Smart Devices are Different: Assessing and MitigatingMobile Sensing Heterogeneities for Activity Recognition
The DOI matches its Crossref record; 48 of the 49 references it cites were found in a registry or an index.
Abstract
The widespread presence of motion sensors on users' personal mobile devices has spawned a growing research interest in human activity recognition (HAR). However, when deployed at a large-scale, e.g., on multiple devices, the performance of a HAR system is often significantly lower than in reported research results. This is due to variations in training and test device hardware and their operating system characteristics among others. In this paper, we systematically investigate sensor-, device- and workload-specific heterogeneities using 36 smartphones and smartwatches, consisting of 13 different device models from four manufacturers. Furthermore, we conduct experiments with nine users and investigate popular feature representation and classification techniques in HAR research. Our results indicate that on-device sensor and sensor handling heterogeneities impair HAR performances significantly. Moreover, the impairments vary significantly across devices and depends on the type of recognition technique used. We systematically evaluate the effect of mobile sensing heterogeneities on HAR and propose a novel clustering-based mitigation technique suitable for large-scale deployment of HAR, where heterogeneity of devices and their usage scenarios are intrinsic.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“Stisen et al. [179] demonstrate the problem of sensing heterogeneities in HAR, showcasing how the same movements recorded at identical locations but with different sensors result in vastly different sensor readings.”
From Past, Present, and Future of Sensor-based Human Activity Recognition Using Wearables: A Surveying Tutorial on a Still Challenging Task (2025) · cites this paper as Stisen et al. [179]
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 [43]
In the citing paper
“The diversity in sensing conditions, including device types [43], placements [5], and user demographics [38] coupled with rapidly evolving sensing technologies and emerging activity types, makes it impractical to collect comprehensive datasets for every scenario.”
From Towards Customizable Foundation Models for Human Activity Recognition with Wearable Devices (2025) · cites this paper as [43]
In the citing paper
“In total, nine participants performed scripted activities for 5 minutes, ensuring an equal distribution of categories.”
From TS2ACT: Few-Shot Human Activity Sensing with Cross-Modal Co-Learning (2023) · cites this paper as [46]
In the citing paper
“The dataset covers a diverse set of devices, including 36 smart devices of 13 models from 4 manufacturers, with varying sampling rates to accommodate heterogeneous data.”
From TS2ACT: Few-Shot Human Activity Sensing with Cross-Modal Co-Learning (2023) · cites this paper as [46]
3 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Pattern Recognition and Machine Learning
(2006) · doi:10.1007/978-0-387-45528-0 · Cited by 9,824
Pattern Recognition and Machine Learning
(2007) · Kybernetes · doi:10.1108/03684920710743466 · Cited by 8,265
(2006) · Springer eBooks · Cited by 8,123
Clustering by Passing Messages Between Data Points
Frey, B. J., & Dueck, D. (2007) · Science · doi:10.1126/science.1136800 · Cited by 6,758 · cited 1×
“To this end, we chose an affinity propagation clustering algorithm [21].”
MethodNote on the Sampling Error of the Difference Between Correlated Proportions or Percentages
McNemar, Q. (1947) · Psychometrika · doi:10.1007/bf02295996 · Cited by 4,754 · cited 1×
“Lastly, we perform statistical testing to measure variations in recognition performances using the McNemar χ(2)-tests with Yates’ correction [35].”
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 1×
“Accelerometer-based HAR has been deployed in a large number of domains including smart homes [5, 32, 38], health care [31, 37], daily activity tracking [29], fitness tracking [16], fall detection of elderly people [18] and transportation mode detection [9, 24, 42].”
BackgroundActivity recognition using cell phone accelerometers
Kwapisz, J. R., Weiss, G. M., & Moore, S. A. (2011) · ACM SIGKDD Explorations Newsletter · doi:10.1145/1964897.1964918 · Cited by 2,912 · cited 2×
“selected activity classes (or a subset of them) have been investigated prominently in a large number of HAR publications [10, 11, 14, 27, 29, 41, 47].”
BackgroundA survey of mobile phone sensing
Lane, N., Miluzzo, E., Lu, H., Peebles, D., Choudhury, T., & Campbell, A. (2010) · IEEE Communications Magazine · doi:10.1109/mcom.2010.5560598 · Cited by 2,292 · cited 4×
“Motion sensors can be further paired with sensors, e.g., GPS, GSM, WiFi, and barometer, especially for recognizing tasks beyond basic HAR.”
BackgroundInfluentialA tutorial on human activity recognition using body-worn inertial sensors
Bulling, A., Blanke, U., & Schiele, B. (2014) · ACM Computing Surveys · doi:10.1145/2499621 · Cited by 1,668 · cited 8×
“A typical ARC for HAR is composed of five stages: (i) data collection, (ii) pre-processing, (iii) segmentation, (iv) feature extraction and (v) classification.”
BackgroundInfluentialUsing mobile phones to determine transportation modes
Reddy, S., Mun, M., Burke, J., Estrin, D., Hansen, M., & Srivastava, M. (2010) · ACM Transactions on Sensor Networks · doi:10.1145/1689239.1689243 · Cited by 852 · cited 1×
“Accelerometer-based HAR has been deployed in a large number of domains including smart homes [5, 32, 38], health care [31, 37], daily activity tracking [29], fitness tracking [16], fall detection of elderly people [18] and transportation mode detection [9, 24, 42].”
Background
Research works printed but not linked: 3
- 10.5555/1771592.1771620 · doi:10.5555/1771592.1771620
- 10.5555/2283516.2283683 · doi:10.5555/2283516.2283683
- 10.5555/1929661.1929712 · doi:10.5555/1929661.1929712
Cited by
A Survey of Deep Active Learning
Ren, P., Xiao, Y., Chang, X., Huang, P.-Y., Li, Z., Gupta, B. B., Chen, X., & Wang, X. (2022) · ACM Computing Surveys · doi:10.1145/3472291 · Cited by 1,169
“011 Robotics [83, 96] HHAR [214], NWFD [145] Smart device [37] Foursquare, Twitter [116] Social network”
MethodVariational Deep Embedding: An Unsupervised and Generative Approach to Clustering
Jiang, Z., Zheng, Y., Tan, H., Tang, B., & Zhou, H. (2017) · Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2017/273 · Cited by 706
Sensor-based and vision-based human activity recognition: A comprehensive survey
Minh Dang, L., Min, K., Wang, H., Jalil Piran, M., Hee Lee, C., & Moon, H. (2020) · Pattern Recognition · doi:10.1016/j.patcog.2020.107561 · Cited by 730
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
DeepSense: A Unified Deep Learning Framework for Time-Series Mobile Sensing Data Processing
Yao, S., Hu, S., Zhao, Y., Zhang, A., & Abdelzaher, T. (2017) · Proceedings of the 26th International Conference on World Wide Web · doi:10.1145/3038912.3052577 · Cited by 667
“Using these sensors, mobile devices are able to infer user activities and states [35, 39] and recognize surrounding context [31, 42].”
BackgroundMethodInfluentialStructural Deep Clustering Network
Bo, D., Wang, X., Shi, C., Zhu, M., Lu, E., & Cui, P. (2020) · Proceedings of The Web Conference 2020 · doi:10.1145/3366423.3380214 · Cited by 534
“• HHAR[23]: The Heterogeneity Human Activity Recognition (HHAR) dataset contains 10299 sensor records from smart phones and smart watches.”
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
“During recent years, many efforts have been put into improving the generalizability of models in HAR [3, 219, 262].”
BackgroundHarari, G. M., Lane, N. D., Wang, R., Crosier, B. S., Campbell, A. T., & Gosling, S. D. (2016) · Perspectives on Psychological Science · doi:10.1177/1745691616650285 · Cited by 515
“Such standardization issues even arise when a standard OS is used across devices made by different manufacturers or devices containing different makes of sensors (e.g., participants using different Android devices; Stisen et al., 2015).”
Ramanujam, E., Perumal, T., & Padmavathi, S. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3069927 · Cited by 455
A Comprehensive Survey on Multi-View Clustering
Fang, U., Li, M., Li, J., Gao, L., Jia, T., & Zhang, Y. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2023.3270311 · Cited by 351
Demrozi, F., Pravadelli, G., Bihorac, A., & Rashidi, P. (2020) · IEEE Access · doi:10.1109/access.2020.3037715 · Cited by 368
“integrated into personal devices such as smartphones and smartwatches, or are integrated into clothes or other specific medical equipment [6]–[9].”
BackgroundMethodInfluentialHuman activity recognition in artificial intelligence framework: a narrative review
Gupta, N., Gupta, S. K., Pathak, R. K., Jain, V., Rashidi, P., & Suri, J. S. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-021-10116-x · Cited by 337
Multi-task Self-Supervised Learning for Human Activity Detection
Saeed, A., Ozcelebi, T., & Lukkien, J. (2019) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3328932 · Cited by 346
“The Heterogeneity Human Activity Recognition (HHAR) dataset [64] contains signals from two sensors (accelerometer and gyroscope) of smartphones and smartwatches for 6 different activities, i.”
BackgroundRecognizing Detailed Human Context in the Wild from Smartphones and Smartwatches
Vaizman, Y., Ellis, K., & Lanckriet, G. (2017) · IEEE Pervasive Computing · doi:10.1109/mprv.2017.3971131 · Cited by 324
Deep 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
Recent trends in machine learning for human activity recognition—A survey
Ramasamy Ramamurthy, S., & Roy, N. (2018) · WIREs Data Mining and Knowledge Discovery · doi:10.1002/widm.1254 · Cited by 299
Imaging and fusing time series for wearable sensor-based human activity recognition
Qin, Z., Zhang, Y., Meng, S., Qin, Z., & Choo, K.-K. R. (2020) · Information Fusion · doi:10.1016/j.inffus.2019.06.014 · Cited by 309
“RF [19] , which selects popular frequency domain and time-domain features from [40] and ECDF features from Hammerla et al. [41] , uses random forest as the clas-sifier.”
BackgroundMethodMachine Learning for Microcontroller-Class Hardware: A Review
Saha, S. S., Sandha, S. S., & Srivastava, M. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3210773 · Cited by 253
A Survey on Deep Learning for Human Activity Recognition
Gu, F., Chung, M.-H., Chignell, M., Valaee, S., Zhou, B., & Liu, X. (2022) · ACM Computing Surveys · doi:10.1145/3472290 · Cited by 272
Edge Intelligence: Empowering Intelligence to the Edge of Network
Xu, D., Li, T., Li, Y., Su, X., Tarkoma, S., Jiang, T., Crowcroft, J., & Hui, P. (2021) · Proceedings of the IEEE · doi:10.1109/jproc.2021.3119950 · Cited by 272
Deep Fusion Clustering Network
Tu, W., Zhou, S., Liu, X., Guo, X., Cai, Z., Zhu, E., & Cheng, J. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i11.17198 · Cited by 241
Multimodal Deep Learning for Activity and Context Recognition
Radu, V., Tong, C., Bhattacharya, S., Lane, N. D., Mascolo, C., Marina, M. K., & Kawsar, F. (2018) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3161174 · Cited by 281
“Evaluation of shallow classifiers was performed in line with their original works, such as employing the same features as described in [65], for activity recognition or by extracting ECDF features (which shows good performance in our evaluation despite its compression effect).”
MethodSelf-citationTransformers and large language models in healthcare: A review
Nerella, S., Bandyopadhyay, S., Zhang, J., Contreras, M., Siegel, S., Bumin, A., Silva, B., Sena, J., Shickel, B., Bihorac, A., et al. (2024) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2024.102900 · Cited by 197
“They studied sequences of human movements through multimodal data (such as RGB, depth and skeletal-data) [390-392] or modeled human activity through accelerometer and gyroscope [393-396].”
Lipsmeier, F., Taylor, K. I., Kilchenmann, T., Wolf, D., Scotland, A., Schjodt‐Eriksen, J., Cheng, W., Fernandez‐Garcia, I., Siebourg‐Polster, J., Jin, L., et al. (2018) · Movement Disorders · doi:10.1002/mds.27376 · Cited by 266
Kumar, P., Chauhan, S., & Awasthi, L. K. (2024) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-023-09986-x · Cited by 206
“Nine people’s recordings have been made [41].”
ClusterFL: a similarity-aware federated learning system for human activity recognition
Ouyang, X., Xie, Z., Zhou, J., Huang, J., & Xing, G. (2021) · Proceedings of the 19th Annual International Conference on Mobile Systems, Applications, and Services · doi:10.1145/3458864.3467681 · Cited by 219
“The design of ClusterFL is motivated by the key observation that, in spite of the heterogeneity, data distributions of different users’ activities may share significant spatial-temporal similarity [11, 51].”
BackgroundInfluentialGraph Neural Networks in IoT: A Survey
Dong, G., Tang, M., Wang, Z., Gao, J., Guo, S., Cai, L., Gutierrez, R., Campbel, B., Barnes, L. E., & Boukhechba, M. (2023) · ACM Transactions on Sensor Networks · doi:10.1145/3565973 · Cited by 196
“HHAR [251] HAR dataset contains accelerometer and gyroscope data [193] [url]”
MethodEdge Intelligence: Architectures, Challenges, and Applications
Xu, D., Li, T., Li, Y., Su, X., Tarkoma, S., Jiang, T., Crowcroft, J., & Hui, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.12172 · Cited by 120
“The data collected by on-device sensors maybe noisy and it is hard to eliminate [381], [383].”
BackgroundA 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
“[11] showed that even OS type and CPU load have also drastic negative effects on recognition accuracy.”
BackgroundManapragada, C., Webb, G. I., & Salehi, M. (2018) · Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3219819.3220005 · Cited by 183
Yao, S., Zhao, Y., Zhang, A., Su, L., & Abdelzaher, T. (2017) · Proceedings of the 15th ACM Conference on Embedded Network Sensor Systems · doi:10.1145/3131672.3131675 · Cited by 188
“6: System performance tradeoff for user identification with biometric motion analysis In this evaluation section, we use the dataset collected by Al-lan et al. [45]. dataset contains readings from two motion sensors (accelerometer and gyroscope).”
MethodFrom smart to deep: Robust activity recognition on smartwatches using deep learning
Bhattacharya, S., & Lane, N. D. (2016) · 2016 IEEE International Conference on Pervasive Computing and Communication Workshops (PerCom Workshops) · doi:10.1109/percomw.2016.7457169 · Cited by 174
Self-citationHuman Activity Recognition Using Federated Learning
Sozinov, K., Vlassov, V., & Girdzijauskas, S. (2018) · 2018 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Ubiquitous Computing & Communications, Big Data & Cloud Computing, Social Computing & Networking, Sustainable Computing & Communications (ISPA/IUCC/BDCloud/SocialCom/SustainCom) · doi:10.1109/bdcloud.2018.00164 · Cited by 167
“The Heterogeneity Human Activity Recognition Dataset produced by [13] is used in this project.”
MethodUTiLearn: A Personalised Ubiquitous Teaching and Learning System for Smart Societies
Mehmood, R., Alam, F., Albogami, N. N., Katib, I., Albeshri, A., & Altowaijri, S. M. (2017) · IEEE Access · doi:10.1109/access.2017.2668840 · Cited by 150
“8 for the Stisen smart phone accelerometer dataset [79].”
BackgroundMulti-Source Deep Domain Adaptation with Weak Supervision for Time-Series Sensor Data
Wilson, G., Doppa, J. R., & Cook, D. J. (2020) · Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3394486.3403228 · Cited by 141
“We also include the Heterogeneity Human Activity Recognition Dataset (HHAR) dataset [35], which is more diverse than HAR, including accelerometer data from 31 smartphones of different manufacturers, models, etc.”
MethodScaling Human Activity Recognition via Deep Learning-based Domain Adaptation
Khan, M. A. A. H., Roy, N., & Misra, A. (2018) · 2018 IEEE International Conference on Pervasive Computing and Communications (PerCom) · doi:10.1109/percom.2018.8444585 · Cited by 139
“Indeed, the accelerometer sensor on different smartphones (of the same model) are known to exhibit perceptible differences [3], and the AR accuracy is known to degrade [4] due to such instance-specific variations in the sensor observations across different devices.”
BackgroundMethodInfluentialA Systematic Study of Unsupervised Domain Adaptation for Robust Human-Activity Recognition
Chang, Y., Mathur, A., Isopoussu, A., Song, J., & Kawsar, F. (2020) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3380985 · Cited by 138
“While the classification performance was high on RealWorld, HHAR, and PAMAP2 datasets, we observed that the performance on Opportunity dataset was low, especially on the wrist, hand, and foot.”
BackgroundInfluentialXu, 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
“HHAR dataset [40] contains readings from accelerometers and gyroscopes from 9 users with 6 different activities (biking, sitting, standing, walking, upstairs, and downstairs), and 6 types of mobile phones (3 models of Samsung Galaxy and one model of LG), which are carried by the users around their waist.”
MethodSelf-Supervised Graph Convolutional Network for Multi-View Clustering
Xia, W., Wang, Q., Gao, Q., Zhang, X., & Gao, X. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3094296 · Cited by 162
“These different tasks involve the following four datasets: • Cora dataset [53] dataset [55] consists of sensor records of 6 categories human activities, 10,299 nodes in total, where the node content of 1-st view is described by a 561-”
BackgroundAttention-driven Graph Clustering Network
Peng, Z., Liu, H., Jia, Y., & Hou, J. (2021) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3474085.3475276 · Cited by 191
“We conduct the experiments on six commonly used benchmark datasets,includingoneimagedataset (USPS[11]),onerecorddataset (HHAR[33]),onetextdataset(Reuters[19]),andthreegraphdatasets (ACM 2 , CiteSeer 3 , and DBLP 4 ).”
Yao, S., Zhao, Y., Shao, H., Liu, S., Liu, D., Su, L., & Abdelzaher, T. (2018) · Proceedings of the 16th ACM Conference on Embedded Networked Sensor Systems · doi:10.1145/3274783.3274840 · Cited by 146
“ivity recognition (HHAR). This task focuses on the generalization ability with human who has not appeared in the training dataset. During this experiment, we use the dataset collected by Allan et al. [30]. During this evaluation, we use DeepSense structure as the original network structure [34]. Table 8 illustrates Se…”
MethodPrivacy, ethics, transparency, and accountability in AI systems for wearable devices
Radanliev, P. (2025) · Frontiers in Digital Health · doi:10.3389/fdgth.2025.1431246 · Cited by 171
Towards multimodal deep learning for activity recognition on mobile devices
Radu, V., Lane, N. D., Bhattacharya, S., Mascolo, C., Marina, M. K., & Kawsar, F. (2016) · Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing: Adjunct · doi:10.1145/2968219.2971461 · Cited by 147
Self-citationSelfHAR: Improving Human Activity Recognition through Self-training with Unlabeled Data
Tang, C. I., Perez-Pozuelo, I., Spathis, D., Brage, S., Wareham, N., & Mascolo, C. (2021) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3448112 · Cited by 140
“Thus, studies [1, 18, 24, 26, 45] which collect HAR data are usually small, mostly involving less than 50 participants.”
BackgroundMethodA Federated Learning Aggregation Algorithm for Pervasive Computing: Evaluation and Comparison
EK, S., PORTET, F., LALANDA, P., & VEGA, G. (2021) · 2021 IEEE International Conference on Pervasive Computing and Communications (PerCom) · doi:10.1109/percom50583.2021.9439129 · Cited by 116
“HAR is well suited to our FL experiments because activities tend to have generic patterns (an activity involves the same sequence of movements for anybody) while being highly idiosyncratic (data depends on people, devices, the way devices are carried, the environment, etc.) [12].”
BackgroundDeepSense: A Unified Deep Learning Framework for Time-Series Mobile Sensing Data Processing
Yao, S., Hu, S., Zhao, Y., Zhang, A., & Abdelzaher, T. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.01942 · Cited by 102
“Using these sensors, mobile devices are able to infer user activities and states [35, 39] and recognize surrounding context [31, 42].”
BackgroundMethodInfluentialSuspicious activity detection using deep learning in secure assisted living IoT environments
Vallathan, G., John, A., Thirumalai, C., Mohan, S., Srivastava, G., & Lin, J. C. (2020) · The Journal of Supercomputing · doi:10.1007/s11227-020-03387-8 · Cited by 146
“The performance of the proposed RFKD with ReHAR , including results for prediction, sensitivity, and specificity, is shown in Table 4.”
MethodInfluentialEdge Intelligence for Data Handling and Predictive Maintenance in IIOT
Hafeez, T., Xu, L., & McArdle, G. (2021) · IEEE Access · doi:10.1109/access.2021.3069137 · Cited by 156
Meta-HAR: Federated Representation Learning for Human Activity Recognition
Li, C., Niu, D., Jiang, B., Zuo, X., & Yang, J. (2021) · Proceedings of the Web Conference 2021 · doi:10.1145/3442381.3450006 · Cited by 133
“Here, we demonstrate with experiments on HHAR dataset [29] that the heterogeneity in signal distributions alone can cause significant performance degradation.”
MethodDeep Learning for the Internet of Things
Yao, S., Zhao, Y., Zhang, A., Hu, S., Shao, H., Zhang, C., Su, L., & Abdelzaher, T. (2018) · Computer · doi:10.1109/mc.2018.2381131 · Cited by 132
A survey on deploying mobile deep learning applications: A systemic and technical perspective
Wang, Y., Wang, J., Zhang, W., Zhan, Y., Guo, S., Zheng, Q., & Wang, X. (2022) · Digital Communications and Networks · doi:10.1016/j.dcan.2021.06.001 · Cited by 110
Big data machine learning using apache spark MLlib
Assefi, M., Behravesh, E., Liu, G., & Tafti, A. P. (2017) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2017.8258338 · Cited by 129
ExtraSensory App: Data Collection In-the-Wild with Rich User Interface to Self-Report Behavior
Vaizman, Y., Ellis, K., Lanckriet, G., & Weibel, N. (2018) · Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3173574.3174128 · Cited by 115
“Data collection in-the-wild raises technical difficulties related to interruptions in sensor recording and diversity in phonedevices [24] and device placement [15].”
BackgroundHARGPT: Are LLMs Zero-Shot Human Activity Recognizers?
Ji, S., Zheng, X., & Wu, C. (2024) · 2024 IEEE International Workshop on Foundation Models for Cyber-Physical Systems & Internet of Things (FMSys) · doi:10.1109/fmsys62467.2024.00011 · Cited by 148
“To facilitate these experiments, we utilized two distinct datasets: Capture24 [4] and HHAR [15], for the experiments respectively.”
MethodColloSSL: Collaborative Self-Supervised Learning for Human Activity Recognition
Jain, Y., Tang, C. I., Min, C., Kawsar, F., & Mathur, A. (2022) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3517246 · Cited by 113
MetaSense: few-shot adaptation to untrained conditions in deep mobile sensing
Gong, T., Kim, Y., Shin, J., & Lee, S.-J. (2019) · Proceedings of the 17th Conference on Embedded Networked Sensor Systems · doi:10.1145/3356250.3360020 · Cited by 107
“Our activity recognition task is composed of nine activities that are commonly used in the literature [2, 45].”
BackgroundMethodInfluentialHuman activity recognition from sensor data using spatial attention-aided CNN with genetic algorithm
Sarkar, A., Hossain, S., & Sarkar, R. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07911-0 · Cited by 119
“HHAR contains the largest number of training and testing data, whereas PAMAP2 contains more additional sensors compared to the rest of the datasets.”
MethodInfluentialSchrader, L., Vargas Toro, A., Konietzny, S., Rüping, S., Schäpers, B., Steinböck, M., Krewer, C., Müller, F., Güttler, J., & Bock, T. (2020) · Journal of Population Ageing · doi:10.1007/s12062-020-09260-z · Cited by 110
“& The HHAR (Heterogeneity HAR) study analysed various heterogeneities in motion sensor-based sensing (i.e., sensor biases, sampling rate heterogeneity and sampling rate instability) and their impact on HAR by sensing a set of activities with 13 different smartphones (Stisen et al. 2015).”
BackgroundAssessing the State of Self-Supervised Human Activity Recognition Using Wearables
Haresamudram, H., Essa, I., & Plötz, T. (2022) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3550299 · Cited by 107
“Further, we observe how having the same target location (i.e., the wrist) can result in increased performance over all supervised baselines, specially in the case of HHAR and Myogym.”
MethodInfluentialFederated Self-Supervised Learning of Multisensor Representations for Embedded Intelligence
Saeed, A., Salim, F. D., Ozcelebi, T., & Lukkien, J. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3009358 · Cited by 106
“For activity classification with smartphones, accelerometer, and gyroscope signals from HHAR [52] and MobiAct [53] data sets are used, which have”
MethodInfluentialAdversarial Spectral Kernel Matching for Unsupervised Time Series Domain Adaptation
Liu, Q., & Xue, H. (2021) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2021/378 · Cited by 145
Robust Human Activity Recognition using smartwatches and smartphones
San-Segundo, R., Blunck, H., Moreno-Pimentel, J., Stisen, A., & Gil-Martín, M. (2018) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2018.04.002 · Cited by 105
Self-citationEfficient algorithm for big data clustering on single machine
Alguliyev, R. M., Aliguliyev, R. M., & Sukhostat, L. V. (2019) · CAAI Transactions on Intelligence Technology · doi:10.1049/trit.2019.0048 · Cited by 100
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
“2015 Complex Human Activities Dataset [47] [122] x x 390 240 csv 10 13 x 50 x x x 2015 Heterogeneity Activity Recognition Data Set (HHAR) [60] [123] x 270 3333.”
BackgroundTrends 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
Human activity recognition with smartphone-integrated sensors: A survey
Dentamaro, V., Gattulli, V., Impedovo, D., & Manca, F. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.123143 · Cited by 118
Xia, W., Wang, S., Yang, M., Gao, Q., Han, J., & Gao, X. (2021) · Neural Networks · doi:10.1016/j.neunet.2021.10.006 · Cited by 102
ADATIME: A Benchmarking Suite for Domain Adaptation on Time Series Data
Ragab, M., Eldele, E., Tan, W. L., Foo, C.-S., Chen, Z., Wu, M., Kwoh, C. K., & Li, X. (2023) · CRC Press eBooks · doi:10.1145/3587937 · Cited by 124
“The Heterogeneity Human Activity Recognition (HHAR) dataset [31] has been collected from 9 subjects using smartphone and smartwatch sensor readings.”
MethodYin, 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
Cosmo: contrastive fusion learning with small data for multimodal human activity recognition
Ouyang, X., Shuai, X., Zhou, J., Shi, I. W., Xie, Z., Xing, G., & Huang, J. (2022) · Proceedings of the 28th Annual International Conference on Mobile Computing And Networking · doi:10.1145/3495243.3560519 · Cited by 94
Recognition of human activity using GRU deep learning algorithm
Mohsen, S. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15571-y · Cited by 104
A review on action recognition for accident detection in smart city transportation systems
Adewopo, V. A., ElSayed, Z., ElSayed, Z., Özer, M., Abdelgawad, A., & Bayoumi, M. (2023) · Journal of Electrical Systems and Information Technology · doi:10.1186/s43067-023-00124-y · Cited by 104
Self-Supervised Contrastive Learning for Medical Time Series: A Systematic Review
Liu, Z., Alavi, A., Li, M., & Zhang, X. (2023) · Sensors · doi:10.3390/s23094221 · Cited by 90
Survey 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
Industry 4.0-Oriented Deep Learning Models for Human Activity Recognition
Mohsen, S., Elkaseer, A., & Scholz, S. G. (2021) · IEEE Access · doi:10.1109/access.2021.3125733 · Cited by 93
“In other applications, wearable accelerometers are used to measure human activity for remotely communicating between patients and hospitals [12].”
BackgroundDeep Unsupervised Domain Adaptation with Time Series Sensor Data: A Survey
Shi, Y., Ying, X., & Yang, J. (2022) · Sensors · doi:10.3390/s22155507 · Cited by 103
Intelligent Wearable System With Motion and Emotion Recognition Based on Digital Twin Technology
Yu, F., Yu, C., Tian, Z., Liu, X., Cao, J., Liu, L., Du, C., & Jiang, M. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3394244 · Cited by 91
“We verify the superiority of the proposed model through comparative experiments on public data sets for human action recognition UCI-HAR [45] and UniMiB SHAR [46].”
MethodHuman Activity Recognition Using K-Nearest Neighbor Machine Learning Algorithm
Mohsen, S., Elkaseer, A., & Scholz, S. G. (2021) · Smart innovation, systems and technologies · doi:10.1007/978-981-16-6128-0_29 · Cited by 99
Yao, S., Piao, A., Jiang, W., Zhao, Y., Shao, H., Liu, S., Liu, D., Li, J., Wang, T., Hu, S., et al. (2019) · International World Wide Web Conference (WWW) · doi:10.1145/3308558.3313426 · Cited by 104
“physics of measured phenomena are best expressed in the frequency domain, decades of research on signal processing developed powerful techniques for time-frequency analysis of signals, including motion sensor signals [12, 23], radio frequency signals [19, 25], acoustic signals [3, 8], and visible light signals [17].”
BackgroundClusterFL: A Clustering-based Federated Learning System for Human Activity Recognition
Ouyang, X., Xie, Z., Zhou, J., Xing, G., & Huang, J. (2022) · ACM Transactions on Sensor Networks · doi:10.1145/3554980 · Cited by 100
“Machine Learning has been increasingly adopted in the area of human activity recognition [36].”
BackgroundMethodInfluentialTransformer-based models to deal with heterogeneous environments in Human Activity Recognition
Ek, S., Portet, F., & Lalanda, P. (2023) · Personal and Ubiquitous Computing · doi:10.1007/s00779-023-01776-3 · Cited by 101
“The HHAR dataset [42] is based on 9 participants.”
Smartwatch Based Activity Recognition Using Active Learning
Shahmohammadi, F., Hosseini, A., King, C. E., & Sarrafzadeh, M. (2017) · 2017 IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE) · doi:10.1109/chase.2017.115 · Cited by 76
“This method was used over 10-fold cross-validation, as cross-validation can obtain deceptively high accuracies in activity recognition classifiers [40].”
MethodTowards federated unsupervised representation learning
van Berlo, B., Saeed, A., & Ozcelebi, T. (2020) · Proceedings of the Third ACM International Workshop on Edge Systems, Analytics and Networking · doi:10.1145/3378679.3394530 · Cited by 79
“The down-stream classifier stages were executed with the HHAR and HAPT datasets.”
MethodInfluentialA New Framework for Smartphone Sensor-Based Human Activity Recognition Using Graph Neural Network
Mondal, R., Mukherjee, D., Singh, P. K., Bhateja, V., & Sarkar, R. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.3015726 · Cited by 88
“We have considered 6 publicly available HAR datasets namely MobiAct [23], WISDM [9], MHEALTH [24], PAMAP2 [11], HHAR [13] and USC-HAD [25] for evaluating our proposed GNN based model.”
MethodInfluentialMM-Fit: Multimodal Deep Learning for Automatic Exercise Logging across Sensing Devices
Strömbäck, D., Huang, S., & Radu, V. (2020) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3432701 · Cited by 73
“The following three datasets were used for pretraining, RecoFit [36], the Heterogeneity Human Activity Recognition (HHAR) dataset [47], and Human3.”
MethodAttention-Based Deep Learning Framework for Human Activity Recognition With User Adaptation
Buffelli, D., & Vandin, F. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3067690 · Cited by 68
“As non-deep learning baselines we considered a Random Forest (RF) classifier (one of the most used and most effective shallow classifiers for HAR [41]) on the same raw frequency domain features fed to the deep learning approaches (denoted with RF-FF ), and then on the most used handcrafted frequency…”
BackgroundMethodScalable real-time classification of data streams with concept drift
Tennant, M., Stahl, F. T., RANA, O. F., & Gomes, J. B. (2017) · Future Generation Computer Systems · doi:10.1016/j.future.2017.03.026 · Cited by 76
“17 shows the speedup of the algorithm on the HAR data set.”
MethodInfluentialOccupancy detection systems for indoor environments: A survey of approaches and methods
Trivedi, D., & Badarla, V. (2019) · Indoor and Built Environment · doi:10.1177/1420326x19875621 · Cited by 80
“Another approach presented by Stisen et al. 89 mitigated the heterogeneity (sensor biases, sampling instabilities and sampling rates) issue in human activity recognition using learner types namely C4.5 tree, SVM, KNN (K-Nearest Neighbour) and RF.”
MethodDeep Human Activity Recognition With Localisation of Wearable Sensors
Lawal, I. A., & Bano, S. (2020) · IEEE Access · doi:10.1109/access.2020.3017681 · Cited by 80
“accelerometer and gyroscope) create new opportunities for continuous monitoring of human physical activities [1].”
BackgroundMethodImproving Deep Learning for HAR with Shallow LSTMs
Bock, M., Hölzemann, A., Moeller, M., & Van Laerhoven, K. (2021) · 2021 International Symposium on Wearable Computers · doi:10.1145/3460421.3480419 · Cited by 74
“Our paper’s contributions are threefold: (1) We show that an altered DeepConvLSTM architecture with a one-layered LSTM overall outperforms architectures employing a two-layered LSTM, by validating our claim using the Opportunity dataset [29] as seen in [26], as well as 4 other popular HAR datasets [28, 32, 33, 36].”
BackgroundMethodInfluentialA 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
Akbari, A., & Jafari, R. (2019) · Proceedings of the 18th International Conference on Information Processing in Sensor Networks · doi:10.1145/3302506.3310391 · Cited by 69
Sensor-Based Human Activity Recognition Using Deep Stacked Multilayered Perceptron Model
Rustam, F., Reshi, A. A., Ashraf, I., Mehmood, A., Ullah, S., Khan, D. M., & Choi, G. S. (2020) · IEEE Access · doi:10.1109/access.2020.3041822 · Cited by 81
“This study uses two datasets, i.e., ‘‘Human Activity Recognition Using Smartphones Dataset’’ [23] and ‘‘Heterogeneity Human Activity Recognition Dataset’’ obtained from UCI Machine Learning Repository [24].”
MethodA Multimodal Data Processing System for LiDAR-Based Human Activity Recognition
Roche, J., Silva, V. D., Hook, J., Moencks, M., & KONDOZ, A. M. (2021) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3085489 · Cited by 80
“These unfavorable results can be attributed to variations in device hardware and the relative position of sensors [32].”
BackgroundApplications of Federated Learning in Mobile Health: Scoping Review
Wang, T., Du, Y. N., Gong, Y., Choo, K. R., & Guo, Y. (2023) · Journal of Medical Internet Research · doi:10.2196/43006 · Cited by 95
Progress on Artificial Neural Networks for Big Data Analytics: A Survey
Chiroma, H., Abdullahi, A. U., Abdulhamid, S. M., Alarood, A. A., Gabralla, L. A., Rana, N., Shuib, L. M., Hashem, M., Dada, E. G., Ibrahim, A. A., et al. (2018) · IEEE Access · doi:10.1109/access.2018.2880694 · Cited by 84
Active and adaptive ensemble learning for online activity recognition from data streams
Krawczyk, B. (2017) · Knowledge-Based Systems · doi:10.1016/j.knosys.2017.09.032 · Cited by 75
“Human Activity Recognition Using Smartphones [40] is a dataset collected from 30 people using Samsung Galaxy S II smartphone, attached to their waists4.”
BackgroundInfluentialMathur, A., Zhang, T., Bhattacharya, S., Velickovic, P., Joffe, L., Lane, N. D., Kawsar, F., & Lio, P. (2018) · 2018 17th ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN) · doi:10.1109/ipsn.2018.00048 · Cited by 70
“Similarly, [25] found that even run-time factors within the same device, such as instantaneous I/O load or delays in OSlevel timestamp attachment to sensor measurements, can lead to an unstable sampling rates.”
BackgroundMethodSelf-citationAccelerometers in Our Pocket: Does Smartphone Accelerometer Technology Provide Accurate Data?
Grouios, G., Ziagkas, E., Loukovitis, A., Chatzinikolaou, K., & Koidou, E. (2022) · Sensors · doi:10.3390/s23010192 · Cited by 78
CALDA: Improving Multi-Source Time Series Domain Adaptation With Contrastive Adversarial Learning
Wilson, G., Doppa, J. R., & Cook, D. J. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3298346 · Cited by 83
“These include four human activity recognition datasets (UCI HAR [4], UCI HHAR [47], WISDM AR [48], and WISDM AT [49]) and two multivariate EMG datasets collected using a Myo armband (Myo EMG [26] and NinaPro Myo [50]).”
MethodInfluential
Metadata
- Authors
- Stisen, A., Blunck, H., Bhattacharya, S., Prentow, T. S., Kjærgaard, M. B., Dey, A., Sonne, T., & Jensen, M. M.
- Affiliations
- Aarhus University (DK)
- Bell Laboratories, Dublin, Ireland
- Carnegie Mellon University (US)
- ORCID
- Venue
- Proceedings of the 13th ACM Conference on Embedded Networked Sensor Systems
- Publisher
- ACM
- Published
- 2015-11
- Pages
- 127-140
- OpenAlex
- W2057907879
- Cited by
- 714
- References
- 49
- Citations by year
- 2026: 45 · 2025: 81 · 2024: 99 · 2023: 91 · 2022: 82 · 2021: 82 · 2020: 61 · 2019: 62 · 2018: 54 · 2017: 35 · 2016: 21 · 2015: 1
- FWCI
- 15.18
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM Conference on Embedded Networked Sensor Systems (SenSys) (publishedVersion)
- Funders
- Danish Advanced Technology Foundation (076-2011- 3.)
- The Danish Council for Strategic Research (11-11533)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Social Sciences › Transportation › Human Mobility and Location-Based Analysis
- Physical Sciences › Computer Science › Computer Science Applications › Mobile Crowdsensing and Crowdsourcing
- Keywords
- human activity recognition, mobile sensing, sensor heterogeneity, heterogeneous devices, smartphone sensors, smartwatches, large-scale deployment, feature representation, classification methods, motion sensors
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.