Fusion of Smartphone Motion Sensors for Physical Activity Recognition
Open accessThe DOI matches its Crossref record; 43 of the 45 references it cites were found in a registry or an index.
Abstract
For physical activity recognition, smartphone sensors, such as an accelerometer and a gyroscope, are being utilized in many research studies. So far, particularly, the accelerometer has been extensively studied. In a few recent studies, a combination of a gyroscope, a magnetometer (in a supporting role) and an accelerometer (in a lead role) has been used with the aim to improve the recognition performance. How and when are various motion sensors, which are available on a smartphone, best used for better recognition performance, either individually or in combination? This is yet to be explored. In order to investigate this question, in this paper, we explore how these various motion sensors behave in different situations in the activity recognition process. For this purpose, we designed a data collection experiment where ten participants performed seven different activities carrying smart phones at different positions. Based on the analysis of this data set, we show that these sensors, except the magnetometer, are each capable of taking the lead roles individually, depending on the type of activity being recognized, the body position, the used data features and the classification method employed (personalized or generalized). We also show that their combination only improves the overall recognition performance when their individual performances are not very high, so that there is room for performance improvement. We have made our data set and our data collection application publicly available, thereby making our experiments reproducible.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures
















Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“This fragmentation stems from varying sensor characteristics across devices (e.g., watches, phones, wristbands), placement-dependent data variations, diverse sensing specifications [38,41,43], and inconsistent activity taxonomies [43].”
From Towards Customizable Foundation Models for Human Activity Recognition with Wearable Devices (2025) · cites this paper as [41]
Experimental — accuracy not yet measuredIn the citing paper
“In previous studies, features extracted from Micro-Electro-Mechanical Systems (MEMS) signals revealed that the gyroscope and accelerometer signals contain the most information about human motion because they measure kinematic motion indirectly [19].”
From Deep CNN-LSTM With Self-Attention Model for Human Activity Recognition Using Wearable Sensor (2022) · cites this paper as [19]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
The WEKA data mining software: an update
Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., & Witten, I. H. (2009) · ACM SIGKDD Explorations Newsletter · doi:10.1145/1656274.1656278 · Cited by 17,750 · cited 3×
“In order to analyze the preprocessed data, we used the WEKA machine learning tool (Waikato Environment for Knowledge Analysis) [37,38].”
MethodActivity Recognition from User-Annotated Acceleration Data
Bao, L., & Intille, S. S. (2004) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-24646-6_1 · Cited by 3,147 · cited 2×
“We used the sliding window approach with an overlap of 50% (1 s overlap here), based on the reporting of previous studies [3,34,35].”
Anguita, D., Ghio, A., Oneto, L., Parra, X., & Reyes-Ortiz, J. L. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-35395-6_30 · Cited by 971 · cited 2×
“The SVM classifier is implemented on smartphones in [20,42].”
MethodHealthcare in the pocket: Mapping the space of mobile-phone health interventions
Klasnja, P., & Pratt, W. (2012) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2011.08.017 · Cited by 970 · cited 1×
“Physical activity recognition using wearable sensors has enabled the scientific community to develop novel applications, especially in the area of healthcare and assisted living [1,2].”
Driving style recognition using a smartphone as a sensor platform
Johnson, D. A., & Trivedi, M. M. (2011) · 2011 14th International IEEE Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2011.6083078 · Cited by 727 · cited 1×
“Moreover, an accelerometer and a gyroscope were combined to detect certain dangerous driving behaviors in [15,16].”
Accurate, Fast Fall Detection Using Gyroscopes and Accelerometer-Derived Posture Information
Li, Q., Stankovic, J. A., Hanson, M. A., Barth, A. T., Lach, J., & Zhou, G. (2009) · 2009 Sixth International Workshop on Wearable and Implantable Body Sensor Networks · doi:10.1109/bsn.2009.46 · Cited by 584
Preprocessing techniques for context recognition from accelerometer data
Figo, D., Diniz, P. C., Ferreira, D. R., & Cardoso, J. M. P. (2010) · Personal and Ubiquitous Computing · doi:10.1007/s00779-010-0293-9 · Cited by 578 · cited 10×
“Though time domain features are computationally cheap compared to frequency domain features, due to the expensive Fourier transformation [4,8], we still chose one feature set from the frequency domain to validate our results in a generic way.”
InfluentialPreece, S. J., Goulermas, J. Y., Kenney, L. P. J., & Howard, D. (2009) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2008.2006190 · Cited by 551 · cited 4×
“We used the sliding window approach with an overlap of 50% (1 s overlap here), based on the reporting of previous studies [3,34,35].”
InfluentialWEKA: The Waikato Environment for Knowledge Analysis
Garner, S. (1996) · Cited by 508
BeWell: A Smartphone Application to Monitor, Model and Promote Wellbeing
Lane, N., Mohammod, M., Lin, M., Yang, X., Lu, H., Ali, S., Doryab, A., Berke, E., Choudhury, T., & Campbell, A. (2011) · Proceedings of the 5th International ICST Conference on Pervasive Computing Technologies for Healthcare · doi:10.4108/icst.pervasivehealth.2011.246161 · Cited by 409 · cited 1×
“Physical activity recognition using wearable sensors has enabled the scientific community to develop novel applications, especially in the area of healthcare and assisted living [1,2].”
Research works printed but not linked: 1
- Bao, L., and Intille, S.S. (2004). Pervasive Computing, Springer.
Cited by
Deep learning for cyber security intrusion detection: Approaches, datasets, and comparative study
Ferrag, M. A., Maglaras, L., Moschoyiannis, S., & Janicke, H. (2020) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2019.102419 · Cited by 1,130
Human activity recognition with smartphone sensors using deep learning neural networks
Ronao, C. A., & Cho, S.-B. (2016) · Expert Systems with Applications · doi:10.1016/j.eswa.2016.04.032 · Cited by 1,215
“This may be attributed to the lesser waveform frequencies of sensor data from stationary activities than from moving ones, of which convnet is also sensitive to, as was found in speech ( Swietojanski, Ghoshal, & Renals, 2014 ).”
Nweke, H. F., Teh, Y. W., Al-garadi, M. A., & Alo, U. R. (2018) · Expert Systems with Applications · doi:10.1016/j.eswa.2018.03.056 · Cited by 930
Deep Learning for Sensor-based Human Activity Recognition
Chen, K., Zhang, D., Yao, L., Guo, B., Yu, Z., & Liu, Y. (2022) · ACM Computing Surveys · doi:10.1145/3447744 · Cited by 690
Human Activity Recognition Using Wearable Sensors by Deep Convolutional Neural Networks
Jiang, W., & Yin, Z. (2015) · Proceedings of the 23rd ACM international conference on Multimedia · doi:10.1145/2733373.2806333 · Cited by 676
“Especially, activity recognition based on wearable sensors is directly related to our daily lives such as healthcare and workout monitoring [3][4].”
BackgroundDeep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances
Zhang, S., Li, Y., Zhang, S., Shahabi, F., Xia, S., Deng, Y., & Alshurafa, N. (2022) · Sensors · doi:10.3390/s22041476 · Cited by 625
UniMiB SHAR: A Dataset for Human Activity Recognition Using Acceleration Data from Smartphones
Micucci, D., Mobilio, M., & Napoletano, P. (2017) · doi:10.20944/preprints201706.0033.v2 · Cited by 596
UniMiB SHAR: A Dataset for Human Activity Recognition Using Acceleration Data from Smartphones
Micucci, D., Mobilio, M., & Napoletano, P. (2017) · Applied Sciences · doi:10.3390/app7101101 · Cited by 596
Predictive Maintenance and Intelligent Sensors in Smart Factory: Review
Pech, M., Vrchota, J., & Bednář, J. (2021) · Sensors · doi:10.3390/s21041470 · Cited by 461
A Survey of Online Activity Recognition Using Mobile Phones
Shoaib, M., Bosch, S., Incel, O., Scholten, H., & Havinga, P. (2015) · Sensors · doi:10.3390/s150102059 · Cited by 489
“We have shown previously [10] that a gyroscope is unable to differentiate between the sitting and the standing activity.”
BackgroundSelf-citationComplex Human Activity Recognition Using Smartphone and Wrist-Worn Motion Sensors
Shoaib, M., Bosch, S., Incel, O., Scholten, H., & Havinga, P. (2016) · Sensors · doi:10.3390/s16040426 · Cited by 423
“We had shown previously that the accelerometer performs poorly at recognizing walking upstairs and downstairs and needs additional gyroscope data for better recognition of these two activities [12].”
BackgroundMethodInfluentialSelf-citationWang, Z., Yang, Z., & Dong, T. (2017) · Sensors · doi:10.3390/s17020341 · Cited by 355
“Readers should refer to [66] for detailed information concerning how to assess a feature set.”
BackgroundMethodInfluentialDeep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities
Chen, K., Zhang, D., Yao, L., Guo, B., Yu, Z., & Liu, Y. (2020) · arXiv · doi:10.48550/arxiv.2001.07416 · Cited by 314
The relationship between mobile phone location sensor data and depressive symptom severity
Saeb, S., Lattie, E. G., Schueller, S. M., Kording, K. P., & Mohr, D. C. (2016) · PeerJ · doi:10.7717/peerj.2537 · Cited by 313
Performance Analysis of Smartphone-Sensor Behavior for Human Activity Recognition
Chen, Y., & Shen, C. (2017) · IEEE Access · doi:10.1109/access.2017.2676168 · Cited by 297
“So far, only a few researches consider the impact of the smartphone-placement [9], [25], [26], [29].”
BackgroundMethodInfluentialDeep CNN-LSTM With Self-Attention Model for Human Activity Recognition Using Wearable Sensor
Khatun, M. A., Yousuf, M. A., Ahmed, S., Uddin, M. Z., Alyami, S. A., Al-Ashhab, S., Akhdar, H. F., Khan, A., Azad, A., & Moni, M. A. (2022) · IEEE Journal of Translational Engineering in Health and Medicine · doi:10.1109/jtehm.2022.3177710 · Cited by 288
“In previous studies, features extracted from Micro-Electro-Mechanical Systems (MEMS) signals revealed that the gyroscope and accelerometer signals contain the most information about human motion because they measure kinematic motion indirectly [19].”
A systematic review of smartphone-based human activity recognition methods for health research
Straczkiewicz, M., James, P., & Onnela, J.-P. (2021) · npj Digital Medicine · doi:10.1038/s41746-021-00514-4 · Cited by 247
“Some studies showed that the use of a single sensor can yield similar accuracy of activity recognition as using multiple sensors in combination 32 .”
BackgroundHuman Activity Recognition Using Inertial Sensors in a Smartphone: An Overview
Sousa Lima, W., Souto, E., El-Khatib, K., Jalali, R., & Gama, J. (2019) · Sensors · doi:10.3390/s19143213 · Cited by 256
Islam, M. M., Nooruddin, S., Karray, F., & Muhammad, G. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.106060 · Cited by 217
“[38] 2015 UCI [93], USCHAD [94], SHO [95] DCNN+, DCNN Accuracy = 99.”
A Comprehensive Analysis on Wearable Acceleration Sensors in Human Activity Recognition
Janidarmian, M., Roshan Fekr, A., Radecka, K., & Zilic, Z. (2017) · Sensors · doi:10.3390/s17030529 · Cited by 217
“(14) [25] 10 (25–30 year) accelerometer gyroscope magnetometer (Samsung Galaxy S II) 50 Hz right and left jeans pocket, belt position towards the right leg, right upper arm, right wrist (5) walking, sitting, standing, walking upstairs and downstairs, jogging, biking (8) All test protocols were carried inside a buildin…”
BackgroundMethodInfluentialTracking the Evolution of Smartphone Sensing for Monitoring Human Movement
Del Rosario, M., Redmond, S., & Lovell, N. (2015) · Sensors · doi:10.3390/s150818901 · Cited by 198
“Combining these estimates of walking distance with models (developed from MLAs) that characterise physical movement [65,103–105] will facilitate long-term, non-invasive monitoring, enabling clinicians and healthcare professionals to determine if patients are maintaining a healthy lifestyle [110]…”
MethodQi, J., Yang, P., Waraich, A., Deng, Z., Zhao, Y., & Yang, Y. (2018) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2018.09.002 · Cited by 199
Activity-Aware Fall Detection and Recognition Based on Wearable Sensors
Hussain, F., Hussain, F., Ehatisham-ul-Haq, M., & Azam, M. A. (2019) · IEEE Sensors Journal · doi:10.1109/jsen.2019.2898891 · Cited by 184
“extracting FS-1 from the sensors data as it consists of four simple statistical features, which have very low computational cost [41].”
MethodZdravevski, E., Lameski, P., Trajkovik, V., Kulakov, A., Chorbev, I., Goleva, R., Pombo, N., & Garcia, N. (2017) · IEEE Access · doi:10.1109/access.2017.2684913 · Cited by 170
“Again, this is just a rule of thumb based on approaches like [14] and [19]–[21].”
BackgroundMethodInfluentialRobust Human Activity Recognition Using Multimodal Feature-Level Fusion
Ehatisham-Ul-Haq, M., Javed, A., Azam, M. A., Malik, H. M. A., Irtaza, A., Lee, I. H., & Mahmood, M. T. (2019) · IEEE Access · doi:10.1109/access.2019.2913393 · Cited by 180
“, K-Nearest Neighbors (K-NN) and Support VectorMachine (SVM), are used for this purpose because of their efficient recognition performance in existing state-of-the-art studies [8], [70]–[72].”
BackgroundHuman Physical Activity Recognition Using Smartphone Sensors
Voicu, R.-A., Dobre, C., Bajenaru, L., & Ciobanu, R.-I. (2019) · Sensors · doi:10.3390/s19030458 · Cited by 172
“Moreover, the testing data collection is also divided in half: one part for the data we gathered ourselves using an application specifically created for this purpose (the “internal dataset”) and the other one for an external dataset [26].”
MethodTrifan, A., Oliveira, M., & Oliveira, J. L. (2019) · JMIR mHealth and uHealth · doi:10.2196/12649 · Cited by 159
HARTH: A Human Activity Recognition Dataset for Machine Learning
Logacjov, A., Bach, K., Kongsvold, A., Bårdstu, H. B., & Mork, P. J. (2021) · Sensors · doi:10.3390/s21237853 · Cited by 184
GCHAR: An efficient Group-based Context—aware human activity recognition on smartphone
Cao, L., Wang, Y., Zhang, B., Jin, Q., & Vasilakos, A. V. (2018) · Journal of Parallel and Distributed Computing · doi:10.1016/j.jpdc.2017.05.007 · Cited by 154
Behavioral biometrics & continuous user authentication on mobile devices: A survey
Stylios, I., Kokolakis, S., Thanou, O., & Chatzis, S. (2020) · Information Fusion · doi:10.1016/j.inffus.2020.08.021 · Cited by 182
Xu, H., Zhou, P., Tan, R., Li, M., & Shen, G. (2021) · Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems · doi:10.1145/3485730.3485937 · Cited by 150
A collaborative healthcare framework for shared healthcare plan with ambient intelligence
Javed, A. R., Sarwar, M. U., Beg, M. O., Asim, M., Baker, T., & Tawfik, H. (2020) · Human-centric Computing and Information Sciences · doi:10.1186/s13673-020-00245-7 · Cited by 142
Ehatisham-ul-Haq, M., Awais Azam, M., Naeem, U., Amin, Y., & Loo, J. (2018) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2018.02.020 · Cited by 138
Time Series Compression Survey
Chiarot, G., & Silvestri, C. (2022) · ACM Computing Surveys · doi:10.1145/3560814 · Cited by 133
“— ACSF1(2)—Power consumptions; — BAFU(3),—Hydrogeological data; — GSATM(4)— Dynamic mixtures of carbon monoxide (CO) and humid synthetic air in a gas chamber; — PigAirwayPressure(5)—vital signs; — SonyAIBORobotSurface2(5)—X-axis of robot movements; — SMN [37]—Seismic measures in Nevada; — HAS [38]—Human activity from…”
BackgroundSelf-Adaptive Data Collection and Fusion for Health Monitoring Based on Body Sensor Networks
Habib, C., Makhoul, A., Darazi, R., & Salim, C. (2016) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2016.2575800 · Cited by 138
“Wireless body sensor networks (WBSNs) are a subset of wireless sensor networks (WSNs) that allow continuous monitoring of health data for a given patient.”
BackgroundTedesco, S., Barton, J., & O’Flynn, B. (2017) · Sensors · doi:10.3390/s17061277 · Cited by 126
Boosting Inertial-Based Human Activity Recognition With Transformers
Shavit, Y., & Klein, I. (2021) · IEEE Access · doi:10.1109/access.2021.3070646 · Cited by 139
“To that end, [43] have collected recordings with a sampling rate of 50Hz of ten participates during seven physical activities: Walking, Running, Sitting, Standing, Jogging, Biking, Upstairs (walking upstairs) and Downstairs (walking downstairs).”
BackgroundMethodInfluentialMulti-view stacking for activity recognition with sound and accelerometer data
Garcia-Ceja, E., Galvan-Tejada, C. E., & Brena, R. (2017) · Information Fusion · doi:10.1016/j.inffus.2017.06.004 · Cited by 135
“[5] explored the use of smarthones’ accelerometers and gyroscopes tested individually and in ombination for activity recognition.”
BackgroundTowards detection of bad habits by fusing smartphone and smartwatch sensors
Shoaib, M., Bosch, S., Scholten, H., Havinga, P. J. M., & Incel, O. D. (2015) · 2015 IEEE International Conference on Pervasive Computing and Communication Workshops (PerCom Workshops) · doi:10.1109/percomw.2015.7134104 · Cited by 114
Self-citationMulti-Sensor Fusion for Activity Recognition—A Survey
Aguileta, A. A., Brena, R., Mayora, O., Minero, E. M., & Trejo, L. A. (2019) · Sensors · doi:10.3390/s19173808 · Cited by 133
“In the category of fusion at the level of features, we present the method of Feature Aggregation (FA), which consists of concatenating the characteristics extracted from all the sensors (vector of features) and training a unique classification model with this vector [22,23,108–115].”
MethodJaved, A. R., Sarwar, M. U., Khan, S., Iwendi, C., Mittal, M., & Kumar, N. (2020) · Sensors · doi:10.3390/s20082216 · Cited by 109
Servati, A., Zou, L., Wang, Z., Ko, F., & Servati, P. (2017) · Sensors · doi:10.3390/s17071622 · Cited by 106
“Many real-world applications involve multiple sensors whose data need to be jointly analyzed [88,89].”
BackgroundAuthentication of Smartphone Users Based on Activity Recognition and Mobile Sensing
Ehatisham-ul-Haq, M., Azam, M. A., Loo, J., Shuang, K., Islam, S., Naeem, U., & Amin, Y. (2017) · Sensors · doi:10.3390/s17092043 · Cited by 123
“The research work in [20,21,58,59] showed that a time interval of 4–5 s is sufficient for the recognition of a physical activity, considering a sampling rate of 50 Hz.”
BackgroundMethodInfluentialAnagnostis, A., Benos, L. T., Tsaopoulos, D. E., Tagarakis, A. C., Tsolakis, N., & Bochtis, D. (2021) · Applied Sciences · doi:10.3390/app11052188 · Cited by 115
“In general, multi-sensor data fusion has been proved to be more reliable than using a single sensor, as possible information losses or the imprecision of one sensor can be compensated by the other sensors [24].”
BackgroundMethodResultInfluentialMobile activity recognition and fall detection system for elderly people using Ameva algorithm
Álvarez de la Concepción, M. Á., Soria Morillo, L. M., Álvarez García, J. A., & González-Abril, L. (2017) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2016.05.002 · Cited by 103
“Shoaib [46] used five positions using a fourmotion sensors smartphone collecting data in some statistics in order to detect sevenphysical activities through a timewindowapproach.”
BackgroundMethodJaved, A. R., Faheem, R., Asim, M., Baker, T., & Beg, M. O. (2021) · Sustainable Cities and Society · doi:10.1016/j.scs.2021.102970 · Cited by 111
Concept drift detection and adaptation for federated and continual learning
Casado, F. E., Lema, D., Criado, M. F., Iglesias, R., Regueiro, C. V., & Barro, S. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11219-x · Cited by 138
“[30], which includes data of seven physical activities: walking, going upstairs, going downstairs, sitting, standing, jogging, and biking.”
BackgroundBoosting the Battery Life of Wearables for Health Monitoring Through the Compression of Biosignals
Hooshmand, M., Zordan, D., Del Testa, D., Grisan, E., & Rossi, M. (2017) · IEEE Internet of Things Journal · doi:10.1109/jiot.2017.2689164 · Cited by 99
“, can be inferred [5].”
LARa: Creating a Dataset for Human Activity Recognition in Logistics Using Semantic Attributes
Niemann, F., Reining, C., Rueda, F. M., Nair, N. R., Steffens, J. A., Fink, G. A., & ten Hompel, M. (2020) · Sensors · doi:10.3390/s20154083 · Cited by 120
“2014 Sensors activity dataset [47] [120] x 2800 308 csv 10 8 x 50 x x x x x 2014 User Identification From Walking Activity Data Set [121] [117] x x 431 4.”
MethodTrends in human activity recognition using smartphones
Ferrari, A., Micucci, D., Mobilio, M., & Napoletano, P. (2021) · Journal of Reliable Intelligent Environments · doi:10.1007/s40860-021-00147-0 · Cited by 110
“Shoaib et al. show that 2 s is enough for recognizing basic physical activities [35].”
BackgroundInfluentialYin, Y., Xie, L., Jiang, Z., Xiao, F., Cao, J., & Lu, S. (2024) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2024.3357591 · Cited by 108
UniMiB SHAR: A Dataset for Human Activity Recognition Using Acceleration Data from Smartphones
Micucci, D., Mobilio, M., & Napoletano, P. (2017) · doi:10.20944/preprints201706.0033.v1 · Cited by 596
“For the experiments presented in this paper, we resampled the signal in order to have a constant sampling rate of 50 Hz, which is commonly used in literature for activity recognition from data acquired through smartphones [24, 23, 25].”
MethodSurvey on Human Activity Recognition based on Acceleration Data
Slim, S. O., Atia, A., Marwa, M. A., & Mostafa, M.-S. M. (2019) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2019.0100311 · Cited by 97
“Some researches on human activities, which works on offline recognition, are using machine learning tools such as WEKA [18-20].”
BackgroundMethodSmartphone-Based Activity Recognition for Indoor Localization Using a Convolutional Neural Network
Zhou, B., Yang, J., & Li, Q. (2019) · Sensors · doi:10.3390/s19030621 · Cited by 99
“Shoaib et al. proposed an activity recognition method by fusing smartphone motion sensors [27].”
MethodRizvi, S., Scanlon, M., McGibney, J., & Sheppard, J. (2022) · IEEE Access · doi:10.1109/access.2022.3214506 · Cited by 98
Recognition of Daily Gestures with Wearable Inertial Rings and Bracelets
Moschetti, A., Fiorini, L., Esposito, D., Dario, P., & Cavallo, F. (2016) · Sensors · doi:10.3390/s16081341 · Cited by 91
“[17,22–24,31–33].”
A sensor-centric survey on the development of smartphone measurement and sensing systems
Grossi, M. (2018) · Measurement · doi:10.1016/j.measurement.2018.12.014 · Cited by 90
“used accelerometer, gyroscope, magnetometer and linear accelerometer to discriminate seven physical activities (walking, running, sitting, standing, jogging, biking, walking upstairs, walking downstairs) [111].”
MethodA Survey on Anomalous Behavior Detection for Elderly Care Using Dense-Sensing Networks
Deep, S., Zheng, X., Karmakar, C. K., Yu, D., Hamey, L., & Jin, J. (2019) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2019.2948204 · Cited by 88
“Sensor fusion has many benefits such as better accuracy, wide range interoperability, portability, and cost effectiveness and integration ability [40].”
Backgroundw-HAR: An Activity Recognition Dataset and Framework Using Low-Power Wearable Devices
Bhat, G., Tran, N., Shill, H. A., & Ogras, U. Y. (2020) · Sensors · doi:10.3390/s20185356 · Cited by 91
“[40] 2 4, 8 7 95 UniMiB SHAR [15] 1 12 9 90”
Performance evaluation of implicit smartphones authentication via sensor-behavior analysis
Shen, C. Q., Chen, Y., & Guan, X. (2017) · Information Sciences · doi:10.1016/j.ins.2017.11.058 · Cited by 86
Improving the Precision and Speed of Euler Angles Computation from Low-Cost Rotation Sensor Data
Janota, A., Šimák, V., Nemec, D., & Hrbček, J. (2015) · Sensors · doi:10.3390/s150307016 · Cited by 79
“…inertial sensors may be found in variety of applications from traditional ones (navigation and positioning of various transport means and/or robots) to sensing of human body walking and movement [2–5], daily life surveillance [6] or new commercial applications available through smart phones [7].”
BackgroundLong-Term Activity Recognition from Wristwatch Accelerometer Data
Garcia-Ceja, E., Brena, R., Carrasco-Jiménez, J. C., & Garrido, L. (2014) · Sensors · doi:10.3390/s141222500 · Cited by 87
“To perform simple activity recognition, usually, the accelerometer data is divided into fixed time windows, generally 2–10 s [19,23,25].”
MethodHabib, C., Makhoul, A., Darazi, R., & Couturier, R. (2018) · Information Fusion · doi:10.1016/j.inffus.2018.06.008 · Cited by 81
Baldominos, A., Cervantes, A., Sáez, Y., & Isasi, P. (2019) · Sensors · doi:10.3390/s19030521 · Cited by 86
“We have selected the mean and standard deviation of the non-transformed values because they have been proved useful for activity recognition [35,36].”
MethodDas, A., Acar, G., Borisov, N., & Pradeep, A. (2018) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/3243734.3243860 · Cited by 74
“…and reconstructing audio signals using gyroscopes [53]; inferring whether you are walking, driving, or taking the subway using motion sensors [73, 79]; tracking the metro ride or inferring the route that was driven using motion data [39, 40]; sniffing users’ browsing history and stealing…”
Trends in human activity recognition with focus on machine learning and power requirements
Nguyen, B., Coelho, Y., Bastos-Filho, T., & Krishnan, S. (2021) · Machine Learning with Applications · doi:10.1016/j.mlwa.2021.100072 · Cited by 93
A study of deep neural networks for human activity recognition
Sansano, E., Montoliu, R., & Belmonte Fernández, Ó. (2020) · Computational Intelligence · doi:10.1111/coin.12318 · Cited by 73
“29,30 Other elements such as magnetometers, light sensors, radio frequency identification (RFID), barometers, temperature sensors, or WiFi readings, are also used in some articles.”
Rani, G. J., Hashmi, M. F., & Gupta, A. D. (2023) · IEEE Access · doi:10.1109/access.2023.3316509 · Cited by 84
Analysis of Movement, Orientation and Rotation-Based Sensing for Phone Placement Recognition
İncel, Ö. D. (2015) · Sensors · doi:10.3390/s151025474 · Cited by 78
“As mentioned, all of the datasets include raw acceleration readings, whereas the first [11] and second datasets [12] include linear acceleration and gravity information, whereas the second set includes also gyroscope and magnetic field sensor information.”
BackgroundMethodInfluentialHong, Z., Li, Z., Zhong, S., Lyu, W., Wang, H., Ding, Y., He, T., & Zhang, D. (2024) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3659597 · Cited by 67
“We utilize UCI [56], Shoaib [63], Motion [46], and HHAR [65], to evaluate different methods, as they are widely used in previous HAR studies [7, 50, 58, 82, 83, 85].”
MethodMulti-sensor fusion based on multiple classifier systems for human activity identification
Nweke, H. F., Wah, T. Y., Mujtaba, G., Alo, U. R., & Al-Garadi, M. A. (2019) · Human-centric Computing and Information Sciences · doi:10.1186/s13673-019-0194-5 · Cited by 76
Lasagna: towards deep hierarchical understanding and searching over mobile sensing data
Liu, C., Zhang, L., Liu, Z., Liu, K., Li, X., & Liu, Y. (2016) · Proceedings of the 22nd Annual International Conference on Mobile Computing and Networking · doi:10.1145/2973750.2973752 · Cited by 63
“To comprehensively evaluate our system, we collect our own dataset and also adopt a public dataset [33] for evaluation and comparison.”
BackgroundMethodInfluentialActivity Recognition Invariant to Sensor Orientation with Wearable Motion Sensors
Yurtman, A., & Barshan, B. (2017) · Sensors · doi:10.3390/s17081838 · Cited by 77
A Deep Learning Model for Transportation Mode Detection Based on Smartphone Sensing Data
Liang, X., Zhang, Y., Wang, G., & Xu, S. (2019) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2019.2951165 · Cited by 68
“A fusion system of motion sensors is proposed to recognize physical activities in [38].”
Background(2018) · International Journal of Machine Learning and Computing · doi:10.18178/ijmlc.2018.8.6.748 · Cited by 57
A Survey of Deep Learning Based Models for Human Activity Recognition
Khan, N. S., & Ghani, M. S. (2021) · Wireless Personal Communications · doi:10.1007/s11277-021-08525-w · Cited by 69
“Table 3 Acronyms used for position of sensors Body Position Acronym References Head HE [44] Chest, Torso, Sternum, Breastbone CH [38, 39, 44, 46, 51, 54, 55] Upper Arm UA [44, 52, 59] Lower Arm LA [52] Hand HA [31, 33, 38, 39] Wrist WR [5, 30, 40–43, 46, 51, 59] Waist WA [6, 30, 34, 43, 44, 48, 49, 57] [53] Belt BE [5…”
BackgroundMethodA perspective on human activity recognition from inertial motion data
Gomaa, W., & Khamis, M. A. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-08863-9 · Cited by 54
A hierarchical lazy smoking detection algorithm using smartwatch sensors
Shoaib, M. A., Scholten, H., Havinga, P., & İncel, Ö. D. (2016) · IEEE International Conference on e-Health Networking, Applications and Services (Healthcom) · doi:10.1109/healthcom.2016.7749439 · Cited by 62
“For this purpose, we applied the same approach on one of our previous data-sets [19] and observed important improvements for all seven activities.”
MethodSelf-citationEstimating Energy Expenditure with ActiGraph GT9X Inertial Measurement Unit
Hibbing, P. R., LaMunion, S. R., Kaplan, A. S., & Crouter, S. E. (2017) · Medicine & Science in Sports & Exercise · doi:10.1249/mss.0000000000001532 · Cited by 68
“Previous research has suggested that magnetometers may be of little value for classifying activities (10,11), and the results of the present study suggest a similar lack of usefulness for predicting EE using regression-based approaches.”
ResultAwais, M., Raza, M., Ali, K., Ali, Z., Irfan, M., Chughtai, O., Khan, I., Kim, S., & Rehman, M. U. (2019) · Sensors · doi:10.3390/s19112498 · Cited by 66
“…of 50 Hz is used for data anlysis as this is The sampling frequency of 50 Hz is used for data anlysis as this is the commonly used sampling rate for the studies related to human activity recognition [29]. commonly used sampling rate for the studies related to human activity recognition [29].”
MethodZhang, L., Yu, J., Gao, Z., & Ni, Q. (2024) · Alexandria Engineering Journal · doi:10.1016/j.aej.2024.01.030 · Cited by 61
Recognizing Human Activities from Raw Accelerometer Data Using Deep Neural Networks
Zhang, L., Wu, X., & Luo, D. (2015) · 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA) · doi:10.1109/icmla.2015.48 · Cited by 59
“These classifiers were more often used and could be found in [1, 2, 3, 8, 9, 15-17].”
MethodCybersecurity Deep: Approaches, Attacks Dataset, and Comparative Study
Barik, K., Misra, S., Konar, K., Sanz, L. F., & Koyuncu, M. (2022) · Applied Artificial Intelligence · doi:10.1080/08839514.2022.2055399 · Cited by 72
“2014) 473 TWENTE dataset 2014 (Shoaib et al. 2014) 406 ICS cyber-attack dataset 2015 (Pan, Morris, and Adhikari 2015 281 CAIDAs dataset 2017 (Jonker et al.”
Kaler, J., Mitsch, J., Vázquez-Diosdado, J. A., Bollard, N. J., Dottorini, T., & Ellis, K. A. (2020) · Royal Society Open Science · doi:10.1098/rsos.190824 · Cited by 64
“This has also been reported in human activity recognition where gyroscope-based features have increased the accuracy of the algorithms for certain complex behaviours [26].”
BackgroundSecurity and Privacy in the Emerging Cyber-Physical World: A Survey
Yu, Z., Kaplan, Z., Yan, Q., & Zhang, N. (2021) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2021.3081450 · Cited by 53
“63% Ensemble Learning I [167] Acc, Gyro, Mag X TO Android Phone User’s Physical Activities 30-98% Multiple/WEKA I [168] Acc, Gyro, Mag X TO Android Phone User Location/Route 30-50% Graph Matching R [169] Acc, Gyro, Mag X TO Custom Sensor Array User Activity/Location 86% K-Nearest Neighbor R [170] Antenna X O TV Receiv…”
BackgroundStrączkiewicz, M., Huang, E. J., & Onnela, J.-P. “. (2023) · npj Digital Medicine · doi:10.1038/s41746-022-00745-z · Cited by 67
Ye, X., Sakurai, K., Nair, N. C., & Wang, K. I. (2024) · Sensors · doi:10.3390/s24247975 · Cited by 68
“[14] Exercise Activity[20] USC-HAD[107] van Kasteren[81] Skoda[106] TUD[44] Shoaib[75] CASAS[24] SHAR[62] Widar3.”
On the Challenges and Potential of Using Barometric Sensors to Track Human Activity
Manivannan, A., Chin, W. C. B., Barrat, A., & Bouffanais, R. (2020) · Sensors · doi:10.3390/s20236786 · Cited by 63
“Since these inertial sensors are now commonly found in today’s smartphones and other MEMS devices, many recent studies use a combination of these sensors to improve classification accuracy [12,13], although a three-axis accelerometer alone can extract good-quality data, resulting in excellent classification results [1…”
BackgroundHuman activity recognition: A comprehensive review
Kaur, H., Rani, V., & Kumar, M. (2024) · Expert Systems · doi:10.1111/exsy.13680 · Cited by 67
“This dataset considers seven different physical activities: standing, sitting, running, walking, bicycling, jogging, and walking downstairs and upstairs (Shoaib et al., 2014).”
LLaSA: A Sensor-Aware LLM for Natural Language Reasoning of Human Activity from IMU Data
Imran, S. A., Khan, M. N. H., Biswas, S., & Islam, B. (2025) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3714394.3756187 · Cited by 67
“We pretrain LIMU-BERT using unlabeled data from four standard HAR datasets: HHAR [36], UCI-HAR [30], MotionSense [26], and Shoaib [34], covering eight activities with 3-axis accelerometer and gyroscope signals.”
Practically Adopting Human Activity Recognition
Xu, H., Zhou, P., Tan, R., & Li, M. (2023) · Proceedings of the 29th Annual International Conference on Mobile Computing and Networking · doi:10.1145/3570361.3613299 · Cited by 55
“■ Shoaib [44] et al. collected data of seven daily activities ( sitting, standing, walking, walking upstairs, walking down-stairs, jogging, and biking ) in the Netherlands. right pocket, left pocket, belt, upper arm, and wrist ). diverse datasets, we select four common activities (i.e., still,…”
BackgroundHow Validation Methodology Influences Human Activity Recognition Mobile Systems
Bragança, H. L. D. S., Colonna, J. G., Oliveira, H. A. B. F., & Souto, E. (2022) · Sensors · doi:10.3390/s22062360 · Cited by 65
“The HAR community have used different sizes of segments in the literature with the use of segment sizes ranging from 1 s to 10 s, with a recognition rate above 90% [7,25,34,35].”
BackgroundMethodMuralidharan, K., Ramesh, A., Rithvik, G., Prem, S., Reghunaath, A. A., & Gopinath, M. P. (2021) · International Journal of Cognitive Computing in Engineering · doi:10.1016/j.ijcce.2021.09.001 · Cited by 69
An overview of human activity recognition based on smartphone
Yuan, G., Wang, Z., Meng, F., Yan, Q., & Xia, S. (2018) · Sensor Review · doi:10.1108/sr-11-2017-0245 · Cited by 60
Whitwell, J. L., Jack, Jr., Senjem, M. L., Parisi, J. E., Boeve, B. F., Knopman, D. S., Dickson, D. W., Petersen, R. C., & Josephs, K. A. (2009) · Neurodegenerative Diseases · doi:10.1159/000209507 · Cited by 53
DCNN based human activity recognition framework with depth vision guiding
Qi, W., Wang, N., Su, H., & Aliverti, A. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.11.044 · Cited by 52
Mario, M.-O. (2019) · IEEE Sensors Journal · doi:10.1109/jsen.2018.2882943 · Cited by 50
“as compared with other datasets previously used in literature such as [18]–[19] and [21]–[23].”
MethodResultA Data Science Framework for Movement
Dodge, S. (2019) · Geographical Analysis · doi:10.1111/gean.12212 · Cited by 53
“…observations to support the study and modeling of complex dynamic systems such as human dynamics (González et al., 2008; Candia et al., 2008; Shoaib et al., 2014; Thums et al., 2018), social networks (Azmandian et al., 2013; Wu et al., 2014; Jurdak et al., 2015), animal behaviors and…”
BackgroundConsumer Wearables and Affective Computing for Wellbeing Support
Saganowski, S., Kazienko, P., Dzieżyc, M., Jakimow, P., Komoszyńska, J., Michalska, W., Dutkowiak, A., Polak, A., Dziadek, A., & Ujma, M. (2020) · EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services (MobiQuitous) · doi:10.1145/3448891.3450332 · Cited by 53
Research Trends on Mobile Mental Health Application for General Population: A Scoping Review
Hwang, W. J., Ha, J. S., & Kim, M. J. (2021) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph18052459 · Cited by 56
“Additional efforts are required to identify the best ways a mobile app can be used to address components [46] such as the development and application of methods to evaluate interactive mechanisms from physical measurements [47,48].”
Background
Metadata
- Authors
- Shoaib, M., Bosch, S., Incel, O., Scholten, H., & Havinga, P.
- Affiliations
- University of Twente (NL)
- Department of Computer Engineering, Galatasaray University, Ortakoy, Istanbul 34349, Turkey
- Corresponding author
- Shoaib, Muhammad
- Venue
- Sensors
- Publisher
- MDPI AG
- Published
- 2014-06-10
- Volume
- 14
- Issue
- 6
- Pages
- 10146-10176
- ISSN
- 1424-8220 (ISSN-L)
- PMC
- PMC4118351
- OpenAlex
- W2129793335
- Cited by
- 552
- References
- 45
- Citations by year
- 2026: 25 · 2025: 34 · 2024: 57 · 2023: 53 · 2022: 53 · 2021: 66 · 2020: 54 · 2019: 58 · 2018: 50 · 2017: 44 · 2016: 34 · 2015: 21 · 2014: 2
- FWCI
- 29.97
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Sensors (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- University of Twente Research Information (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- University of Twente Research Information (submittedVersion, other-oa)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Health Sciences › Medicine › Public Health, Environmental and Occupational Health › Physical Activity and Health
- Social Sciences › Transportation › Human Mobility and Location-Based Analysis
- Keywords
- physical activity recognition, smartphone motion sensors, accelerometer, gyroscope, magnetometer, sensor fusion, sensor combination, posture, personalized classification
- MeSH terms
- Activities of Daily Living, Adult, Algorithms, Humans, Male, Monitoring, Physiologic, Movement, Pattern Recognition, Automated, Models, Statistical, Walking, Cell Phone, Accelerometry
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.
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 sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.