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
Items 301–400 of 578
A classification of accelerometer data to differentiate pedestrian state
Prasertsung, P., & Horanont, T. (2016) · International Computer Science and Engineering Conference · doi:10.1109/icsec.2016.7859881 · Cited by 9
“In [9], a combination of accelerometer data”
Chakraborty, B., Nakano, K., Tokoi, Y., & Hashimoto, T. (2019) · IEEE Region 10 Conference (TENCON) · doi:10.1109/tencon.2019.8929241 · Cited by 9
“The details of the data set can be found in [26].”
Backgroundmachine and deep learning approaches for human activity recognition
Alhumayyani, M. M., Mounir, M., & Ismail, R. M. (2021) · International journal of intelligent computing and information sciences/International Journal of Intelligent Computing and Information Sciences · doi:10.21608/ijicis.2021.82008.1106 · Cited by 8
“In addition to this, Shoaib et al. [21] proposed another study based on a methodology for the identification of the HAR based on a filtering method using a simple difference filter.”
MethodActiRecognizer: Design and Implementation of a Real-Time Human Activity Recognition System
Cao, L., Wang, Y., Jin, Q., & Ma, J. (2017) · International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC) · doi:10.1109/cyberc.2017.71 · Cited by 8
SPINDLES+: An adaptive and personalized system for leg shake detection
Xia, S., Wei, P., Vega, J., & Jiang, X. (2018) · Smart Health · doi:10.1016/j.smhl.2018.07.019 · Cited by 8
Human Activity Recognition by Deep Convolution Neural Networks and Principal Component Analysis
Aljarrah, A. A., & Ali, A. H. (2021) · Intelligent systems reference library · doi:10.1007/978-3-030-57835-0_10 · Cited by 11
Improved Spatiotemporal Framework for Human Activity Recognition in Smart Environment
Salem, Z., & Weiss, A. P. (2022) · Sensors · doi:10.3390/s23010132 · Cited by 8
“Time domain features are easily extracted from the raw data, whereas frequency domain features require higher computation and storage capacities [18].”
BackgroundSiirtola, P., & Röning, J. (2018) · International Journal of Interactive Multimedia and Artificial Intelligence · doi:10.9781/ijimai.2018.12.001 · Cited by 8
Siirtola, P., Koskimäki, H., & Röning, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.12285 · Cited by 8
“However, by fusing the sensors of a mobile phone more accurate models could be build than using only one sensor [5].”
MethodOdhiambo, C. O., Wright, P. J., Corbett, C., & Valafar, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.08907 · Cited by 8
Multi-Position Human Activity Recognition using a Multi-Modal Deep Convolutional Neural Network
Muhoza, A. C., Bergeret, E., Brdys, C., & Gary, F. (2023) · International Conference on Smart and Sustainable Technologies (SpliTech) · doi:10.23919/splitech58164.2023.10193600 · Cited by 7
“SHO [20] This dataset combines data from 10 participants.”
MethodSelfVis: Self-Supervised Learning for Human Activity Recognition Based on Area Charts
Jiang, A., & Ye, J. (2024) · IEEE Transactions on Emerging Topics in Computing · doi:10.1109/tetc.2024.3392850 · Cited by 7
“SHOAIB [34] is collected on 7 physical activities including walking, sitting, standing, jogging, biking, walking upstairs, and walking downstairs.”
A Spatio-temporal Graph Transformer driven model for recognizing fine-grained data human activity
Yan, M., Zhang, G., & Ye, C. (2024) · Alexandria Engineering Journal · doi:10.1016/j.aej.2024.06.042 · Cited by 7
Mercati, P., & Bhat, G. (2024) · IEEE Design and Test · doi:10.1109/mdat.2024.3432862 · Cited by 11
“For instance, activity monitoring applications mount wearable devices on various locations on the body to collect motion data [9], [95], [96], [97], [98].”
Indoor Abnormal Behavior Detection for the Elderly: A Review
Gu, T., & Tang, M. (2025) · Sensors · doi:10.3390/s25113313 · Cited by 10
“Traditional machine learning model [48] and manual feature extraction [49] The recognition accuracy is improved compared to the threshold method.”
Ban, L., Zhu, T., Lu, X., Qiu, Q., Han, W., Li, S., Chen, L., Wang, K. I.-K., Nie, M., & Wan, Y. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133963 · Cited by 10
A Mobile App Authentication Approach by Fusing the Scores from Multi-Modal Data
Li, G., & Bours, P. (2018) · International Conference on Information Fusion (FUSION) · doi:10.23919/icif.2018.8455650 · Cited by 7
Feature Relevance Analysis to Explain Concept Drift - A Case Study in Human Activity Recognition
Siirtola, P., & Röning, J. (2022) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3544793.3560390 · Cited by 7
“This study uses open data set presented in [13] in the experiments.”
MethodThe Significance of IoT and Deep Learning in Activity Recognition
Thakur, D., & Saini, J. K. (2023) · Studies in computational intelligence · doi:10.1007/978-3-031-35783-1_18 · Cited by 8
Leveraging a Smartwatch for Activity Recognition in Salat
Eliza, I. J., Al-Nabhan, N., Noor, J., Rahaman, M., & Islam, A. B. M. A. A. (2023) · IEEE Access · doi:10.1109/access.2023.3311261 · Cited by 9
Assessment System for Child Head Injury from Falls Based on Neural Network Learning
Yang, Z., Tsui, B., & Wu, Z. (2023) · Sensors · doi:10.3390/s23187896 · Cited by 7
Big Data Analytics in Mobile and Cloud Computing Environments
Rehman, M. H. U., Khan, A. U. R., & Batool, A. (2016) · Advances in systems analysis, software engineering, and high performance computing book series · doi:10.4018/978-1-5225-0287-6.ch014 · Cited by 9
A mobile application to improve the quality of life via exercise
Costa, J., Fazendeiro, P., & Ferreira, F. (2016) · IEEE International Conference on Intelligent Computer Communication and Processing (ICCP) · doi:10.1109/iccp.2016.7737122 · Cited by 7
“Recent studies also suggest that certain behaviours in children, like a low level of moderate to vigorous physical activity, short sleep duration and high level of sedentary activities like watching TV are some of the most important factors for child obesity [3] and prevalence of major diseases [4].”
BackgroundRecognizing Human-Object Interaction (HOI) Using Wrist-Mounted Inertial Sensors
Tahir, S., Raheel, A., Ehatisham-ul-haq, M., & Arsalan, A. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2020.3044315 · Cited by 5
“In literature, many researchers have worked on developing different solutions for HAR and various schemes have bee presented in this regard using wide-ranging sensors [24], [29], [30].”
BackgroundSmart Device Monitoring System Based on Multi-type Inertial Sensor Machine Learning
Zeng, Y., Chen, W., Chen, C., Xiong, W., Liu, Z., Huang, Y., & Shen, C. (2021) · Sensors and Materials · doi:10.18494/sam.2021.3037 · Cited by 7
Pellatt, L., & Roggen, D. (2021) · International Symposium on Wearable Computers · doi:10.1145/3460421.3478813 · Cited by 7
“Ref Modalities Dataset Components NL NP [8] IMU SBHAR [43], UniMiB [32], REALDISP [5] CNN, Pool, Bi-LSTM 5 — [12] IMU PAMAP2 [42], Skoda [53], Opportunity [7] MLP 5 49K [45] IMU, Altitude HHAR [47], UniMiB, UCI HAR [2], MobiAct [48], WISDM [50], MSense [30] CNN, Pool, MLP 5 — [38] IMU Ubicomp 08 [21], Opportunity CNN,…”
Permatasari, J., Connie, T., & Ong, T. S. (2019) · Lecture notes in electrical engineering · doi:10.1007/978-981-15-0058-9_19 · Cited by 7
Flooding Level Classification by Gait Analysis of Smartphone Sensor Data
Panchal, U. K., Ajmani, H., & Sait, S. Y. (2019) · IEEE Access · doi:10.1109/access.2019.2959557 · Cited by 9
“Further, it has been noted that accelerometer and gyroscope signals provide the most information about human movement [3].”
BackgroundCasado, F. E., Lema, D., Iglesias, R., Regueiro, C. V., & Barro, S. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-62579-5_6 · Cited by 8
Indumathi, V. M., & Prabakeran, S. (2021) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-981-16-0965-7_70 · Cited by 8
Sensor-based human activity recognition: Overcoming issues in a real world setting
Sztyler, T. (2019) · MADOC (University of Mannheim) · Cited by 15
Entropy Decision Fusion for Smartphone Sensor based Human Activity RecognitionPreprint
Arigbabu, O. A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.00367 · Cited by 10
“Such assessment has been conducted to understand the influence of positioning of on-body sensors at different body parts on HAR performance [31].”
EMI: Energy Management Meets Imputation in Wearable IoT Devices
Hussein, D., Yamin, N., & Bhat, G. (2024) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2024.3448379 · Cited by 6
“We validate EMI with six diverse health monitoring datasets [2], [10], [11], [12], [13], [14].”
BackgroundMethodInfluentialCHAR: Composite Head-Body Activities Recognition With a Single Earable Device
Zhu, P., Zhu, Y., Li, W., He, Y., Zou, Y., Wu, K., & Leung, V. C. M. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3548647 · Cited by 8
“We refer to some HAR benchmark datasets of body movements recognition such as HHAR [24], UCI [25], MotionSense [26] and Shoaib [11], which have been commonly used in many works.”
InfluentialDifferentiable Prior-Driven Data Augmentation for Sensor-Based Human Activity Recognition
Zhang, Y., Gao, Q. H., Hu, R., Ding, Q., Li, B., & Guo, Y. (2025) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2025.3565414 · Cited by 6
“1) Descriptions of Benchmark Datasets and Baseline Models: Five benchmark HAR datasets, including HAPT [40], HHAR [41], Opportunity [42], DSADS [43], and SHO [44], are used to demonstrate the effectiveness of DriveData.”
CHAR: Composite Head-body Activities Recognition with A Single Earable Device
Zhu, P., Zou, Y., Li, W., & Wu, K. (2023) · IEEE International Conference on Pervasive Computing and Communications · doi:10.1109/percom56429.2023.10099218 · Cited by 6
“These works have considered a wide range of daily activities including walking [11], sleeping [12], eating [13], and etc. .”
BackgroundMethodInfluentialDOMINO: A Dataset for Context-Aware Human Activity Recognition using Mobile Devices
Arrotta, L., Civitarese, G., Presotto, R., & Bettini, C. (2023) · IEEE International Conference on Mobile Data Management (MDM) · doi:10.1109/mdm58254.2023.00063 · Cited by 11
“Some datasets simulated the smartwatch by requiring subjects to wear a smartphone on the wrist, like in NTUT-HAR [16] and other datasets [17]–[19].”
BackgroundMethodSmartphone-based activity tracking for spine patients: Current technology and future opportunities
Leibold, A. T., Ali, D. M., Harrop, J. S., Sharan, A. D., Vaccaro, A. R., & Sivaganesan, A. (2023) · World Neurosurgery X · doi:10.1016/j.wnsx.2023.100238 · Cited by 6
Identifying Smartphone Users Based on Activities in Daily Living Using Deep Neural Networks
Mekruksavanich, S., & Jitpattanakul, A. (2024) · Information · doi:10.3390/info15010047 · Cited by 6
“To examine user identification, this study utilized smartphone sensor data from a dataset called the “pervasive dataset” [18].”
MethodEarDA: Towards Accurate and Data-Efficient Earable Activity Sensing
Lyu, S., Chen, Y., Duan, D., Jia, R., & Xu, W. (2024) · doi:10.1109/cscaiot62585.2024.00005 · Cited by 15
“…six different activities (walking, walking upstairs, walking downstairs, standing, lying down and sitting) at 50 Hz. d) Shoaib: The Shoaib dataset [19] consists of the motion data of seven daily activities (walking, walking upstairs, walking downstairs, standing, jogging, biking and sitting) .”
BackgroundSensor-Aware Data Imputation for Time-Series Machine Learning on Low-Power Wearable Devices
Hussein, D., Belkhouja, T., Bhat, G., & Doppa, J. (2024) · ACM Transactions on Design Automation of Electronic Systems · doi:10.1145/3698195 · Cited by 9
“Use of multiple sensors in wearable devices has enhanced their capabilities for health monitoring [7, 8, 47, 53].”
Defining a Roadmap Towards Comparative Research in Online Activity Recognition on Mobile Phones
Shoaib, M. A., Bosch, S., İncel, Ö. D., Scholten, H., & Havinga, P. (2015) · International Conference on Pervasive and Embedded Computing and Communication Systems · doi:10.5220/0005324401540159 · Cited by 6
“Most of this research has been done in an offline way (Incel et al., 2013; Shoaib et al., 2014).”
BackgroundSelf-citationOn-Chip Activity Recognition in a Smart Home
Sprute, D., & König, M. (2016) · International Conference on Intelligent Environments (IE) · doi:10.1109/ie.2016.23 · Cited by 6
“[16] investigated on the role of several sensors in activity recognition, and they found out that an accelerometer is capable to take the lead role in activity recognition.”
BackgroundFrom the Outside In: Integrating External Exposures into the Exposome Concept
Cui, Y., & Balshaw, D. M. (2018) · Springer eBooks · doi:10.1007/978-3-319-89321-1_10 · Cited by 6
Smoking recognition with smartwatch sensors in different postures and impact of user’s height
Agac, S., Shoaib, M. A., & İncel, Ö. D. (2020) · Journal of Ambient Intelligence and Smart Environments · doi:10.3233/ais-200558 · Cited by 6
“Particularly, we used Support Vector Machine (SVM), Random Forest (RF) and Multilayer Perceptron(MLP) which are commonly used for activity recognition [21,24,29].”
Self-citationActivity recognition from smartphone data using weighted learning methods
Abidine, M. B., & Fergani, B. (2021) · Intelligenza Artificiale · doi:10.3233/ia-200059 · Cited by 6
“ForWKNNmethod, wehaveusedanorder q of similarity distance in a range of [1, 1.5, 2] and the k parameter in the range [1, 3, 5, 7, 9, 11].”
InfluentialQuantization for Communication-Efficient Change-Point Detection Over Networks
Jiao, Y., Xu, X., & Gu, Y. (2021) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2021.3134885 · Cited by 6
RSSI and Device Pose Fusion for Fingerprinting-Based Indoor Smartphone Localization Systems
Khan, I. M., Thompson, A., Al‐Hourani, A., Kandeepan, S., & Rowe, W. S. T. (2023) · Future Internet · doi:10.3390/fi15060220 · Cited by 8
“[19,20], the authors compared the use of different sensors individually and together for device-pose-only identification, and both studies concluded that using multiple sensors (together with, or aside from, the accelerometer) does not significantly increase accuracy compared with using the accelerometer alone.”
BackgroundChang, K.-M., Chun, Y.-T., Chen, S.-H., Lu, L., Su, H.-T., Liang, H.-M., Santhosh, J., Ching, C. T., & Liu, S.-H. (2016) · Sensors · doi:10.3390/s16071126 · Cited by 6
“cell phones was used to detect physical activities [42–44].”
Fine-grained Accelerometer-based Smartphone Carrying States Recognition during Walking
Fujinami, K., Saeki, T., Li, Y., Tsuyoshi, I., Jimbo, T., Nagase, D., & Sato, K. (2017) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2017.080858 · Cited by 9
“Various sensors are embedded into the device, which allows the a system to extract a user’s and/or a device’s context such as engaging activity [19], [23], [26] and a person/device location [16], [24], identity of pedestrian [28], environmental conditions around a user [8], [10], [15], [27], and so on, which contribut…”
BackgroundMachine Learning Models for Activity Recognition and Authentication of Smartphone Users
Ahmadi, S. S., Rashad, S. S., & Elgazzar, H. (2019) · IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON) · doi:10.1109/uemcon47517.2019.8993055 · Cited by 6
“, sn}, RMS is obtained using equation (7) [20,28]:”
BackgroundMethodInfluentialActivity-Independent Person Identification Based on Daily Activities Using Wearable Sensors
Hussein, S., Barlow, M., & Lakshika, E. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-64984-5_30 · Cited by 6
Sabel, C. E., Amegbor, P. M., Zhang, Z., Chen, T. K., Poulsen, M. B., Hertel, O., Sigsgaard, T., Horsdal, H. T., Pedersen, C. B., & Khan, J. (2021) · The urban book series · doi:10.1007/978-981-15-8983-6_17 · Cited by 7
“The cell phone has been applied in public-health studies and can be combined with gyroscope (Shoaib et al. 2014) and barometer (Muralidharan et al. 2014) to identify physical activity and sleep quality.”
BackgroundEasySpiro: Assessing Lung Function via Arbitrary Exhalations on Commodity Earphones
Xu, C., Xie, W., Yang, B., Zhang, Y., Gong, Y., Zhang, J., Li, W., Yang, S., & Zhang, Q. (2025) · ACM Annual International Conference on Mobile Computing and Networking (MobiCom) · doi:10.1145/3680207.3723489 · Cited by 7
“We pretrain this model on large IMU datasets [32, 44, 50, 53] using random masking as recommended in [69].”
Hi-OSCAR: Hierarchical Open-set Classifier for Human Activity Recognition
McCarthy, C., Quirijnen, L., van Zandwijk, J. P., Geradts, Z., & Worring, M. (2025) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3770681 · Cited by 6
“Early research in HAR relied on handcrafted feature extraction usually based upon either the time domain [7, 14, 43], the frequency domain [2, 10, 87], or both [6, 64, 65].”
Wonderwall: A Virtual-to-Real Foundation Model for IMU-based HAR
Miao, S., & Chen, L. (2026) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3789688 · Cited by 9
“For downstream evaluation, we select ten datasets: UTD-MHAD [8], MMAct [20], Mhealth [4], UT-Complex [48], WISDM [53], Wharf [6], DSADS [2], PAMAP [42], W-HAR [5], and Shoaib [47].”
Leveraging dataset integration and continual learning for human activity recognition
Amrani, H., Micucci, D., Mobilio, M., & Napoletano, P. (2025) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-025-02569-1 · Cited by 6
“SAD [46] contains 3-axial acceleration, gyroscope, mag-netometer, and linear acceleration sensor data of 7 ADLs.”
Sensor-Based Human Activity and Behavior Computing
Antar, A. D., Ahmed, M., & Ahad, M. A. R. (2021) · Intelligent systems reference library · doi:10.1007/978-3-030-75490-7_6 · Cited by 5
Spatial Structure-Related Sensory Landmarks Recognition Based on Long Short-Term Memory Algorithm
Wang, Y., Zhang, J., Zhao, H., Liu, M., Chen, S., Kuang, J., & Niu, X. (2021) · Micromachines · doi:10.3390/mi12070781 · Cited by 5
“In addition, clustering [23], SVM [19,24], and deep learning [25] can also be used for HAR.”
MethodInvited Paper: Hierarchical Activity Recognition with Smartwatch IMU
Alevizaki, A., Pham, N., & Trigoni, N. (2023) · International Conference on Distributed Computing and Networking (ICDCN) · doi:10.1145/3571306.3571390 · Cited by 5
“Providing appropriate and concise information about the activities people perform in their everyday lives, commonly known as Activities of Daily Living (ADL), is helpful in various application domains, such as remote healthcare, localisation, smart homes and workout monitoring [7, 31].”
A Feature Set for the Similar Activity Recognition Using Smartphone
Yan, N., Chen, J., & Yu, T. (2018) · International Conference on Wireless Communications and Signal Processing (WCSP) · doi:10.1109/wcsp.2018.8555704 · Cited by 6
“To find the appropriate feature set we use the dataset in [15].”
MethodLow‐powered wearable motion detecting system using static electric fields
Lambert, S., Lu, H., Shreve, Z., Zhan, Y., Majumder, A. J. A., & Şahin, G. (2019) · IET Cyber-Physical Systems Theory & Applications · doi:10.1049/iet-cps.2018.5034 · Cited by 5
Predicting Human Motion Signals Using Modern Deep Learning Techniques and Smartphone Sensors
Kim, T., Park, J.-H., Lee, J., & Park, J. (2021) · Sensors · doi:10.3390/s21248270 · Cited by 7
“However, it has been known through previous studies that using the magnetometer should be used with caution due to problems such as direction dependence [45,46] and inefficiency in recognition performance [47,48].”
ResultTransfer Learning Model Knowledge Across Multi-Sensors Locations Over Body Sensor Network
Qian, X., Chen, H., Cai, Y. M., Chu, K., Xu, W., & Huang, M.-C. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3166187 · Cited by 6
“All signals are re-sampled to 50 Hz before training according to the literature [45] and adopted the segmentation technique around founded peak [46] into fixed windows with 200 samples and 50% overlap for human activity recognition and fall detection.”
MethodLIMU-BERT: Unleashing the Potential of Unlabeled Data for IMU Sensing Applications
Xu, H., Zhou, P., Tan, R., Li, M., & Shen, G. (2022) · GetMobile Mobile Computing and Communications · doi:10.1145/3568113.3568124 · Cited by 7
“, HAR [11], UCI [12], Motion [13], and Shoaib [14].”
MethodKuschan, J., Filaretov, H., & Krüger, J. (2022) · IEEE International Conference on Industrial Informatics (INDIN) · doi:10.1109/indin51773.2022.9976078 · Cited by 5
“The Opportunity Challenge is focused on ADL, as are most of the other popular benchmarking HAR datasets [3] like Daily Living Activities (DaLiAc)[4], mHealth[5], Five Smart Phone (FSP)[6] and Smartphone-based Human Activity Recognition (SBHAR).”
BackgroundBalfas, M., Ahamed, S. I., Tamma, C. P., Arif, M., Kattan, A. J., & Chu, W. C. (2018) · IEEE Annual International Computer Software and Applications Conference (COMPSAC) · doi:10.1109/compsac.2018.00149 · Cited by 5
“[11] [18].”
Towards Customizable Foundation Models for Human Activity Recognition with Wearable Devices
Qiu, M., Weng, C., Fan, M., & Wu, K. (2025) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3749479 · Cited by 4
“Additionally, HAR systems incorporate vision-based [32], wireless-based [16, 21, 50, 61, 66, 67], and mobile-based [17, 24, 27, 38, 40, 41, 43, 55, 57, 59] methods.”
InfluentialWearable Spine Tracker vs. Video-Based Pose Estimation for Human Activity Recognition
Walkling, J., Sander, L., Masch, A., & Deserno, T. M. (2025) · Sensors · doi:10.3390/s25123806 · Cited by 5
UniMiB AAL: An Android Sensor Data Acquisition and Labeling Suite
Ginelli, D., Micucci, D., Mobilio, M., & Napoletano, P. (2018) · Applied Sciences · doi:10.3390/app8081265 · Cited by 5
“These techniques have proven to be effective in many application domains, such as physical activity recognition and the estimation of energy expenditure [4,5], the monitoring of Parkinson’s disease development [6], and the early detection of dementia disease [7].”
Yao, M., Chen, W., Wang, Z., Cheng, M., Zhang, C., Yu, F. R., & Leung, V. C. M. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3602828 · Cited by 4
“Shoaib2014 : The Shoaib2014 dataset [24] is a widely used HAR benchmark, collected using various wearable sensors.”
Position-aware Human Activity Recognition with Smartphone Sensors based on Deep Learning Approaches
Mekruksavanich, S., & Jitpattanakul, A. (2023) · International Conference on Telecommunications and Signal Processing (TSP) · doi:10.1109/tsp59544.2023.10197773 · Cited by 4
“The Pervasive dataset [18] is widely used for recognizing human activity through smartphone sensors.”
MethodSemi-supervised Human Activity Recognition with individual difference alignment
Yang, Z., Li, T., Xu, Z., Huang, Z., Cao, Y., Li, K., & Ma, J. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.126976 · Cited by 5
Pohybová aktivita a sportovní preference adolescentek
Neuls, F., & Frömel, K. (2016) · doi:10.5507/ftk.16.24450902 · Cited by 9
Wearable sensors for gesture analysis in smart healthcare applications
Butt, A. H., Moschetti, A., Fiorini, L., Dario, P., & Cavallo, F. (2017) · Institution of Engineering and Technology eBooks · doi:10.1049/pbhe009e_ch4 · Cited by 5
Chaurasia, S. K., & Reddy, S. R. N. (2018) · EAI Endorsed Transactions on Pervasive Health and Technology · doi:10.4108/eai.30-10-2018.160460 · Cited by 4
Scheurer, S., Tedesco, S. A., Brown, K. N., & O’Flynn, B. (2019) · International Workshop on Sensor-based Activity Recognition and Interaction (iWOAR) · doi:10.1145/3361684.3361689 · Cited by 5
Filjar, R., Sklebar, I., & Horvat, M. (2020) · Communications - Scientific letters of the University of Zilina · doi:10.26552/com.c.2020.4.153-162 · Cited by 4
“The results have the potential of utilisation in Location-Based Services (LBS), urban and transport strategic planning, location intelligence, medical diagnostics and conditions’ observation, (urban) surveyed in [2].”
BackgroundImpact of Time Domain Features & Inertial Sensors on Activity Recognition using Randomized Selection
Chaurasia, S. K., & Reddy, S. R. N. (2021) · International Conference on Computing, Communication, and Intelligent Systems (ICCCIS) · doi:10.1109/icccis51004.2021.9397213 · Cited by 5
“The data are mostly collected with a sampling rate of 50 Hz [15].”
Dedeyne, L., Wullems, J. A., Dupont, J., Tournoy, J., Gielen, E., & Verschueren, S. (2021) · Journal for the Measurement of Physical Behaviour · doi:10.1123/jmpb.2020-0008 · Cited by 4
Toward Personalized Human Activity Recognition Model with Auto-Supervised Learning Framework
Mhalla, A., & Favreau, J.-M. (2021) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme51207.2021.9428296 · Cited by 4
“The SHO [13] dataset represents the source dataset which is used to train the proposed generic HAR model.”
MethodA sequence models-based real-time multi-person action recognition method with monocular vision
Yang, A., Lu, W., Naeem, W., Chen, L., & Fei, M. (2021) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-021-03399-z · Cited by 4
KATN: Key Activity Detection via Inexact Supervised Learning
You, X., Zhang, L., Yu, H., Yuan, M., & Li, X. (2021) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3494957 · Cited by 5
“Public Datasets: We adopt two public datasets: Shoaib Dataset (SHO) [37] and The University of Sussex-Huawei Locomotion (SHL) [15][45].”
MethodActivity recognition on smartphones using an AKNN based support vectors
Abidine, M. B., Oussalah, M., Fergani, B., & Lounis, H. (2022) · Sensor Review · doi:10.1108/sr-05-2021-0157 · Cited by 4
Energy-Efficient Missing Data Recovery in Wearable Devices: A Novel Search-Based Approach
Hussein, D., Belkhouja, T., Bhat, G., & Doppa, J. R. (2023) · International Symposium on Low Power Electronics and Design (ISLPED) · doi:10.1109/islped58423.2023.10244309 · Cited by 8
“[8]: The Shoaib dataset includes three-axis accelerometer data for 10 users performing seven activities.”
MethodInfluentialRISK-Sleep: Real-Time Stroke Early Detection System During Sleep Using Wristbands
Jeon, S., Park, T., Lee, Y., Son, S. H., Lee, H., & Eun, Y. (2018) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2018.00732 · Cited by 4
“The function M is appropriate for orientationindependence activity recognition [17].”
BackgroundContext Detection for Advanced Self-Aware Navigation using Smartphone SensorsPreprint
Gao, H., & Groves, P. D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.07539 · Cited by 4
“As previous research [30][31] has already proved, among the sensors in a smartphone, measurements from the inertial sensors are capable of taking the leading roles in motion recognition.”
BackgroundMethodInfluentialPushing the limits of intertial motion sensing
Bosch, S. (2022) · doi:10.3990/1.9789036554350 · Cited by 4
Self-citationOptimizing On-Body Sensor Placements for Deep Learning-Driven Human Activity Recognition
Mekruksavanich, S., & Jitpattanakul, A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-64608-9_21 · Cited by 3
MuSAC: Mutualistic Sensing and Communication for Mobile Crowdsensing
Ji, S., Lian, L., Zheng, Y., & Wu, C. (2024) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs60910.2024.00031 · Cited by 3
“To further substantiate Proposition 1, we sampled the same portion of IMU data from the publicly available Shoaib dataset [12] to replace the IMU data that we collected.”
MethodA Novel Human Activity Recognition Using Spiking Neural Network
Nguyen, H. H., Nghiem, T. K., Hoang, M. P., & Nguyen, D. M. (2024) · IEEE International Conference on Contemporary Computing and Communications (InC4) · doi:10.1109/inc460750.2024.10649246 · Cited by 4
“It’s important to note that the choice of sampling rate may vary depending on the specific task; for instance, 50 Hz is often employed to recognize activities using smartphone data [5,22,23], while 45 Hz is used in [24] and 30 to 32 Hz is used in [25].”
MethodAhmad, N., Leung, H.-F., & Farnia, F. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3555799 · Cited by 4
“Earlier HAR models employ manual feature extraction [10], [11], [12].”
Yang, Z., Li, K., Huang, Z., Xu, Z., Zhu, X., & Xiao, Y. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.112317 · Cited by 3
Automatic Detection of Gait Perturbations With Everyday Wearable Technology
Feld, L., Hellmers, S., Schell-Majoor, L., Koschate, J., Zieschang, T., Hein, A., & Kollmeier, B. (2025) · IEEE Open Journal of Engineering in Medicine and Biology · doi:10.1109/ojemb.2025.3624591 · Cited by 3
“Several studies have shown that tasks such as gait classification [22], fall detection [23], and activity recognition [24] can be effectively performed using only accelerometer data, even just with two axes of it [25].”
Driver Behaviour Analysis Using Telematics Sensor Data and Deep Learning Models
Yedilkhan, D., Agybetov, N., & Amirgaliyev, B. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.10.253 · Cited by 3
Body position classification for cardiorespiratory measurement
Młyńczak, M., Berka, M., Niewiadomski, W., & Cybulski, G. (2016) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2016.7591486 · Cited by 3
Evaluation of Power-Based Stair Climb Performance via Inertial Measurement Units
Hellmers, S., Lau, S., Diekmann, R., Dasenbrock, L., Kromke, T., Bauer, J. M., Fudickar, S., & Hein, A. (2019) · Communications in computer and information science · doi:10.1007/978-3-030-29196-9_13 · Cited by 3
Redefining Micro-Moments for Improving Energy Behaviour: The SIT4Energy Approach
Peppas, K. P., Chouliara, A., Tsolakis, A. C., Krinidis, S., & Tzovaras, D. K. (2019) · IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI) · doi:10.1109/smartworld-uic-atc-scalcom-iop-sci.2019.00320 · Cited by 3
“[7] investigated a diverse range of sensor number, types and positioning, Pattern Recognition (PR) methods and feature sets, concluding that although each of the accelerometer and gyroscope sensors excel in recognizing different kinds of activities, they always achieve at least as good results in synergy.”
Big Data Analytics in Mobile and Cloud Computing Environments
Rehman, M. H. U., Khan, A. U. R., & Batool, A. (2017) · IGI Global eBooks · doi:10.4018/978-1-5225-1837-2.ch068 · Cited by 4
Alencar, M., Barreto, R., Oliveira, H. A. B. F., & Souto, E. (2023) · IEEE Embedded Systems Letters · doi:10.1109/les.2023.3289810 · Cited by 3
“3—green line), called magnitude [16].”
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.