, 2011, Automatic detection of anomalies in blood glucose using a machine learning approach, J. Commun. Netw. source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Interpretationnone given
The length of time for considering data set measurements is a particular challenge for wearable sensor data in order to orientate data mining techniques and the manner of data interpretation.
“The length of time for considering data set measurements is a particular challenge for wearable sensor data in order to orientate the data mining techniques and the manner of data interpretation.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing).
Interpretationnone given
Working with unlabeled data leads to unsupervised learning methods to extract unseen knowledge among raw sensor data.
“On the other hand, working with unlabeled data leads to have unsupervised learning methods in order to extract unseen knowledge among raw sensor data.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation
Due to the nature of vital signs, some are essentially counted as continuous such as ECG, heart rate and respiration rate, or discrete like blood glucose level.
“Due to the nature of vital signs, some of them are essentially counted as continuous such as ECG, heart rate and respiration rate [31,42] or discrete like blood glucose level [28].”
Quote in the paperNot a substantial claim0 of 3 sources checked
- cites [31] Clifton, 2013, Gaussian processes for personalized e-health monitoring with wearable sensors, IEEE Trans. Biomed. Eng. source
  Not checked in the free run.
- cites [42] Choi, 2012, Development and evaluation of an ambulatory stress monitor based on wearable sensors, IEEE Trans. Inf. Technol. Biomed. source
  Not checked in the free run.
- cites [28] Zhu, 2011, Automatic detection of anomalies in blood glucose using a machine learning approach, J. Commun. Netw. source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Interpretationcitation
From the data mining point of view, the continuity of physiological data is important because dealing with streams of sensor data has its own problems and challenges as well as analyzing sporadic measurements.
“From the data mining point of view, the continuity of physiological data is important, since dealing with streams of sensor data has its own problems and challenges as well as analyzing sporadic measurements [30].”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [30] Huang, G., Zhang, Y., Cao, J., Steyn, M., and Taraporewalla, K. (2013). Online mining abnormal period patterns from multiple medical sensor data streams. World Wide Web. source
  Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.
Interpretationnone given
Data mining techniques have progressed significantly in the past few years and with the availability of large and open data sets, new possibilities for achieving suitable algorithms for wearable sensors exist.
“Data mining techniques have progressed significantly in the past few years and with the availability of large and open data sets, new possibilities for achieving suitable algorithms for wearable sensors exist.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.
Interpretationnone given
For decision-making tasks in healthcare, statistical methods play a lesser role, while SVM, NN, and decision tree techniques have usually been applied with good success.
“So, the role of statistical methods in this task is less, but SVM, NN, and decision tree techniques have usually applied for the healthcare problems with decision making tasks with good success.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing).
Interpretationreasoning
Simple methods such as rule-based, decision tree, and statistical techniques can quickly handle online data processing requirements.
“But simple methods such as rule-based, decision tree and statistical techniques can quickly handle the online data processing requirements.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing), S4 (based).
Interpretationnone given
Any decision making task needs a strong modeling and inferring system with proper usage of contextual information.
“Finally, any decision making task needs a strong modeling and inferring system with a proper usage of the contextual information.”
Quote in the paperNot a substantial claim
May combine two claims.
Interpretationnone given
Application of data mining to health monitoring is hindered by challenges present in data from wearable sensors, which create new challenges for the data mining field.
“Still, despite these developments, their application to health monitoring is hindered by the challenges that are present in data from wearable sensors which create new challenges for the data mining field.”
Quote in the paperSubstantial claim
Probably not a substantial claim: may not pass S3 (load-bearing).
Interpretationnone given
The properties of the data set and experimental condition influence the choice of data mining method.
“The properties of the data set and experimental condition also influence the choice of method.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Interpretationcitation
It is possible to automate the retrieval of high-level information via available ontologies and link this information to the data.
“It is also possible to automate the retrieval of high level information via available ontologies [98,99] and link this information to the data.”
Quote in the paperNot a substantial claim0 of 2 sources checked
- cites [98] Kim, J., Kim, J., Lee, D., and Chung, K.Y. (2012). Ontology driven interactive healthcare with wearable sensors. Multimed. Tools Appl. source
  Not checked in the free run.
- cites [99] Alirezaie, M., and Loutfi, A. (2013, January 19–22). Automatic Annotation of Sensor Data Streams Using Abductive Reasoning. Vilamoura, Portugal.
  Not checked in the free run.
- Rests on an assumption: The literature study performed here is sufficient to identify general challenges in the field of health monitoring.
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Interpretationnone given
A caveat with automated data mining and black box learning methods is the amount of trust between the data analysis system and the experts who use the system for decision making tasks.
“A caveat with automated data mining and black box learning methods is the amount of trust between the data analysis system and the experts who use the system for decision making tasks.”
Quote in the paperNot a substantial claim
- Rests on an assumption: The literature study performed here is sufficient to identify general challenges in the field of health monitoring.
Probably not a substantial claim: may not pass S3 (load-bearing).
Interpretationnone given
A challenge in the field is to exploit the multiple measurements of vital signs simultaneously.
“Another challenge in this field is to exploit the multiple measurements of vital signs simultaneously.”
Quote in the paperNot a substantial claim
- Rests on an assumption: The literature study performed here is sufficient to identify general challenges in the field of health monitoring.
Probably not a substantial claim: may not pass S3 (load-bearing).
Interpretationnone given
Sensor fusion techniques that consider dependencies and correlations between different vital sign parameters could assist in performing prediction, decision making, and anomaly detection.
“In particular, sensor fusion techniques which are able to consider dependencies and correlations between different vital sign parameters could assist in performing the main data mining tasks of prediction, decision making and anomaly detection.”
Quote in the paperNot a substantial claim
- Rests on an assumption: The literature study performed here is sufficient to identify general challenges in the field of health monitoring.
Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing), S4 (based).
Interpretationnone given
In real-world systems such as home monitoring, it would be difficult to model unexpected features with straightforward techniques.
“It also worth noting that in real world system such as home monitoring, it would be difficult to model the unexpected features with straightforward techniques.”
Quote in the paperNot a substantial claim
- Rests on an assumption: The literature study performed here is sufficient to identify general challenges in the field of health monitoring.
Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing), S4 (based).
Interpretationreasoning
Usage of contextual information to assist in data mining is of ever increasing importance.
“In addition, usage of contextual information to assist in data mining is of ever increasing importance.”
Quote in the paperNot a substantial claim
- Rests on an assumption: The literature study performed here is sufficient to identify general challenges in the field of health monitoring.
Probably not a substantial claim: may not pass S4 (based). May combine two claims.
Interpretationreasoning
For multivariate analysis of wearable sensor data, methods working with domain knowledge such as rule-based, decision tree, and statistical tools are more usable, while GMM and HMM cannot play this role in healthcare systems.
“For multivariate analysis of wearable sensor data, the methods working with domain knowledge such as rule-based, decision tree, and statistical tools are more usable, while GMM and HMM could not play this role in healthcare systems.”
Quote in the paperNot a substantial claim
Probably not a substantial claim: may not pass S3 (load-bearing).
Interpretationcitation
Case-based reasoning may increase the level of trust by being explicit and referring to previous cases.
“For this reason, different approaches such as case based reasoning [100] may increase the level of trust by being explicit and referring to previous cases.”
Quote in the paperNot a substantial claim0 of 1 sources checked
- cites [100] Ahmed, 2013, Health monitoring for elderly: An application using case-based reasoning and cluster analysis, ISRN Artif. Intell. source
  Not checked in the free run.
- Rests on an assumption: The literature study performed here is sufficient to identify general challenges in the field of health monitoring.
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.
Interpretationnone given
Hardware architectures allow for more parameters to be collected, so more information could readily be collected.
“As hardware architectures allow for more parameters to be collected, more information could readily be collected.”
Quote in the paperNot a substantial claim
- Rests on an assumption: The literature study performed here is sufficient to identify general challenges in the field of health monitoring.
Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing), S4 (based). May combine two claims.
Interpretationnone given
Important features of the data may be unintuitive (e.g., frequency domain features) and may be needed for providing proper analysis and uncovering important characteristics from the data which cannot be obtained by hand-engineered features.
“Still, important features of the data which may be unintuitive e.g., frequency domain features may be needed for providing proper analysis and uncovering important characteristics from the data which cannot be obtained by hand-engineered features.”
Quote in the paperNot a substantial claim
- Rests on an assumption: The literature study performed here is sufficient to identify general challenges in the field of health monitoring.
Classified as probably not a substantial claim. May combine two claims.
Interpretationnone given
Annotating data is expensive, time-consuming, and non-trivial for long-term continuous data.
“The process of annotating data is expensive, time consuming and non-trivial considering long-term continuous data.”
Quote in the paperSubstantial claim
- Rests on an assumption: The literature study performed here is sufficient to identify general challenges in the field of health monitoring.
Classified as probably not a substantial claim.
Interpretationreasoning
The result is a move from applying out-of-the-box data mining algorithms to a more concentrated effort towards novel data mining methods for wearable sensors in health monitoring.
“The result is a move from applying out of the box data mining algorithms to a more concentrated effort towards novel data mining methods for the wearable sensors in health monitoring.”
Quote in the paperSubstantial claim

138 of 138

The paper relies on this without support.
The selected set of more than eighty papers is representative of recent research in data mining for wearable health monitoring.
“So, the selected papers as the representatives of the performed research are limited to the more than eighty papers.”
The authors state this as an assumption.
GMM assumes that the input data are a linear combination of Gaussian distributions.
“This method is based on this assumption that the input data are a linear combination of Gaussian distributions.”
The paper relies on this without support.
The basic task of healthcare monitoring is to find the obvious problem in physiological data.
“Due to the basic task of the healthcare monitoring which is to find the obvious problem in physiological data, the RBR phase is necessary to apply on any wearable sensor framework [82].”
The paper relies on this without support.
Having a robust data processing stage requires adequate information about the data itself.
“In any health monitoring system, having a robust data processing stage requires adequate information about the data itself.”
The paper relies on this without support.
Dealing with the type of input data and its properties is the prerequisite of any data processing system.
“In other words, dealing with the type of input data and its properties is the prerequisite of any data processing system in order to handle the significant issues such as: selecting the proper data mining approach, designing and adjusting new method and features, and tuning the parameters of data analysis.”
The paper relies on this without support.
Health monitoring systems need to evaluate their results in order to show the correctness of the decision making process.
“Health monitoring systems need to evaluate their results in order to show the correctness of the decision making process.”
The paper relies on this without support.
The literature study performed here is sufficient to identify general challenges in the field of health monitoring.
“These challenges are general challenges in the field of health monitoring and have emerged from the literature study performed here.”

7 of 7

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Data mining techniques such as wavelet analysis for artifact reduction and data compression, rule-based methods for data summary and transmission, and Gaussian processing for secure authentication have been implemented.
“To solve such problems, data mining techniques such as wavelet analysis for artifact reduction and data compression, rule-based methods for data summary and transmission, and Gaussian processing for secure authentication have been implemented.129”
From Wearable sensors for monitoring the physiological and biochemical profile of the athlete (2019) · cites this paper as [129]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

Method attributed to [57] changes from Gaussian process to GMM
Minor
The preprocessing discussion attributes a Gaussian process for secure authentication to [57], while the description of the same work says it uses a Gaussian mixture model (GMM).
Reference [73] does not match the claimed neural-network source
Minor
The neural-network section cites [73] for replicator neural networks, but reference [73] is about the value of self-monitored blood glucose testing.
Reference [16] does not match the claimed arrhythmia-detection study
Minor
The text attributes an ECG arrhythmia-detection method to [16], but the paper's entry for [16] identifies it as a review of wearable sensors for rehabilitation.
Study [44] is described as using both unlabeled and expert-labeled data
Minor
The data-properties section lists [44] among studies of unlabeled data, whereas the description of [44] says its data episodes have expert-assigned severity labels.

4 of 4

Support-vector networks
Cortes, C., & Vapnik, V. (1995) · Machine Learning · doi:10.1007/bf00994018 · Cited by 59,421 · see citing works
Support-Vector Networks
Cortes, C., & Vapnik, V. N. (1995) · Machine Learning · doi:10.1023/a:1022627411411 · Cited by 34,565 · see citing works
PhysioBank, PhysioToolkit, and PhysioNet: Components of a New Research Resource for Complex Physiologic Signals
Goldberger, A. L., Amaral, L. A. N., Glass, L., Hausdorff, J. M., Ivanov, P. C., Mark, R. G., Mietus, J. E., Moody, G. B., Peng, C.-K., & Stanley, H. E. (2000) · Circulation · doi:10.1161/01.cir.101.23.e215 · Cited by 14,809 · see citing works
Anomaly detection: A survey
Chandola, V., Banerjee, A., & Kumar, V. (2009) · ACM Computing Surveys · doi:10.1145/1541880.1541882 · Cited by 11,687 · see citing works
An introduction to hidden Markov models
Rabiner, L., & Juang, B. (1986) · IEEE ASSP Magazine · doi:10.1109/massp.1986.1165342 · Cited by 4,775 · see citing works
A Survey on Human Activity Recognition using Wearable Sensors
Lara, O. D., & Labrador, M. A. (2013) · IEEE Communications Surveys & Tutorials · doi:10.1109/surv.2012.110112.00192 · Cited by 2,662 · see citing works
A review of wearable sensors and systems with application in rehabilitation
Patel, S., Park, H., Bonato, P., Chan, L., & Rodgers, M. (2012) · Journal of NeuroEngineering and Rehabilitation · doi:10.1186/1743-0003-9-21 · Cited by 2,396 · see citing works
From data mining to knowledge discovery: an overview
Fayyad, U. M., Piatetsky-Shapiro, G., & Smyth, P. (1996) · Knowledge Discovery and Data Mining · Cited by 2,319 · see citing works
A Survey on Wearable Sensor-Based Systems for Health Monitoring and Prognosis
Pantelopoulos, A., & Bourbakis, N. G. (2010) · IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews) · doi:10.1109/tsmcc.2009.2032660 · Cited by 2,296 · see citing works
Feature Extraction: Foundations and Applications (Studies in Fuzziness and Soft Computing)
Guyon, I., Gunn, S., Nikravesh, M., & Zadeh, L. A. (2006) · Springer eBooks · Cited by 1,845 · see citing works
Wireless sensor networks for healthcare: A survey
Alemdar, H., & Ersoy, C. (2010) · Computer Networks · doi:10.1016/j.comnet.2010.05.003 · Cited by 1,427 · see citing works
Body Area Networks: A Survey
Chen, M., González-Valenzuela, S., Vasilakos, A. V., Cao, H., & Leung, V. C. M. (2010) · Mobile Networks and Applications · doi:10.1007/s11036-010-0260-8 · Cited by 1,353 · see citing works
A survey on ambient-assisted living tools for older adults
Rashidi, P., & Mihailidis, A. (2013) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2012.2234129 · Cited by 1,128 · see citing works
Feature Extraction
Kacprzyk, J., Zadeh, L. A., Nikravesh, M., Guyon, I., & Gunn, S. (2006) · Studies in fuzziness and soft computing · doi:10.1007/978-3-540-35488-8 · Cited by 991 · see citing works
Smart wearable systems: Current status and future challenges
Chan, M., Estève, D., Fourniols, J.-Y., Escriba, C., & Campo, E. (2012) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2012.09.003 · Cited by 953 · see citing works
Artificial neural networks in medical diagnosis
Amato, F., López, A., Peña-Méndez, E. M., Vaňhara, P., Hampl, A., & Havel, J. (2013) · Journal of Applied Biomedicine · doi:10.2478/v10136-012-0031-x · Cited by 898 · see citing works
Predictive data mining in clinical medicine: Current issues and guidelines
BELLAZZI, R., & ZUPAN, B. (2008) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2006.11.006 · Cited by 823 · see citing works
Neural networks and statistical techniques: A review of applications
Paliwal, M., & Kumar, U. A. (2009) · Expert Systems with Applications · doi:10.1016/j.eswa.2007.10.005 · Cited by 792 · see citing works
Machine Learning Methods for Classifying Human Physical Activity from On-Body Accelerometers
Mannini, A., & Sabatini, A. M. (2010) · Sensors · doi:10.3390/s100201154 · Cited by 785 · see citing works
Decision trees: An overview and their use in medicine
Podgorelec, V., Kokol, P., Stiglic, B., & Rozman, I. (2002) · Journal of Medical Systems · doi:10.1023/a:1016409317640 · Cited by 736 · see citing works
Anomaly Detection for Discrete Sequences: A Survey
Chandola, V., Banerjee, A., & Kumar, V. (2010) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2010.235 · Cited by 709 · see citing works
Longitudinal Modeling of the Relationship between Age and Maximal Heart Rate
GELLISH, R. L., GOSLIN, B. R., OLSON, R. E., McDONALD, A., RUSSI, G. D., & MOUDGIL, V. K. (2007) · Medicine & Science in Sports & Exercise · doi:10.1097/mss.0b013e31803349c6 · Cited by 660 · see citing works
Data Mining in Healthcare and Biomedicine: A Survey of the Literature
Yoo, I., Alafaireet, P. E., Marinov, M. D., Pena-Hernandez, K. E., Gopidi, R., Chang, J.-F., & Hua, L. (2011) · Journal of Medical Systems · doi:10.1007/s10916-011-9710-5 · Cited by 547 · see citing works
Physiological parameter monitoring from optical recordings with a mobile phone
Scully, C. G., Lee, J., Meyer, J., Gorbach, A. M., Granquist-Fraser, D., Mendelson, Y., & Chon, K. H. (2012) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2011.2163157 · Cited by 452 · see citing works
Activity Recognition Using Inertial Sensing for Healthcare, Wellbeing and Sports Applications: A Survey
Avci, A., Bosch, S., Marin-Perianu, M., Marin-Perianu, R., & Havinga, P. (2010) · University of Twente Research Information · Cited by 443 · see citing works
Smart health monitoring systems: An overview of design and modeling
Baig, M. M., & Gholamhosseini, H. (2013) · Journal of Medical Systems · doi:10.1007/s10916-012-9898-z · Cited by 396 · see citing works
Apnea medassist: Real-time sleep apnea monitor using single-lead ECG
Bsoul, M., Minn, H., & Tamil, L. (2011) · IEEE Transactions on Information Technology in Biomedicine · doi:10.1109/titb.2010.2087386 · Cited by 297 · see citing works
Managing and Mining Sensor Data
(2013) · doi:10.1007/978-1-4614-6309-2 · Cited by 294 · see citing works
Real-time sleep apnea detection by classifier combination
Xie, B., & Minn, H. (2012) · IEEE Transactions on Information Technology in Biomedicine · doi:10.1109/titb.2012.2188299 · Cited by 294 · see citing works
Activity-Aware Mental Stress Detection Using Physiological Sensors
Sun, F.-T., Kuo, C., Cheng, H.-T., Buthpitiya, S., Collins, P., & Griss, M. (2012) · Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-642-29336-8_12 · Cited by 292 · see citing works
Application of nonlinear feature extraction and support vector machines for fault diagnosis of induction motors
Widodo, A., & Yang, B.-S. (2007) · Expert Systems with Applications · doi:10.1016/j.eswa.2006.04.020 · Cited by 292 · see citing works
A Zigbee-Based Wearable Physiological Parameters Monitoring System
Malhi, K., Mukhopadhyay, S. C., Schnepper, J., Haefke, M., & Ewald, H. (2010) · IEEE Sensors Journal · doi:10.1109/jsen.2010.2091719 · Cited by 283 · see citing works
Dynamic time warping and machine learning for signal quality assessment of pulsatile signals
Li, Q., & Clifford, G. D. (2012) · Physiological Measurement · doi:10.1088/0967-3334/33/9/1491 · Cited by 274 · see citing works
Sleep Stage Classification Using Unsupervised Feature Learning
Längkvist, M., Karlsson, L., & Loutfi, A. (2012) · Advances in Artificial Neural Systems · doi:10.1155/2012/107046 · Cited by 248 · see citing works
Self-citation
Development and Evaluation of an Ambulatory Stress Monitor Based on Wearable Sensors
Choi, J., Ahmed, B., & Gutierrez-Osuna, R. (2012) · IEEE Transactions on Information Technology in Biomedicine · doi:10.1109/titb.2011.2169804 · Cited by 221 · see citing works
Automated diagnosis of Coronary Artery Disease affected patients using LDA, PCA, ICA and Discrete Wavelet Transform
Giri, D., Rajendra Acharya, U., Martis, R. J., Vinitha Sree, S., Lim, T.-C., Ahamed, T., & Suri, J. S. (2013) · Knowledge-Based Systems · doi:10.1016/j.knosys.2012.08.011 · Cited by 221 · see citing works
Discrete Wavelet transform-based time series analysis and mining
Chaovalit, P., Gangopadhyay, A., Karabatis, G., & Chen, Z. (2011) · ACM Computing Surveys · doi:10.1145/1883612.1883613 · Cited by 218 · see citing works
On the classification of emotional biosignals evoked while viewing affective pictures: An integrated data-mining-based approach for healthcare applications
Frantzidis, C. A., Bratsas, C., Klados, M. A., Konstantinidis, E., Lithari, C. D., Vivas, A. B., Papadelis, C. L., Kaldoudi, E., Pappas, C., & Bamidis, P. D. (2010) · IEEE Transactions on Information Technology in Biomedicine · doi:10.1109/titb.2009.2038481 · Cited by 166 · see citing works
Enabling ubiquitous patient monitoring: Model, decision protocols, opportunities and challenges
Sneha, S., & Varshney, U. (2009) · Decision Support Systems · doi:10.1016/j.dss.2008.11.014 · Cited by 153 · see citing works
Health technology assessment review: Remote monitoring of vital signs—current status and future challenges
Nangalia, V., Prytherch, D. R., & Smith, G. B. (2010) · Critical Care · doi:10.1186/cc9208 · Cited by 150 · see citing works
A Review on Architectures and Communications Technologies for Wearable Health-Monitoring Systems
Custodio, V., Herrera, F. J., López, G., & Moreno, J. I. (2012) · Sensors · doi:10.3390/s121013907 · Cited by 147 · see citing works
Temporal abstraction in intelligent clinical data analysis: A survey
Stacey, M., & McGregor, C. (2007) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2006.08.002 · Cited by 146 · see citing works
A Remote Patient Monitoring System for Congestive Heart Failure
Suh, M.-K., Chen, C.-A., Woodbridge, J., Tu, M. K., Kim, J. I., Nahapetian, A., Evangelista, L. S., & Sarrafzadeh, M. (2011) · Journal of Medical Systems · doi:10.1007/s10916-011-9733-y · Cited by 144 · see citing works
Unsupervised pattern discovery in electronic health care data using probabilistic clustering models
Marlin, B. M., Kale, D. C., Khemani, R. G., & Wetzel, R. C. (2012) · International Health Informatics Symposium · doi:10.1145/2110363.2110408 · Cited by 143 · see citing works
<i>Prognosis</i>—A Wearable Health-Monitoring System for People at Risk: Methodology and Modeling
Pantelopoulos, A., & Bourbakis, N. G. (2010) · IEEE Transactions on Information Technology in Biomedicine · doi:10.1109/titb.2010.2040085 · Cited by 136 · see citing works
Sleep and wake classification with ECG and respiratory effort signals
Karlen, W., Mattiussi, C., & Floreano, D. (2009) · IEEE Transactions on Biomedical Circuits and Systems · doi:10.1109/tbcas.2008.2008817 · Cited by 134 · see citing works
Automatic generation of natural language nursing shift summaries in neonatal intensive care: BT-Nurse
Hunter, J., Freer, Y., Gatt, A., Reiter, E., Sripada, S., & Sykes, C. (2012) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2012.09.002 · Cited by 127 · see citing works
Gaussian processes for personalized e-health monitoring with wearable sensors
Clifton, L., Clifton, D. A., Pimentel, M. A. F., Watkinson, P. J., & Tarassenko, L. (2013) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2012.2208459 · Cited by 117 · see citing works
Using data mining techniques to predict hospitalization of hemodialysis patients
Yeh, J.-Y., Wu, T.-H., & Tsao, C.-W. (2011) · Decision Support Systems · doi:10.1016/j.dss.2010.11.001 · Cited by 110 · see citing works
Gait phase analysis based on a Hidden Markov Model
Bae, J., & Tomizuka, M. (2011) · Mechatronics · doi:10.1016/j.mechatronics.2011.03.003 · Cited by 106 · see citing works
Predictive data mining in clinical medicine: a focus on selected methods and applications
Bellazzi, R., Ferrazzi, F., & Sacchi, L. (2011) · Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery · doi:10.1002/widm.23 · Cited by 106 · see citing works
An Enhanced Security Solution for Electronic Medical Records Based on AES Hybrid Technique with SOAP/XML and SHA-1
Kiah, M. L. M., Abdulnabi, M. S., Zaidan, B. B., & Zaidan, A. A. (2013) · Journal of Medical Systems · doi:10.1007/s10916-013-9971-2 · Cited by 100 · see citing works
Real-time analysis of physiological data to support medical applications
Apiletti, D., Baralis, E., Bruno, G., & Cerquitelli, T. (2009) · IEEE Transactions on Information Technology in Biomedicine · doi:10.1109/titb.2008.2010702 · Cited by 87 · see citing works
Current evidence regarding the value of self-monitored blood glucose testing
Blonde, L., & Karter, A. J. (2005) · The American Journal of Medicine · doi:10.1016/j.amjmed.2005.07.053 · Cited by 86 · see citing works
Web-based remote human pulse monitoring system with intelligent data analysis for home health care
Chen, C. (2010) · Expert Systems with Applications · doi:10.1016/j.eswa.2010.07.136 · Cited by 77 · see citing works
An integrated data mining approach to real-time clinical monitoring and deterioration warning
Mao, Y., Chen, W., Chen, Y., Lu, C., Kollef, M., & Bailey, T. (2012) · Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/2339530.2339709 · Cited by 76 · see citing works
Robust medical ad hoc sensor networks (MASN) with wavelet-based ECG data mining
Hu, F., Jiang, M., Celentano, L., & Xiao, Y. (2008) · Ad Hoc Networks · doi:10.1016/j.adhoc.2007.09.002 · Cited by 74 · see citing works
Predicting cardiovascular disease from real-time electrocardiographic monitoring: An adaptive machine learning approach on a cell phone
Jin, Z., Sun, Y., & Cheng, A. C. (2009) · doi:10.1109/iembs.2009.5333610 · Cited by 73 · see citing works
Processing of signals recorded through smart devices: Sleep-quality assessment
Bianchi, A. M., Mendez, M. O., & Cerutti, S. (2010) · IEEE Transactions on Information Technology in Biomedicine · doi:10.1109/titb.2010.2049025 · Cited by 61 · see citing works
Ontology driven interactive healthcare with wearable sensors
Kim, J., Kim, J., Lee, D., & Chung, K.-Y. (2014) · Multimedia Tools and Applications · doi:10.1007/s11042-012-1195-9 · Cited by 57 · see citing works
Real Time ECG Feature Extraction and Arrhythmia Detection on a Mobile Platform
Patel, A. M., Gakare, P. K., & Cheeran, A. N. (2012) · International Journal of Computer Applications · Cited by 50 · see citing works
Can pervasive sensing address current challenges in global healthcare?
Atallah, L., Lo, B. P. L., & Yang, G. (2012) · Journal of Epidemiology and Global Health · doi:10.1016/j.jegh.2011.11.005 · Cited by 47 · see citing works
Heart rate: An independent risk factor in cardiovascular disease
Hjalmarson, Å. (2007) · European Heart Journal Supplements · doi:10.1093/eurheartj/sum030 · Cited by 46 · see citing works
Secure stochastic ECG signals based on gaussian mixture model for e-healthcare systems
Wang, W., Wang, H., Hempel, M., Peng, D., Sharif, H., & Chen, H.-H. (2011) · IEEE Systems Journal · doi:10.1109/jsyst.2011.2165597 · Cited by 45 · see citing works
Data Analytics in Ubiquitous Sensor-Based Health Information Systems
Mukherjee, A., Pal, A., & Misra, P. (2012) · 2012 Sixth International Conference on Next Generation Mobile Applications, Services and Technologies · doi:10.1109/ngmast.2012.39 · Cited by 35 · see citing works
Low-energy formulations of support vector machine kernel functions for biomedical sensor applications
Lee, K. H., Kung, S.-Y., & Verma, N. (2012) · Journal of Signal Processing Systems · doi:10.1007/s11265-012-0672-8 · Cited by 35 · see citing works
Comparison of different signal processing methods for reducing artifacts from photoplethysmograph signal
Naraharisetti, K. V. P., & Bawa, M. (2011) · 2011 IEEE INTERNATIONAL CONFERENCE ON ELECTRO/INFORMATION TECHNOLOGY · doi:10.1109/eit.2011.5978571 · Cited by 35 · see citing works
Wearable sensor activity analysis using semi-Markov models with a grammar
Thomas, O., Sunehag, P., Dror, G., Yun, S., Kim, S., Robards, M., Smola, A. J., Green, D., & Saunders, P. U. (2010) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2010.01.002 · Cited by 34 · see citing works
Leveraging Knowledge From Physiological Data: On-Body Heat Stress Risk Prediction With Sensor Networks
Gaura, E., Kemp, J., & Brusey, J. (2013) · IEEE Transactions on Biomedical Circuits and Systems · doi:10.1109/tbcas.2013.2254485 · Cited by 32 · see citing works
Automatic detection of anomalies in blood glucose using a machine learning approach
Zhu, Y. (2011) · Journal of Communications and Networks · doi:10.1109/jcn.2011.6157411 · Cited by 31 · see citing works
Improving medical decision trees by combining relevant health-care criteria
López-Vallverdú, J. A., Riaño, D., & Bohada, J. A. (2012) · Expert Systems with Applications · doi:10.1016/j.eswa.2012.04.073 · Cited by 28 · see citing works
Inhaled activated protein C protects mice from ventilator-induced lung injury
Maniatis, N. A., Letsiou, E., Orfanos, S. E., Kardara, M., Dimopoulou, I., Νάκος, Γ., Lekka, M. E., Roussos, C. S., Armaganidis, A., & Kotanidou, A. N. (2010) · Critical Care · doi:10.1186/cc8976 · Cited by 28 · see citing works
Persuasive and Pervasive Sensing: A New Frontier to Monitor, Track and Assist Older Adults Suffering from Type-2 Diabetes
Chatterjee, S., Dutta, K., Xie, H. (., Byun, J., Pottathil, A., & Moore, M. (2013) · 2013 46th Hawaii International Conference on System Sciences · doi:10.1109/hicss.2013.618 · Cited by 28 · see citing works
An approach for real-time stress-trend detection using physiological signals in wearable computing systems for automotive drivers
Singh, R. R., Conjeti, S., & Banerjee, R. (2011) · 2011 14th International IEEE Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2011.6082900 · Cited by 27 · see citing works
Online mining abnormal period patterns from multiple medical sensor data streams
Huang, G., Zhang, Y., Cao, J., Steyn, M., & Taraporewalla, K. (2014) · World Wide Web · doi:10.1007/s11280-013-0203-y · Cited by 27 · see citing works
Automatic detection of anomalies in blood glucose using a machine learning approach
Zhu, Y. N. (2010) · IEEE International Conference on Information Reuse and Integration (IRI) · doi:10.1109/iri.2010.5558959 · Cited by 26 · see citing works
A lightweight anomaly detection framework for medical wireless sensor networks
Salem, O., Liu, Y., & Mehaoua, A. (2013) · 2013 IEEE Wireless Communications and Networking Conference (WCNC) · doi:10.1109/wcnc.2013.6555279 · Cited by 26 · see citing works
On-line adaptive trend extraction of multiple physiological signals for alarm filtering in intensive care units
Charbonnier, S., & Gentil, S. (2010) · International Journal of Adaptive Control and Signal Processing · doi:10.1002/acs.1123 · Cited by 26 · see citing works
Detecting specific health-related events using an integrated sensor system for vital sign monitoring
Adnane, M., Jiang, Z., Choi, S., & Jang, H. (2009) · Sensors · doi:10.3390/s90906897 · Cited by 23 · see citing works
Development of remote healthcare system for measuring and promoting healthy lifestyle
Youm, S., Lee, G., Park, S., & Zhu, W. (2010) · Expert Systems with Applications · doi:10.1016/j.eswa.2010.08.075 · Cited by 22 · see citing works
Online discovery of Heart Rate Variability patterns in mobile healthcare services
Vu, T. H. N., Park, N., Lee, Y. K., Lee, Y., Lee, J. Y., & Ryu, K. H. (2010) · Journal of Systems and Software · doi:10.1016/j.jss.2010.05.074 · Cited by 21 · see citing works
A Framework for Automatic Text Generation of Trends in Physiological Time Series Data
Banaee, H., Ahmed, M. U., & Loutfi, A. (2013) · 2013 IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2013.661 · Cited by 21 · see citing works
Self-citation
Health monitoring for elderly: An application using case-based reasoning and cluster analysis
Ahmed, M. U., Banaee, H., & Loutfi, A. (2013) · ISRN Artificial Intelligence · doi:10.1155/2013/380239 · Cited by 21 · see citing works
Self-citation
Robust preprocessing for health care monitoring framework
Ahmad, N. F., Hoang, D. B., & Phung, M. H. (2009) · 2009 11th International Conference on e-Health Networking, Applications and Services (Healthcom) · doi:10.1109/health.2009.5406196 · Cited by 21 · see citing works
Extraction and Analysis of features acquired by wearable sensors network
Bellos, C. C., Papadopoulos, A., Rosso, R., & Fotiadis, D. I. (2010) · Proceedings of the 10th IEEE International Conference on Information Technology and Applications in Biomedicine · doi:10.1109/itab.2010.5687761 · Cited by 21 · see citing works
Towards Health Data Stream Analytics
Zhang, Q., Pang, C., McBride, S. J., Hansen, D. T., Cheung, C., & Steyn, M. (2010) · ICME International Conference on Complex Medical Engineering (CME) · doi:10.1109/iccme.2010.5558827 · Cited by 20 · see citing works
Wearable sensing systems for healthcare monitoring
Yamada, I., & Lopez, G. F. (2012) · Symposium on VLSI Technology · doi:10.1109/vlsit.2012.6242435 · Cited by 19 · see citing works
Abnormal ECG signal detection based on compressed sampling in Wearable ECG sensor
Ding, H., Sun, H., & Hou, K.-M. (2011) · 2011 International Conference on Wireless Communications and Signal Processing (WCSP) · doi:10.1109/wcsp.2011.6096677 · Cited by 16 · see citing works
Ensemble Empirical Mode Decomposition and adaptive filtering for ECG signal enhancement
He, X., Goubran, R. A., & Liu, X. P. (2012) · IEEE International Symposium on Medical Measurements and Applications (MeMeA) · doi:10.1109/memea.2012.6226649 · Cited by 13 · see citing works
Categorization of patients' health status in COPD disease using a wearable platform and random forests methodology
Bellos, C., Papadopoulos, A., Rosso, R., & Fotiadis, D. I. (2012) · Proceedings of 2012 IEEE-EMBS International Conference on Biomedical and Health Informatics · doi:10.1109/bhi.2012.6211600 · Cited by 12 · see citing works
Support Vector Machine for Abnormal Pulse Classification
Thakker, B., & Vyas, A. L. (2011) · International Journal of Computer Applications · doi:10.5120/2597-3610 · Cited by 12 · see citing works
An intelligent decision support system for enhancing an m-health application
Ramesh, M. V., Anu, T. A., & Thirugnanam, H. (2012) · International Conference on Wireless and Optical Communications Networks (WOCN) · doi:10.1109/wocn.2012.6335564 · Cited by 10 · see citing works
Three-Tiered Data Mining for Big Data Patterns of Wireless Sensor Networks in Medical and Healthcare Domains
Yoon, J. P. (2013) · International Conference on Internet and Web Applications and Services · Cited by 8 · see citing works
Identifying Chronic Disease Complications Utilizing State of the Art Data Fusion Methodologies and Signal Processing Algorithms
Gialelis, J., Chondros, P., Karadimas, D., Dima, S., & Serpanos, D. (2012) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-642-29734-2_35 · Cited by 8 · see citing works
Experimental Study of the Stress Level at the Workplace Using an Smart Testbed of Wireless Sensor Networks and Ambient Intelligence Techniques
Silva, F., Olivares, T., Royo, F., Vergara, M. A., & Analide, C. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-38622-0_21 · Cited by 8 · see citing works
Salient Segmentation of Medical Time Series Signals
Woodbridge, J., Lan, M., Sarrafzadeh, M., & Bui, A. A. T. (2011) · IEEE International Conference on Healthcare Informatics, Imaging and Systems Biology · doi:10.1109/hisb.2011.41 · Cited by 8 · see citing works
Classification of Patients Using Novel Multivariate Time Series Representations of Physiological Data
Ordonez, P., Armstrong, T., Oates, T., & Fackler, J. (2011) · 2011 10th International Conference on Machine Learning and Applications and Workshops · doi:10.1109/icmla.2011.46 · Cited by 8 · see citing works
Processing body sensor data streams for continuous physiological monitoring
Pradhan, G. N., Chattopadhyay, R., & Panchanathan, S. (2010) · Proceedings of the international conference on Multimedia information retrieval · doi:10.1145/1743384.1743468 · Cited by 7 · see citing works
Mining of Sensor Data in Healthcare: A Survey.
Sow, D., Turaga, D. S., & Schmidt, J. M. (2013) · Cited by 7 · see citing works
A Support Vector Machine Approach for Categorization of Patients Suffering from Chronic Diseases
Bellos, C., Papadopoulos, A., Rosso, R., & Fotiadis, D. I. (2012) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-642-29734-2_36 · Cited by 5 · see citing works
An Association Rule Analysis Framework for Complex Physiological and Genetic Data
He, J., Zhang, Y., Huang, G., Xin, Y., Liu, X., Zhang, H., Chiang, S., & Zhang, H. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-29361-0_17 · Cited by 5 · see citing works
Automatic Annotation of Sensor Data Streams using Abductive Reasoning
Alirezaie, M., & Loutfi, A. (2013) · International Conference on Knowledge Engineering and Ontology Development · doi:10.5220/0004623403450354 · Cited by 4 · see citing works
Self-citation
Clinical quality guaranteed physiological data compression in mobile health monitoring
Yang, S., Kim, J., & Gerla, M. (2012) · doi:10.1145/2248341.2248351 · Cited by 4 · see citing works
Health Information Science
(2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-29361-0 · Cited by 4 · see citing works
Human State Classification and Predication for Critical Care Monitoring by Real-Time Bio-signal Analysis
Li, X., & Porikli, F. (2010) · 2010 20th International Conference on Pattern Recognition · doi:10.1109/icpr.2010.602 · Cited by 3 · see citing works
An automated program for mental stress and apnea/hypopnea events detection
Adnane, M., Jiang, Z., Mori, N., & Matsumoto, Y. (2011) · International Workshop on Systems, Signal Processing and their Applications, WOSSPA · doi:10.1109/wosspa.2011.5931412 · Cited by 2 · see citing works
A Comparison of Decision Analysis and Expert Rules for Sequential DiagnosisPreprint
Kalagnanam, J., & Henrion, M. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1304.2362 · Cited by 2 · see citing works
A Support Vector Machine Approach for Categorization of Patients Suffering from Chronic Diseases
Bellos, C. V., Papadopoulos, A. N., Rosso, R. S. U., Jr., & Fotiadis, D. I. (2012) · Wireless Mobile Communication and Healthcare · Cited by 2 · see citing works

Flagged first, then by citations

Sorted by citations

Wearable health devices-vital sign monitoring, systems and technologies
Dias, D., & Paulo Silva Cunha, J. (2018) · Sensors · doi:10.3390/s18082414 · Cited by 919 · see citing works
Multi-sensor fusion in body sensor networks: State-of-the-art and research challenges
Gravina, R., Alinia, P., Ghasemzadeh, H., & Fortino, G. (2017) · Information Fusion · doi:10.1016/j.inffus.2016.09.005 · Cited by 899 · see citing works
Wearable sensors for monitoring the physiological and biochemical profile of the athlete
Seshadri, D. R., Li, R. T., Voos, J. E., Rowbottom, J. R., Alfes, C. M., Zorman, C. A., & Drummond, C. K. (2019) · npj Digital Medicine · doi:10.1038/s41746-019-0150-9 · Cited by 537 · see citing works
The emergence of AI-based wearable sensors for digital health technology: a review
Shajari, S., Kuruvinashetti, K., Komeili, A., & Sundararaj, U. (2023) · Sensors · doi:10.3390/s23239498 · Cited by 535 · see citing works
Fog Assisted-IoT Enabled Patient Health Monitoring in Smart Homes
Verma, P., & Sood, S. K. (2018) · IEEE Internet of Things Journal · doi:10.1109/jiot.2018.2803201 · Cited by 473 · see citing works
A Survey of Healthcare Internet of Things (HIoT): A Clinical Perspective
Habibzadeh, H., Dinesh, K., Shishvan, O. R., Boggio-Dandry, A., Gaurav Sharma, A., & Soyata, T. (2019) · IEEE Internet of Things Journal · doi:10.1109/jiot.2019.2946359 · Cited by 419 · see citing works
ECG Monitoring Systems: Review, Architecture, Processes, and Key Challenges
Serhani, M. A., Kassabi, H. T. E., Ismail, H., & Navaz, A. N. (2020) · Sensors · doi:10.3390/s20061796 · Cited by 373 · see citing works
IoT Wearable Sensors and Devices in Elderly Care: A Literature Review
Stavropoulos, T. G., Papastergiou, A., Mpaltadoros, L., Nikolopoulos, S., & Kompatsiaris, I. Y. (2020) · Sensors · doi:10.3390/s20102826 · Cited by 366 · see citing works
Data-driven modeling and prediction of blood glucose dynamics: Machine learning applications in type 1 diabetes
Woldaregay, A. Z., Årsand, E., Walderhaug, S., Albers, D., Mamykina, L., Botsis, T., & Hartvigsen, G. (2019) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2019.07.007 · Cited by 358 · see citing works
A Systematic Review of Wearable Patient Monitoring Systems–Current Challenges and Opportunities for Clinical Adoption
Baig, M. M., GholamHosseini, H., Moqeem, A. A., Mirza, F., & Lindén, M. (2017) · Journal of Medical Systems · doi:10.1007/s10916-017-0760-1 · Cited by 351 · see citing works
Graphene-Based Sensors for Human Health Monitoring
Huang, H., Su, S., Wu, N., Wan, H., Wan, S., Bi, H., & Sun, L. (2019) · Frontiers in Chemistry · doi:10.3389/fchem.2019.00399 · Cited by 336 · see citing works
A multi-sensor data fusion enabled ensemble approach for medical data from body sensor networks
Muzammal, M., Talat, R., Sodhro, A. H., & Pirbhulal, S. (2020) · Information Fusion · doi:10.1016/j.inffus.2019.06.021 · Cited by 311 · see citing works
–Omic and Electronic Health Record Big Data Analytics for Precision Medicine
Wu, P.-Y., Cheng, C., Kaddi, C. D., Venugopalan, J., Hoffman, R., & Wang, M. D. (2016) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2016.2573285 · Cited by 308 · see citing works
Internet of Health Things: Toward intelligent vital signs monitoring in hospital wards
da Costa, C. A., Pasluosta, C. F., Eskofier, B. M., da Silva, D. B., & Righi, R. D. R. (2018) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2018.05.005 · Cited by 278 · see citing works
Impact of remote patient monitoring on clinical outcomes: An updated meta-analysis of randomized controlled trials
Noah, B., Keller, M. S., Mosadeghi, S., Stein, L., Johl, S., Delshad, S., Tashjian, V. C., Lew, D., Kwan, J. T., Jusufagic, A., et al. (2018) · npj Digital Medicine · doi:10.1038/s41746-017-0002-4 · Cited by 273 · see citing works
Cloud-centric IoT based disease diagnosis healthcare framework
Verma, P., & Sood, S. K. (2018) · Journal of Parallel and Distributed Computing · doi:10.1016/j.jpdc.2017.11.018 · Cited by 246 · see citing works
A Systematic Review of Wearable Sensors and IoT-Based Monitoring Applications for Older Adults – a Focus on Ageing Population and Independent Living
Baig, M. M., Afifi, S. M., GholamHosseini, H., & Mirza, F. (2019) · Journal of Medical Systems · doi:10.1007/s10916-019-1365-7 · Cited by 216 · see citing works
Computational Health Informatics in the Big Data Age: A Survey
Fang, R., Pouyanfar, S., Yang, Y., Chen, S.-C., & Iyengar, S. S. (2017) · ACM Computing Surveys · doi:10.1145/2932707 · Cited by 210 · see citing works
Translational bioinformatics in the era of real-time biomedical, health care and wellness data streams
Shameer, K., Badgeley, M. A., Miotto, R., Glicksberg, B. S., Morgan, J. W., & Dudley, J. T. (2017) · Briefings in Bioinformatics · doi:10.1093/bib/bbv118 · Cited by 198 · see citing works
AI-BASED SMART TEXTILE WEARABLES FOR REMOTE HEALTH SURVEILLANCE AND CRITICAL EMERGENCY ALERTS: A SYSTEMATIC LITERATURE REVIEW
Sarker, M. T. H., Ishtiaque, A., & Rahaman, M. A. (2023) · American Journal of Scholarly Research and Innovation · doi:10.63125/ceqapd08 · Cited by 190 · see citing works
Monitoring Methods of Human Body Joints: State-of-the-Art and Research Challenges
Faisal, A. I., Majumder, S., Mondal, T., Cowan, D., Naseh, S., & Deen, M. J. (2019) · Sensors · doi:10.3390/s19112629 · Cited by 187 · see citing works
An architecture and protocol for smart continuous eHealth monitoring using 5G
Lloret, J., Parra, L., Taha, M., & Tomás, J. (2017) · Computer Networks · doi:10.1016/j.comnet.2017.05.018 · Cited by 164 · see citing works
Data-Driven Blood Glucose Pattern Classification and Anomalies Detection: Machine-Learning Applications in Type 1 Diabetes
Woldaregay, A. Z., Årsand, E., Botsis, T., Albers, D. J., Mamykina, L., & Hartvigsen, G. (2019) · Journal of Medical Internet Research · doi:10.2196/11030 · Cited by 164 · see citing works
Towards a conceptual framework of OSH risk management in smart working environments based on smart PPE, ambient intelligence and the Internet of Things technologies
Podgórski, D., Majchrzycka, K., Dabrowska, A. K., Gralewicz, G., & Okrasa, M. (2016) · International Journal of Occupational Safety and Ergonomics · doi:10.1080/10803548.2016.1214431 · Cited by 153 · see citing works
RETRACTED ARTICLE: A secure remote health monitoring model for early disease diagnosis in cloud-based IoT environment
Akhbarifar, S., Javadi, H. H. S., Rahmani, A. M., & Hosseinzadeh, M. (2020) · Personal and Ubiquitous Computing · doi:10.1007/s00779-020-01475-3 · Cited by 149 · see citing works
Retracted
Handling big data: research challenges and future directions
Anagnostopoulos, I. E., Zeadally, S., & Expósito, E. (2016) · The Journal of Supercomputing · doi:10.1007/s11227-016-1677-z · Cited by 148 · see citing works
Cloud-centric IoT based student healthcare monitoring framework
Verma, P., Sood, S. K., & Kalra, S. (2017) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-017-0520-6 · Cited by 141 · see citing works
Integration of RFID, wireless sensor networks, and data mining in an e-pedigree food traceability system
Alfian, G., Rhee, J., Ahn, H., Lee, J., Farooq, U., Ijaz, M. F., & Syaekhoni, M. A. (2017) · Journal of Food Engineering · doi:10.1016/j.jfoodeng.2017.05.008 · Cited by 140 · see citing works
Real-time data analysis in health monitoring systems: A comprehensive systematic literature review
Paganelli, A. I., Mondéjar, A. G., da Silva, A. C., Silva-Calpa, G. F. M., Teixeira, M. F., Carvalho, F. G. D., Raposo, A. B., & Endler, M. (2022) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2022.104009 · Cited by 136 · see citing works
Know Thyself: A Theory of the Self for Personal Informatics
Rapp, A., & Tirassa, M. (2017) · Human-Computer Interaction · doi:10.1080/07370024.2017.1285704 · Cited by 134 · see citing works
Ethical perspectives on recommending digital technology for patients with mental illness
Bauer, M., Glenn, T., Monteith, S., Bauer, R., Whybrow, P. C., & Geddes, J. R. (2017) · International Journal of Bipolar Disorders · doi:10.1186/s40345-017-0073-9 · Cited by 132 · see citing works
Tough, anti-freezing and conductive ionic hydrogels
Wu, S., Wang, T., Du, Y., Yao, B., Duan, S., Yan, Y., Hua, M., Alsaid, Y., Zhu, X., & He, X. (2022) · NPG Asia Materials · doi:10.1038/s41427-022-00410-7 · Cited by 126 · see citing works
Wearable technologies for active living and rehabilitation: Current research challenges and future opportunities
Rodgers, M. M., Alon, G., Pai, V. M., & Conroy, R. S. (2019) · Journal of Rehabilitation and Assistive Technologies Engineering · doi:10.1177/2055668319839607 · Cited by 119 · see citing works
A conceptual IoT-based early-warning architecture for remote monitoring of COVID-19 patients in wards and at home
Paganelli, A. I., Velmovitsky, P. E., de Miranda, P. C., Branco, A. F., Alencar, P., Cowan, D. D., Endler, M., & Morita, P. P. (2021) · Internet of Things · doi:10.1016/j.iot.2021.100399 · Cited by 117 · see citing works
A review of analytics and clinical informatics in health care
Simpao, A. F., Ahumada, L. M., Gálvez, J. A., & Rehman, M. A. (2014) · Journal of Medical Systems · doi:10.1007/s10916-014-0045-x · Cited by 154 · see citing works
Use and performance of machine learning models for type 2 diabetes prediction in community settings: A systematic review and meta-analysis
Silva, K. D., Lee, W. K., Forbes, A. B., Demmer, R. T., Barton, C., & Enticott, J. (2020) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2020.104268 · Cited by 108 · see citing works
An accurate and dynamic predictive model for a smart M-Health system using machine learning
Qureshi, K. N., Din, S., Jeon, G., & Piccialli, F. (2020) · Information Sciences · doi:10.1016/j.ins.2020.06.025 · Cited by 107 · see citing works
Smart city architecture for community level services through the internet of things
Jalali, R., El‐Khatib, K., & McGregor, C. (2015) · International Conference on Intelligence in Next Generation Networks · doi:10.1109/icin.2015.7073815 · Cited by 104 · see citing works
New Measures of Mental State and Behavior Based on Data Collected From Sensors, Smartphones, and the Internet
Glenn, T., & Monteith, S. (2014) · Current Psychiatry Reports · doi:10.1007/s11920-014-0523-3 · Cited by 104 · see citing works
Big data and visual analytics in anaesthesia and health care
Allan F. Simpao, M., Ahumada, L. M., & Rehman, M. A. (2015) · British Journal of Anaesthesia · doi:10.1093/bja/aeu552 · Cited by 103 · see citing works
Kinect and wearable inertial sensors for motor rehabilitation programs at home: state of the art and an experimental comparison
Milosevic, B., Leardini, A., & Farella, E. (2020) · BioMedical Engineering OnLine · doi:10.1186/s12938-020-00762-7 · Cited by 103 · see citing works
Machine learning for sperm selection
You, J. B., McCallum, C., Wang, Y., Riordon, J., Nosrati, R., & Sinton, D. A. (2021) · Nature Reviews Urology · doi:10.1038/s41585-021-00465-1 · Cited by 101 · see citing works
A Semantic Big Data Platform for Integrating Heterogeneous Wearable Data in Healthcare
Mezghani, E., Expósito, E., Drira, K., Silveira, M. D., & Pruski, C. (2015) · Journal of Medical Systems · doi:10.1007/s10916-015-0344-x · Cited by 100 · see citing works
Healthcare and anomaly detection: using machine learning to predict anomalies in heart rate data
Šabić, E., Keeley, D., Henderson, B., & Nannemann, S. (2020) · AI & Society · doi:10.1007/s00146-020-00985-1 · Cited by 99 · see citing works
Use of wearable sensors for pregnancy health and environmental monitoring: Descriptive findings from the perspective of patients and providers
Runkle, J., Sugg, M., Boase, D., Galvin, S. L., & C. Coulson, C. (2019) · DIGITAL HEALTH · doi:10.1177/2055207619828220 · Cited by 98 · see citing works
A new Internet of Things architecture for real-time prediction of various diseases using machine learning on big data environment
Ed-daoudy, A., & Maalmi, K. (2019) · Journal Of Big Data · doi:10.1186/s40537-019-0271-7 · Cited by 96 · see citing works
Energy efficient clustering with disease diagnosis model for IoT based sustainable healthcare systems
Bharathi, R., Abirami, T., Dhanasekaran, S., Gupta, D. K., Khanna, A. K., Elhoseny, M., & Shankar, K. (2020) · Sustainable Computing Informatics and Systems · doi:10.1016/j.suscom.2020.100453 · Cited by 96 · see citing works
Using Psychophysiological Sensors to Assess Mental Workload During Web Browsing
Jimenez-Molina, A., Retamal, C., & Lira, H. (2018) · Sensors · doi:10.3390/s18020458 · Cited by 95 · see citing works
Modeling Heart Rate and Activity Data for Personalized Fitness Recommendation
Ni, J., Muhlstein, L., & McAuley, J. (2019) · The World Wide Web Conference · doi:10.1145/3308558.3313643 · Cited by 94 · see citing works
Highly sensitive ammonia sensor for diagnostic purpose using reduced graphene oxide and conductive polymer
Nhiem, L. T., & Park, S. (2018) · Scientific Reports · doi:10.1038/s41598-018-36468-z · Cited by 89 · see citing works
Promises and Challenges in the Use of Consumer-Grade Devices for Sleep Monitoring
Roomkham, S., Lovell, D. R., Cheung, J., & Perrin, D. (2018) · IEEE Reviews in Biomedical Engineering · doi:10.1109/rbme.2018.2811735 · Cited by 84 · see citing works
A Validation Study of Freezing of Gait (FoG) Detection and Machine-Learning-Based FoG Prediction Using Estimated Gait Characteristics with a Wearable Accelerometer
Aich, S., Pradhan, P. M., Park, J., Sethi, N. K., Vathsa, V. S. S., & Kim, H. (2018) · Sensors · doi:10.3390/s18103287 · Cited by 84 · see citing works
Big Healthcare Data Analytics: Challenges and Applications
Lee, C., Luo, Z., Ngiam, K. Y., Zhang, M., Zheng, K., Chen, G., Ooi, B. C., & Yip, W. L. J. (2017) · Scalable computing and communications · doi:10.1007/978-3-319-58280-1_2 · Cited by 83 · see citing works
Transforming sensor data to the image domain for deep learning — An application to footstep detection
Singh, M. S., Pondenkandath, V., Zhou, B., Lukowicz, P., & Liwicki, M. (2017) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2017.7966182 · Cited by 81 · see citing works
Recent trends and challenges in predictive maintenance of aircraft’s engine and hydraulic system
Khan, K., Sohaib, M., Rashid, A., Ali, S., Akbar, H., Basit, A., & Ahmad, T. (2021) · Journal of the Brazilian Society of Mechanical Sciences and Engineering · doi:10.1007/s40430-021-03121-2 · Cited by 79 · see citing works
Recognition of Sedentary Behavior by Machine Learning Analysis of Wearable Sensors during Activities of Daily Living for Telemedical Assessment of Cardiovascular Risk
Kańtoch, E. (2018) · Sensors · doi:10.3390/s18103219 · Cited by 77 · see citing works
Health risk assessment and decision-making for patient monitoring and decision-support using Wireless Body Sensor Networks
Habib, C., Makhoul, A., Darazi, R., & Couturier, R. (2018) · Information Fusion · doi:10.1016/j.inffus.2018.06.008 · Cited by 76 · see citing works
Anomaly Detection Framework for Wearables Data: A Perspective Review on Data Concepts, Data Analysis Algorithms and Prospects
Sunny, J. S., Patro, C. P. K., Karnani, K., Pingle, S. C., Lin, F., Anekoji, M., Jones, L., Kesari, S., & Ashili, S. (2022) · Sensors · doi:10.3390/s22030756 · Cited by 73 · see citing works
Using data to advance service: managerial issues and theoretical implications from action research
Lim, C., Kim, M.-J., Kim, K.-H., Kim, K.-J., & Maglio, P. P. (2017) · Journal of Service Theory and Practice · doi:10.1108/jstp-08-2016-0141 · Cited by 72 · see citing works
Multi-level assessment model for wellness service based on human mental stress level
Jung, Y., & Yoon, Y. I. (2016) · Multimedia Tools and Applications · doi:10.1007/s11042-016-3444-9 · Cited by 68 · see citing works
Remaining useful life prediction via a variational autoencoder and a time‐window‐based sequence neural network
Su, C., Li, L., & Wen, Z. (2020) · Quality and Reliability Engineering International · doi:10.1002/qre.2651 · Cited by 67 · see citing works
Recent Advances in Artificial Intelligence and Wearable Sensors in Healthcare Delivery
Junaid, S. B., Imam, A. A., Abdulkarim, M., Surakat, Y. A., Balogun, A. O., Kumar, G., Shuaibu, A. N., Garba, A., Sahalu, Y., Mohammed, A., et al. (2022) · Applied Sciences · doi:10.3390/app122010271 · Cited by 65 · see citing works
Detecting physical activity within lifelogs towards preventing obesity and aiding ambient assisted living
Dobbins, C., Rawassizadeh, R., & Momeni, E. (2016) · Neurocomputing · doi:10.1016/j.neucom.2016.02.088 · Cited by 65 · see citing works
The Design of an Automated System for the Analysis of the Activity and Emotional Patterns of Dogs with Wearable Sensors Using Machine Learning
Aich, S., Chakraborty, S., Sim, J. S., Jang, D.-J., & Kim, H. (2019) · Applied Sciences · doi:10.3390/app9224938 · Cited by 63 · see citing works
A systematic review of feasibility studies promoting the use of mobile technologies in clinical research
Bakker, J. P., Goldsack, J. C., Clarke, M. J., Coravos, A., Geoghegan, C., Godfrey, A., Heasley, M. G., Karlin, D. R., Manta, C. J., Peterson, B., et al. (2019) · npj Digital Medicine · doi:10.1038/s41746-019-0125-x · Cited by 63 · see citing works
Palladium/palladium oxide coated electrospun fibers for wearable sweat pH-sensors
Diculescu, V. C., Beregoi, M., Evanghelidis, A., Negrea, R., Apostol, N. G., & Enculescu, I. (2019) · Scientific Reports · doi:10.1038/s41598-019-45399-2 · Cited by 63 · see citing works
From Personalized Medicine to Population Health: A Survey of mHealth Sensing Techniques
Wang, Z., Xiong, H., Zhang, J., Yang, S., Boukhechba, M., Zhang, D., Barnes, L. E., & Dou, D. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3161046 · Cited by 62 · see citing works
Graphene and Its Derivatives: Synthesis and Application in the Electrochemical Detection of Analytes in Sweat
Singh, A., Ahmed, A., Sharma, A., & Arya, S. K. (2022) · Biosensors · doi:10.3390/bios12100910 · Cited by 62 · see citing works
Machine and Deep Learning Models for Stress Detection Using Multimodal Physiological Data
Abdelfattah, E., Joshi, S., & Tiwari, S. (2025) · IEEE Access · doi:10.1109/access.2024.3525459 · Cited by 62 · see citing works
Advancing hospital healthcare: achieving IoT-based secure health monitoring through multilayer machine learning
Qi, K. (2025) · Journal Of Big Data · doi:10.1186/s40537-024-01038-w · Cited by 61 · see citing works
An Internet of Things (IoT) Application for Predicting the Quantity of Future Heart Attack Patients
Ahmed, F. (2017) · International Journal of Computer Applications · doi:10.5120/ijca2017913773 · Cited by 61 · see citing works
A medical monitoring scheme and health‐medical service composition model in cloud‐based IoT platform
Asghari, P., Rahmani, A. M., & Javadi, H. H. S. (2019) · Transactions on Emerging Telecommunications Technologies · doi:10.1002/ett.3637 · Cited by 61 · see citing works
Detecting and Classifying Self-injurious Behavior in Autism Spectrum Disorder Using Machine Learning Techniques
Cantin-Garside, K. D., Kong, Z., White, S. W., Antezana, L., Kim, S., & Nussbaum, M. A. (2020) · Journal of Autism and Developmental Disorders · doi:10.1007/s10803-020-04463-x · Cited by 61 · see citing works
Energy-Efficient Integration of Continuous Context Sensing and Prediction into Smartwatches
Rawassizadeh, R., Tomitsch, M., Nourizadeh, M., Momeni, E., Peery, A., Ulanova, L., & Pazzani, M. J. (2015) · Sensors · doi:10.3390/s150922616 · Cited by 60 · see citing works
M4CVD: Mobile Machine Learning Model for Monitoring Cardiovascular Disease
Boursalie, O., Samavi, R., & Doyle, T. E. (2015) · Procedia Computer Science · doi:10.1016/j.procs.2015.08.357 · Cited by 60 · see citing works
Personalized Health Monitoring System of Elderly Wellness at the Community Level in Hong Kong
Yu, L., Chan, W. M., Zhao, Y., & Tsui, K. (2018) · IEEE Access · doi:10.1109/access.2018.2848936 · Cited by 60 · see citing works
Decision support system for arrhythmia prediction using convolutional neural network structure without preprocessing
Fujita, H., & Cimr, D. (2019) · Applied Intelligence · doi:10.1007/s10489-019-01461-0 · Cited by 59 · see citing works
Assessment and prioritisation of Healthcare 4.0 implementation in hospitals using Quality Function Deployment
Tortorella, G. L., Fogliatto, F. S., Vijaya Sunder, M., Vergara, A., & Vassolo, R. S. (2021) · International Journal of Production Research · doi:10.1080/00207543.2021.1912429 · Cited by 57 · see citing works
Exploring the Lived Experience of Behavior Change Technologies: Towards an Existential Model of Behavior Change for HCI
Rapp, A., & Boldi, A. (2023) · ACM Transactions on Computer-Human Interaction · doi:10.1145/3603497 · Cited by 57 · see citing works
Advances in breast cancer diagnosis: a comprehensive review of imaging, biosensors, and emerging wearable technologies
Khan, A. Q., Touseeq, M., Rehman, S., Tahir, M., Ashfaq, M., Jaffar, E., & Abbasi, S. F. (2025) · Frontiers in Oncology · doi:10.3389/fonc.2025.1587517 · Cited by 57 · see citing works
Patchable micro/nanodevices interacting with skin
Bai, W., Kuang, T., Chitrakar, C., Yang, R., Li, S., Zhu, D., & Chang, L. (2018) · Biosensors and Bioelectronics · doi:10.1016/j.bios.2018.09.035 · Cited by 56 · see citing works
AnoFed: Adaptive anomaly detection for digital health using transformer-based federated learning and support vector data description
Raza, A., Tran, K. P., Koehl, L., & Li, S. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106051 · Cited by 55 · see citing works
A Comprehensive Survey on Wearable Computing for Mental and Physical Health Monitoring
Elfouly, T., & Alouani, A. T. (2025) · Electronics · doi:10.3390/electronics14173443 · Cited by 56 · see citing works
A systematic literature review of data science, data analytics and machine learning applied to healthcare engineering systems
Salazar-Reyna, R., Aleu, F. G., Gutiérrez, E. M. A. G., Díaz-Ramírez, J., Garza‐Reyes, J. A., & Kumar, A., V (2020) · Management Decision · doi:10.1108/md-01-2020-0035 · Cited by 53 · see citing works
Trajectories, bifurcations, and pseudo-time in large clinical datasets: applications to myocardial infarction and diabetes data
Golovenkin, S. E., Bac, J., Chervov, A., Mirkes, E. M., Orlova, Y. V., Barillot, E., Gorban, A. N., & Zinovyev, A. Y. (2020) · GigaScience · doi:10.1093/gigascience/giaa128 · Cited by 52 · see citing works
A Scheduling Mechanism Based on Optimization Using IoT-Tasks Orchestration for Efficient Patient Health Monitoring
Iqbal, N., Imran, I., Ahmad, S., Ahmad, R., & Kim, D. (2021) · Sensors · doi:10.3390/s21165430 · Cited by 52 · see citing works
Big Data and Predictive Analytics
Suresh, S. (2016) · Pediatric Clinics of North America · doi:10.1016/j.pcl.2015.12.007 · Cited by 51 · see citing works
Big data for bipolar disorder
Monteith, S., Glenn, T., Geddes, J. R., Whybrow, P. C., & Bauer, M. (2016) · International Journal of Bipolar Disorders · doi:10.1186/s40345-016-0051-7 · Cited by 50 · see citing works
Estrous detection by continuous measurements of vaginal temperature and conductivity with supervised machine learning in cattle
Higaki, S., Miura, R., Suda, T., Andersson, L. M., Okada, H., Zhang, Y., Itoh, T., Miwakeichi, F., & Yoshioka, K. (2018) · Theriogenology · doi:10.1016/j.theriogenology.2018.09.038 · Cited by 50 · see citing works
Thermal Energy Harvesting on the Bodily Surfaces of Arms and Legs through a Wearable Thermo-Electric Generator
Proto, A., Bibbo, D., Černý, M., Vala, D., Kašík, V., Peter, L., Conforto, S., Schmid, M., & Penhaker, M. (2018) · Sensors · doi:10.3390/s18061927 · Cited by 48 · see citing works
Ambient Assisted Living [Guest editors' introduction]
Monekosso, D., Flórez‐Revuelta, F., & Remagnino, P. (2015) · IEEE Intelligent Systems · doi:10.1109/mis.2015.63 · Cited by 47 · see citing works
Robust and Accurate Modeling Approaches for Migraine Per-Patient Prediction from Ambulatory Data
Pagán, J., Orbe, M.-I. D., Gago‐Veiga, A. B., Sobrado, M., Risco‐Martín, J. L., Mora, J., Moya, J. M., & Ayala, J. L. (2015) · Sensors · doi:10.3390/s150715419 · Cited by 47 · see citing works
Flexible Sensors for Pressure Therapy: Effect of Substrate Curvature and Stiffness on Sensor Performance
Khodasevych, I. E., Parmar, S., & Troynikov, O. (2017) · Sensors · doi:10.3390/s17102399 · Cited by 47 · see citing works
Modeling perceived stress via HRV and accelerometer sensor streams
Wu, M., Cao, H., Nguyen, H.-L., Surmacz, K., & Hargrove, C. (2015) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2015.7318686 · Cited by 47 · see citing works
Big Data for Context Aware Computing – Perspectives and Challenges
Subbu, K. P., & Vasilakos, A. V. (2017) · Big Data Research · doi:10.1016/j.bdr.2017.10.002 · Cited by 45 · see citing works
Biosensor for rapid and accurate detection of cardiovascular biomarkers: Progress and prospects in biosensors
Nazir, S., & Iqbal, R. A. (2023) · Biosensors and Bioelectronics X · doi:10.1016/j.biosx.2023.100388 · Cited by 44 · see citing works
Nursing and mHealth
Samples, C., Ni, Z., & Shaw, R. J. (2014) · International Journal of Nursing Sciences · doi:10.1016/j.ijnss.2014.08.002 · Cited by 44 · see citing works
PASS: A Multimodal Database of Physical Activity and Stress for Mobile Passive Body/ Brain-Computer Interface Research
Parent, M., Albuquerque, I., Tiwari, A., Cassani, R., Gagnon, J.-F., Lafond, D., Tremblay, S., & Falk, T. H. (2020) · Frontiers in Neuroscience · doi:10.3389/fnins.2020.542934 · Cited by 44 · see citing works
Non-Invasive Data Acquisition and IoT Solution for Human Vital Signs Monitoring: Applications, Limitations and Future Prospects
Salem, M., Elkaseer, A., El-Maddah, I. A. M., Youssef, K. Y., Scholz, S. G., & Mohamed, H. K. (2022) · Sensors · doi:10.3390/s22176625 · Cited by 43 · see citing works
The path from big data to precision medicine
Huang, B. E., Mulyasasmita, W., & Rajagopal, G. (2016) · Expert Review of Precision Medicine and Drug Development · doi:10.1080/23808993.2016.1157686 · Cited by 43 · see citing works

Authors: Banaee, H., Ahmed, M., & Loutfi, A.
Affiliations: Örebro University (SE)
Corresponding author: Banaee, Hadi
ORCID: Banaee, Hadi
Ahmed, Mobyen
Loutfi, Amy
Venue: Sensors
Publisher: MDPI AG
Published: 2013-12-17
Volume: 13
Issue: 12
Pages: 17472-17500
ISSN: 1424-8220 (ISSN-L)
DOI: 10.3390/s131217472
PMC: PMC3892855
OpenAlex: W2146884567
Semantic Scholar: 1b8ac910c710b035c4601dc628587dafec25dad7
Cited by: 452
References: 107
Citations by year: 2026: 13 · 2025: 26 · 2024: 28 · 2023: 33 · 2022: 36 · 2021: 45 · 2020: 42 · 2019: 49 · 2018: 49 · 2017: 48 · 2016: 48 · 2015: 26 · 2014: 8
FWCI: 2.56
Type: journal article
Language: en
Open access: gold
doi.org
Licence: cc-by
creativecommons.org/licenses/by/3.0/ (vor)
Locations: Sensors (publishedVersion, cc-by)
Europe PMC (PubMed Central) (publishedVersion, cc-by)
PubMed Central (publishedVersion, cc-by)
PubMed (publishedVersion)
Örebro University Library (Örebro University) (submittedVersion, other-oa)
DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics: Physical Sciences › Engineering › Biomedical Engineering › Non-Invasive Vital Sign Monitoring
Physical Sciences › Computer Science › Signal Processing › Time Series Analysis and Forecasting
Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
Keywords: wearable sensors, health monitoring system, physiological monitoring, vital signs, data mining, anomaly detection, time series forecasting, decision-making, continuous time series, machine learning, population aging
MeSH terms: Algorithms, Artificial Intelligence, Humans, Monitoring, Physiologic, Biosensing Techniques, Monitoring, Ambulatory, Data Mining

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Claims read by deepseek-v4.1-flash under definition version 3 (extract-v3) on 2026-10-09.

Classified by jev-1.13-20260917 (gold-guideline-v0.2) on 2026-10-09.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data Mining for Wearable Sensors in Health Monitoring Systems: A Review of Recent Trends and Challenges

Abstract

AI snapshot

TL;DR

Key findings

Methods

Limitations

Integrity signals

Claims the paper makes

Claims other papers make about this one

Self-check

Cites

Cited by

Related

Record

About these checks