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
Items 701–800 of 800
Multidomain Multimodal Fusion For Human Action Recognition Using Inertial SensorsPreprint
Ahmad, Z., & Khan, N. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.09748
“These datasets are : Inertial component of UTD Multimodal Human Action Dataset (UTD-MHAD) [19],”Heterogeneity Human Activity Recognition Dataset” (HHAR), [20] and the inertial component of Kinect V2 dataset [21].”
MethodUSER AUTHENTICATION ACROSS DEVICES, MODALITIES AND REPRESENTATION: BEHAVIORAL BIOMETRIC METHODS
Belman, K., & Kamath, A. (2020) · Syracuse University Libraries (Syracuse University)
Inertial Sensor Data To Image Encoding For Human Action RecognitionPreprint
Ahmad, Z., & Khan, N. (2023) · doi:10.32920/22734293
Learning representations using neural networks and optimal transport
Harchaoui, W. (2020) · theses.fr (ABES) · doi:10.70675/23e3dc6cz3b37z4168z9062z329613fe1a0c · Cited by 4
Dependency-Based Classification With Multimodal Data Using Regular Vine Copulas
Raman, P. J., Gaonkar, A., Chukkapalli, Y., Srikanth, S., & Gurugopinath, S. (2021) · IEEE India Conference · doi:10.1109/indicon52576.2021.9691612
Applications of Deep Learning Models within National Project IT Academy – Education for 21st Century
Andrejková, G., Antoni, Ľ., Bruoth, E., Bugata, P., Gajdoš, D., Guniš, J., Horvát, Š., Hudák, D., Kmečová, V., Krajči, S., et al. (2021) · International Conference on Emerging eLearning Technologies and Applications (ICETA) · doi:10.1109/iceta54173.2021.9726253
A Public Repository to Improve Replicability and Collaboration in Deep Learning for HAR
Pellatt, L., Bock, M., Roggen, D., & Laerhoven, K. V. (2022) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomworkshops53856.2022.9767436
“The repository contains complete data loading and preprocessing pipelines for 6 popular datasets [6]–[11].”
MethodTransfer Learning in Mobile Health
Rafatirad, S., Homayoun, H., Chen, Z., & Dinakarrao, S. M. P. (2022) · Springer eBooks · doi:10.1007/978-3-030-96756-7_11
Towards an Approach for Intelligent Adaptation Decision-Making of Pervasive Middleware
Jabla, R. (2023) · RiuNet (Universitat Politècnica de València) · doi:10.4995/thesis/10251/191878
Multidomain Multimodal Fusion For Human Action Recognition Using Inertial SensorsPreprint
Ahmad, Z., & Khan, N. (2023) · doi:10.32920/22734383
Pushpalatha, S., Math, S., & Pujari, C. G. (2023) · International Conference on Trends in Electronics and Informatics (ICOEI) · doi:10.1109/icoei56765.2023.10125822
“The difficulty with this general method for classification is that it takes a lot of effort to develop strong hand-crafted features; this is because good generalization to multiple circumstances, such as variable sensor noise patterns and heterogeneous user actions, necessitates lengthy experimentation [80].”
Solar Cell Based Activity Recognition
Sandhu, M. M., Khalifa, S., Portmann, M., & Jurdak, R. (2023) · Green energy and technology · doi:10.1007/978-3-031-27685-9_6
Fusion-Based Activity Recognition
Sandhu, M. M., Khalifa, S., Portmann, M., & Jurdak, R. (2023) · Green energy and technology · doi:10.1007/978-3-031-27685-9_7
Classification of human activities by smart device measurements
Kalkan, M., & Ar, Y. (2023) · Communications Faculty of Sciences University of Ankara Series A2-A3 Physical Sciences and Engineering · doi:10.33769/aupse.1306885
Iwan, I., Yahya, B., & Lee, S. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4572245
Villegas-Cortéz, J., Román-Alonso, G., de Vega, F. F., Flores-Morales, Y. A., & Cordero-Sánchez, S. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-47765-2_24 · Cited by 1
Neural Network Models for Time Series Data
Yao, S., & Abdelzaher, T. (2023) · Springer eBooks · doi:10.1007/978-3-031-40787-1_1
Multimodal Sensor Fusion Frameworks With Application to Human Action Recognition
Ahmad, Z. (2024) · doi:10.32920/25234624.v1 · Cited by 1
Deep Learning Models for NEAT Activity Detection on Smartwatch
Dewan, A., Gunturi, V. M. V., & Naik, V. S. (2023) · IEEE Smart World Congress (SWC) · doi:10.1109/swc57546.2023.10449263
“Works in this area can be classified into two categories: (a) collecting sensor data from multiple devices, including customized hardware [8]– [15] and (b) collecting sensor data from a single device, such as a smartphone or smartwatch [16]–[20].”
BackgroundAdaptive Correction for Sensor Deviation Data of Monitoring
Chen, X., Wang, S., & Chen, X. (2023) · International Conference on Artificial Intelligence and Automation Control (AIAC) · doi:10.1109/aiac61660.2023.00001
SEGCN: Structural Enhancement Graph Clustering Network
Chen, Y., Yan, X., Cui, P., & Gong, L. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-2303-4_12
Digitale Phänotypisierung – Integration alltagsnah erhobener Daten in die Einzelfallbeurteilung
Garatva, P., & Baumeister, H. (2024) · Springer eBooks · doi:10.1007/978-3-662-64801-8_143-1
The Preprocessing for Predicting of Physical Activity Recognition
Muangsrinoon, S., & Boonbrahm, P. (2018) · International Journal of Engineering & Technology · doi:10.14419/ijet.v7i4.19.22089
Gafurov, B. S., & Stavrou, A. (2024) · International Conference on Computer, Information and Telecommunication Systems · doi:10.1109/cits61189.2024.10608020
Oshima, H., Ishizone, T., & Higuchi, T. (2024) · Transactions of the Japanese Society for Artificial Intelligence · doi:10.1527/tjsai.39-5_e-o41
Time Series Domain Adaptation via Multiscale Feature Extraction and Mix-up
Zhu, H., Tan, Z., Fang, S., & Yang, C. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10651463
DNN Model Comparison for Sensor Location Robustness
Enokibori, Y., Sato, T., & Mase, K. (2024) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3675094.3678449
He, Q.-Q., Gong, X., & Si, Y. (2024) · The Journal of Supercomputing · doi:10.1007/s11227-024-06622-8
“HHAR (Heterogeneity Human Activity Recognition) dataset [36] is a collection of sensor data obtained from smartphones and smartwatches.”
Uncertainty Awareness for Unsupervised Domain Adaptation on Human Activity Recognition
Liu, W., Zhong, X., Wang, L., Hou, J., Luo, Y., Yan, J., & Fang, Y. (2024) · Communications in computer and information science · doi:10.1007/978-981-97-9003-6_6
Human Activity Recognition with Consumer Devices and Real-Life Perspectives
Matey-Sanz, M., & Matey-Sanz, M. (2024) · Tesis Doctorals en Xarxa (Consorci de Serveis Universitaris de Catalunya) · doi:10.6035/14101.2024.663821
Oshima, H., Ishizone, T., & Higuchi, T. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2412.04682
CAUDA: Cloud-assisted Active Unsupervised Domain Adaptation for On-device Learning
Wang, Z., Zheng, Z., & Wu, F. (2024) · IEEE International Performance, Computing, and Communications Conference · doi:10.1109/ipccc59868.2024.10850366
Digitale Phänotypisierung – Integration alltagsnah erhobener Daten in die Einzelfallbeurteilung
Garatva, P., & Baumeister, H. (2025) · Springer eBooks · doi:10.1007/978-3-662-64797-4_143
UCT: Uncertainty-based consistency training for domain adaptive human activity recognition
Hu, H., She, C., Wang, L., & Duan, S. (2025) · Digital Signal Processing · doi:10.1016/j.dsp.2025.105209
Peng, Y. (2024) · International Conference on Image Processing, Computer Vision and Machine Learning (ICICML) · doi:10.1109/icicml63543.2024.10957874
Deep learning approaches, platforms, datasets for behaviorbased recognition: a survey
Jeddah, Y. M., Hashim, A. H. A., & Khalifa, O. O. (2025) · Indonesian Journal of Electrical Engineering and Computer Science · doi:10.11591/ijeecs.v38.i3.pp1880-1895
“Some datasets are intended for complex activities, like [19]; others are designed only for simple activities, like [20], while others are made for both activity types, such as [21].”
A Comprehensive Review on Human Activity and Fitness Tracker using Different Approaches
Mishra, Y. (2025) · International Journal for Research in Applied Science and Engineering Technology · doi:10.22214/ijraset.2025.70544
Synthetic Sensory Data Generators: How Much Progress Are We Making?
Sharma, R., Khamis, A., Khalifa, S., Bretherton, D., & Kusý, B. (2025) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomworkshops65533.2025.00084 · Cited by 1
“We analyse the impact of this distributional gap between synthetic and real datasets using three real-world datasets, UCI [18], HHAR [19], and MotionSense [15].”
Multi-dimensional Topological Association Strengthening Clustering Network
Sun, M., Han, R., Zeng, M., Li, M., Hu, T., Yang, Z., Wang, Z., Liu, J., Xin, W., & Feng, J. (2025) · Neural Processing Letters · doi:10.1007/s11063-025-11781-7
A Data Contribution-Based Adaptive Federated Learning Approach for Wearable Activity Recognition
Yi, Z., Hu, C., Yang, X., Yuan, L., Tian, X., Gao, T., & Chen, Y. (2025) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd64889.2025.11033257
One-Step Graph Fusion Fuzzy Clustering Network
Tang, B., Zhou, Z., Liu, X., & Chen, F. (2025) · IEEE Access · doi:10.1109/access.2025.3593844
“We conducted extensive experiments to evaluate our method on six popular public datasets, including three graph datasets (ACM 1 DBLP, 2 and CITE 3 ) and three non-graph datasets (USPS [35], HHAR [46], and Reuters [47]).”
Hamiltonian cycle clustering with asymmetric correlation
Huang, T., Zhang, Z., & Cheng, S. (2025) · Visual Informatics · doi:10.1016/j.visinf.2025.100263
Vu, Q. N. P., Lago, P., Bader, S., & Inoue, S. (2025) · International Conference on Activity and Behavior Computing (ABC) · doi:10.1109/abc64332.2025.11118576
Tri-Learn Graph Fusion Network for Attributed Graph ClusteringPreprint
Li, B., Xu, X., Li, X., Zhao, B., Gao, H., & Zhao, Q. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2507.13620
“We evaluated our model using various types of public datasets, which are: ACM 1 , DBLP [39], Citeseer [40], HHAR [41], Cora [42], USPS [43] and Reuters [44].”
GCL-GCN: Graphormer and Contrastive Learning Enhanced Attributed Graph Clustering NetworkPreprint
Li, B., Xu, X., Li, X., Lou, Q., Zhao, B., Liu, Y., Tang, H., & Yang, B. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2507.19095
“These datasets include graph datasets ACM 1 [34], DBLP [35], CiteSeer [36], Cora [37]; and non-graph datasets HHAR [38] and Reuters [39].”
Tan, S., & Li, H. (2025) · Pattern Analysis and Applications · doi:10.1007/s10044-025-01560-4
Data-Free Backdoor Attacks on Self-Supervised Human Activity Recognition Models
Zhao, T., & Wang, X. (2025) · IEEE International Conference on Mobile Ad-Hoc and Sensor Systems (MASS) · doi:10.1109/mass66014.2025.00051
Kann, B., Castellanos-Paez, S., Rombourg, R., & Lalanda, P. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-4575-9_2
Metric Embedding Initialization-Based Differentially Private and Explainable Graph Clustering
You, H., & Liu, B. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3061-8_2
Experience Paper: Adopting Activity Recognition in On-demand Food Delivery Business
Xu, H., Zhang, Y., Gao, W., Shen, G., & Li, M. (2025) · ACM Annual International Conference on Mobile Computing and Networking (MobiCom) · doi:10.1145/3680207.3765261 · Cited by 5
Goldman, R., Komperla, V., Plötz, T., & Haresamudram, H. (2026) · ACM International Symposium on Wearable Computers (ISWC) · doi:10.1145/3830727.3834826
Akhlaghi, S. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-08120-x
Xu, Q., Zhao, W., & Liu, K. (2025) · doi:10.1117/12.3093522
Datasets for Human Activity Recognition: A Comparative Analysis
Mercado, L. F. B., Beltrán, J., & Castro, L. A. (2025) · Avances en Interacción Humano-Computadora · doi:10.47756/aihc.y10i1.198
“Several studies have shown that most available datasets were obtained from small groups of subjects, generally young and healthy, which limits the applicability of the models to broader populations [15], [23].”
Human Activity Recognition Using Wearable Inertia Sensor Data adnd Machine Learning
Yu, X. (2019) · Figshare · doi:10.25394/pgs.9108512
Assessing the Robustness of HAR Deep Learning Models against Variability
Khaked, A. A. (2024) · Spectrum Research Repository (Concordia University)
Antolínez López, D. (2023) · University of Valladolid Documentary Repository (University of Valladolid) · Cited by 1
Time Series Domain Adaptation: A Review
Furqon, M. T., Pratama, M., & Jatmiko, W. (2026) · Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery · doi:10.1002/widm.70130
Controlled Domain-Adversarial Pretraining for Efficient Adaptation in Human Activity RecognitionPreprint
Lalanda, P., Vega, G., & Schlake, M. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6145966
SENTINEL-DL: a forensic framework for device attribution using motion sensor data
Buriro, A., Buriro, A. B., Ahmad, T., Luccio, F., Yaqub, M. A., & Zanker, M. (2026) · Scientific Reports · doi:10.1038/s41598-025-34734-5
“For further details on the dataset and its collection process, readers are referred to the publication by Stisen et al. 26 .”
Unsupervised Domain Adaptation Algorithm for Time Series Based on Adaptive Contrastive Learning
Liu, H., & Lin, P. (2026) · Entropy · doi:10.3390/e28030272
“Each subject is regarded as an independent domain [36].”
Niftaliyeva, G. Y. (2026) · Problems of Information Technology · doi:10.25045/jpit.v17.i1.06
UniMotion: Self-Supervised Learning for Cross-Domain IMU Motion RecognitionPreprint
Khanna, P., Srivastava, T., Jain, S., & Balasubramanian, A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.12218 · Cited by 1
“The success of these self-supervised techniques is due to the large amounts of activity data available [33, 45, 55].”
Confidence-Aware Optimal Transport for Open Set Time Series Adaptation Under Non-Stationary Shifts
Mishra, K., & Dutta, T. (2026) · IEEE Signal Processing Letters · doi:10.1109/lsp.2026.3661475
Doukaga, H. N. (2025) · Constellation (Université du Québec à Chicoutimi)
Amroun, H. (2018) · theses.fr (ABES) · doi:10.70675/e1d74124z7080z4564z9804z501d417a4179
“Chen [35] AMB DA HW(8) Acc 6 places pc NAT SPC TF,FD SMCRF 93%”
BackgroundInfluentialMetalearning guided by domain knowledge in distributed and decentralized applications
Hamidi, M. (2022) · theses.fr (ABES) · doi:10.70675/834a3ee6z6a4dz49fcz963bz834bfd0ffa27 · Cited by 1
Ek, S. (2024) · theses.fr (ABES) · doi:10.70675/a47253c1zf05az480aza992zc137c06fbc2f · Cited by 1
Eyes-free gestural interaction with smartphone using haptic feedback
Jamalzadeh, M. (2024) · theses.fr (ABES) · doi:10.70675/b5bb18e5z9ef2z45ffzb3f1z799bd6f37602
Unsupervised STDP-based Feature Learning for Video Analysis with Spiking Neural Networks
El-Assal, M. (2024) · theses.fr (ABES) · doi:10.70675/4aa220eaz87e6z4ba0za31az4b4a4bd2b065
Khan, N., Davidson, L., Sarkar, N., & Cole, K. R. (2026) · Digital Health · doi:10.1177/20552076261444097
ShiftLIF: Efficient Multi-Level Spiking Neurons with Power-of-Two Quantization
Tang, K., Yu, D., Zheng, J., Lv, C., Liu, Q., Yan, Z., & Wong, W. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3835483
Heterogeneous Federated Learning Model for Recognizing Human Activity
Al-Blihed, N. S., & Ibrahim, D. M. (2026) · doi:10.3390/cmsf2026013010
Efficient federated self-supervised human activity recognition via delta-loss client clustering
Bukit, T. A., Yahya, B. N., & Lee, S. (2026) · Digital Signal Processing · doi:10.1016/j.dsp.2026.106251
Choudhury, N. A., & Soni, B. (2026) · Transactions on computer systems and networks · doi:10.1007/978-981-95-7206-9_3
Robust Graph Clustering via Diffusion Graph Fusion with High-Order Random Walk
Liu, S., & Wen, Z. (2026) · International Conference on Sensor-Cloud and Edge Computing System (SCECS) · doi:10.1109/scecs69812.2026.11565868
Toward Practical Learning-Based Indoor Localization in the Real-World Wi-Fi ISAC System
Wang, G., Yang, S., Zhang, D., Zhang, T., Sun, Q., & Chen, Y. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3710178
“Given the heterogeneity of the data, a natural approach is to cluster the data and train a separate machine learning model for each cluster [63].”
Accelerating TSXor Using CUDA GPUs
Sharl, M., & Elmongui, H. G. (2026) · International Conference on Computer and Communication Systems (ICCCS) · doi:10.1109/icccs69761.2026.11613373
Efficient and Adaptive Human Activity Recognition via LLM Backbones
Bredikhin, A., Lalanda, P., & Vega, G. (2026) · IEEE International Conference on Smart Computing · doi:10.1109/smartcomp69968.2026.00022
Gradient Angles for Runtime Detection of Body-Position Shift in Human Activity Recognition
Kuila, S., Chatterjee, S., & Chakraborty, S. (2026) · IEEE International Workshop on Foundation Models for Cyber-Physical Systems & Internet of Things (FMSys) · doi:10.1109/fmsys72110.2026.00010
UniMoRe : Uni fied Mo tion Re presentation via Gait IMU Pretraining
Chakraborty, S., Kumar, A., & Nigam, A. (2026) · IEEE Sensors Journal · doi:10.1109/jsen.2026.3718949
“In our experiments, we use the publicly available encoder pretrained on the HHAR dataset [39].”
Hou, Q., Yin, R., Li, K., Han, Z., & Huang, Y. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.111293
Islam, M. Z., Afzel Noore, B., Adarbah, H. Y., Sagar, A. S. M. S., & Haider, A. (2026) · IEEE Sensors Journal · doi:10.1109/jsen.2026.3723733
“…the dataset includes ten participants and four activity classes, this scale is consistent with prior feasibility-driven HAR and wearable sensing studies [22], [23], [24], [25], [26], [27], which employ similarly small cohorts to validate system architecture, personalization, and edge intelligence.”
Li, Z., Miao, F., Zhang, W., & Gui, G. (2026) · Information Communication Technologies Conference (ICTC) · doi:10.1109/ictc70246.2026.11650001
Shift-Aware Operator Selection for Label-Free Test-Time Calibration in Cross-Domain Dataset
Deshagouni, M., & Akther, S. (2026) · IEEE International Conference on Big Data Computing Service and Applications (BigDataService) · doi:10.1109/bigdataservice70481.2026.00051
“2 Sayma Akther is the corresponding author. differing only through subtle gravity direction and low-motion posture cues [10]–[12].”
Revisiting Time-Domain Interpretability for Self-Supervised IMU Sensing Models
Wang, Y., Zhao, T., & Wang, X. (2026) · IEEE/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies · doi:10.1109/chase69719.2026.00039
“HHAR [15] includes data from 9 users across six activities with strong device heterogeneity, making it a challenging benchmark for cross-device generalization.”
How capable are large language models at human activity recognition within a smart home?
Larouche, J.-P. (2026) · Constellation (Université du Québec à Chicoutimi)
Yang, Q., Huang, Y., Han, J., Liang, H., Wei, H., & Hou, Z. (2026) · Processes · doi:10.3390/pr14182876
Chen, Y., & Sun, H. (2026) · Scientific Reports · doi:10.1038/s41598-026-70892-w
Mask-Aware Dynamic Gating for Robust Multi-Sensor Activity Recognition
Ouyang, W., Liu, S., Meng, T., Zhou, X., & Yang, Y. (2026) · International Conference on Big Data and Information Analytics (BigDIA) · doi:10.1109/bigdia71496.2026.11684722
“Public datasets and benchmarked sensing protocols later made it easier to compare systems across sensor placements, subjects, and device types [3], [7].”
Metacognitive Selective Ensemble for Mobile SystemsPreprint
Lee, S., Lee, K., Lee, J., Park, J., Kim, S., & Ko, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.31031
“For this motivating study, we use HHAR [45], which contains IMU measurements for six human activities, and train a pool of 𝑁 = 10 Transformer models with the same training configuration [48, 53] but different random initial-izations.”
Adapting Pretrained Large Vision Models for Sensor-based Activity Recognition
Cai, Y.-Z., Feng, R.-X., Cai, K.-L., Liu, Y.-H., Guo, B.-S., & Hong, Z.-Q. (2026) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3832003
“(1) HHAR [99] includes data from nine subjects performing six activities, including downstairs, upstairs, walking, standing, sitting, and biking, collected using smartphones and smartwatches.”
An Empirical Study for Effective LLM-Based Human-State Prediction from Physiological Data
Wang, L., Guo, A., & Ma, J. (2026) · International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW) · doi:10.1109/aciiw71585.2026.11712086
“HHAR was used for stair-activity prediction [11].”
REFIT: Recognize, Fix, and Test Wearable Sensor Placement Shifts without LabelsPreprint
Tang, B. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.08991
“A related line measures and mitigates the heterogeneity of devices, such as differences in their sampling and sensor responses [Mathur et al. 2018; Stisen et al. 2015].”
Barandas, M., Pereira, A. C., Carvalho, C., Folgado, D., Santos, R., Russo, M., Guimarães, V., Gamboa, H. F. S., & Sousa, I. (2026) · Scientific Data · doi:10.1038/s41597-026-08470-y
IMU-Bench: Benchmarking Wrist IMU Representations Across Kinematic, Semantic and Clinical TasksPreprint
Li, Y., Bradshaw, A., Gao, C., & Ahuja, K. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.19481
“HHAR, MHEALTH and PRISM use subject-disjoint splits [4, 5, 60]; PRISM uses its five global classes.”
HAR-R1: Hierarchical LLM Reasoning for Cross-Domain Human Activity RecognitionPreprint
Li, S., Ban, L., Zhu, T., Tian, J., Fang, L., Shi, P. J., Šolić, P., & Chen, L. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7649976
Wang, G., & Wang, P. (2026) · IEEE Access · doi:10.1109/access.2026.3748591
Next Token Prediction for Generalizable Human Activity Recognition
Cai, Y.-Z., Yu, A.-L., Guo, B.-S., Liu, Y.-H., & Hong, Z.-Q. (2026) · Proceedings of the 35th ACM International Conference on Information and Knowledge Management · doi:10.1145/3799682.3840756
Rethinking the Role of the Classification Head in CNN-BiLSTM-Based Human Activity Recognition
Shi, J., Wang, Y., & Yang, L. (2026) · Electronics · doi:10.3390/electronics15215194
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.