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 401–500 of 800
SensiX: A System for Best-effort Inference of Machine Learning Models in Multi-device Environments
Min, C., Mathur, A., Montanari, A., & Kawsar, F. (2022) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2022.3173914 · Cited by 10
“In [7], the impact of heterogeneous IMU sensors on the activity recognition performance has also been thoroughly studied.”
BackgroundPermatasari, J., Connie, T., & Ong, T. S. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09438-9 · Cited by 9
“The authors in [40] reported that the accuracy of HAR is degraded when observed under differing device-instances.”
BackgroundTFC: Time–frequency contrasting network for wearable-based human activity recognition
Huang, Z., Deng, J., Wang, S., Tang, C., & Xiao, S. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113373 · Cited by 9
Explainability and importance estimate of time series classifier via embedded neural network
Chan, H. T. J., Šimić, I., & Veas, E. E. (2025) · Scientific Reports · doi:10.1038/s41598-025-17703-w · Cited by 8
“This is also a dataset from the UCI Machine Learning Repsoitory 94 , it was used in the work of Stisen, et al. 95 for the investigation of sensor heterogeneities for activity recognition.”
A Large-Scale Multimodal Dataset and Benchmarks for Human Activity Scene Understanding and Reasoning
Jiang, S., Yuan, M., Ji, X., Yang, B., Liu, Z., Xu, L., Li, Y. X., He, Y., Dong, L., Lu, W., et al. (2026) · International Conference on Mobile Systems, Applications, and Services · doi:10.1145/3745756.3809209 · Cited by 13
Robust Domain-Free Domain Generalization with Class-Aware Alignment
Zhang, W., Ragab, M., & Sagarna, R. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9413872 · Cited by 8
Transformer-based Dynamic Fusion Clustering Network
Zhang, C., Zhao, Y., & Wang, J. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.109984 · Cited by 11
Streaming data cleaning based on speed change
Wang, H., Zhang, A., Song, S., & Wang, J. (2023) · The VLDB Journal · doi:10.1007/s00778-023-00796-y · Cited by 10
Park, S.-H., Syazwany, N. S., Nam, J.-H., & Lee, S. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109205 · Cited by 8
Delta: A Cloud-assisted Data Enrichment Framework for On-Device Continual Learning
Gong, C., Zheng, Z., Wu, F., Jia, X., & Chen, G. (2024) · ACM Annual International Conference on Mobile Computing and Networking (MobiCom) · doi:10.1145/3636534.3690701 · Cited by 17
“HHAR [64], UCI [65], MotionSense [66] and Shoaib [67] are four public datasets collected from 73 users performing 6 basic activities (still, walking, upstairs, downstairs, jogging, bike) with 5 device placements (pocket, belt, arm, wrist, waist).”
Learning under label noise through few-shot human-in-the-loop refinement
Saeed, A., Spathis, D., Oh, J., Choi, E., & Etemad, A. (2025) · Scientific Reports · doi:10.1038/s41598-025-87046-z · Cited by 10
“We use the Heterogeneity Human Activity Recognition (HHAR) dataset (Stisen et al., 2015) to recognize activities in daily living from IMU signals (i.e., accelerometer and gyroscope) collected from a smartphone.”
Quantum contrastive learning for human activity recognition
Ren, Y., Wang, D., An, L., Mao, S., & Wang, X. (2025) · Smart Health · doi:10.1016/j.smhl.2025.100574 · Cited by 9
Deep unsupervised domain adaptation for time series classification: a benchmark
Fawaz, H. I., Grosso, G. D., Kerdoncuff, T., Boisbunon, A., & Saffar, I. (2025) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-025-01108-4 · Cited by 9
“HHAR is also a very common time series problem (Stisen et al, 2015)”
Large-Scale Continuous Mobility Monitoring of Parkinson’s Disease Patients Using Smartphones
Cheng, W., Lipsmeier, F., Creigh, A., Scotland, A., Kilchenmann, T., Jin, L., Schjodt‐Eriksen, J., Wolf, D., Zhang, Y., Garcia, I. F., et al. (2018) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-319-98551-0_2 · Cited by 8
Nouredanesh, M., Ojeda, L., Alexander, N. B., Godfrey, A., Schwenk, M., Melek, W., & Tung, J. Y. (2022) · IEEE Journal of Translational Engineering in Health and Medicine · doi:10.1109/jtehm.2022.3163967 · Cited by 8
“Overall, considering the large range of free-living movement patterns captured in the validation/test dataset, and considering state-of-the-art models may not generalize well to new users whose data have not been used in the training process [37], the proposed framework exhibited a satisfactory performance.”
BackgroundHe, Q.-Q., Siu, S. W. I., & Si, Y. (2022) · Applied Intelligence · doi:10.1007/s10489-022-04176-x · Cited by 8
“The benchmarks contain Human Activity Recognition (HAR) dataset [1], Heterogeneity Human Activity Recognition (HHAR) dataset [20], WIreless Sensor Data Mining Activity Recognition (WISDM AR) dataset [11], and gesture recognition (uWave) dataset [13].”
BackgroundHuman Activity Recognition using Deep Learning: Past, Present and Future
Saini, S., Juneja, A., & Shrivastava, A. (2023) · International Conference on Intelligent Computing and Research Trends (ICRT) · doi:10.1109/icrt57042.2023.10146621 · Cited by 11
“HHAR [20] 4 smartwatches & 8 smartphones Waist, Pouch A, G 6 ✔ ✘ ✘ 9 Highest”
Single/Multi-Source Black-Box Domain Adaption for Sensor Time Series Data
Ren, L., & Cheng, X. (2023) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2023.3300832 · Cited by 9
“1) har [56]: The har dataset contains multichannel sensor time series data for 30 participants performing six tasks: 1) sitting; 2) standing; 3) walking; 4) biking; 5) stair up; and 6) stair down.”
MethodAn Unsupervised Method to Recognise Human Activity at Home Using Non-Intrusive Sensors
Ramos, R. G., Domingo, J. D., Zalama, E., & Gómez‐García‐Bermejo, J. (2023) · Electronics · doi:10.3390/electronics12234772 · Cited by 8
Bukhari, A., Hosseinimotlagh, S., & Kim, H. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3385016 · Cited by 8
“HHAR: The HHAR [39] data set records 6 activities performed by 9 different users.”
MethodTemporal Learning Using Echo State Network for Human Activity Recognition
Basterrech, S., & Ojha, V. (2016) · European Network Intelligence Conference (ENIC) · doi:10.1109/enic.2016.039 · Cited by 8
“Recently, a large public dataset that deals with the problems related to HAR in real-time contexts was introduced to the research communities [2].”
BackgroundMethodInfluentialDeep Architectures for Human Activity Recognition using Sensors
Baloch, Z., Shaikh, F. K., & Unar, M. A. (2019) · 3C Tecnología_Glosas de innovación aplicadas a la pyme · doi:10.17993/3ctecno.2019.specialissue2.14-35 · Cited by 10
Lago, P., Takeda, S., Okita, T., & Inoue, S. (2019) · Springer series in adaptive environments · doi:10.1007/978-3-030-13001-5_10 · Cited by 10
Opiela, M., & Galčík, F. (2020) · Sensors · doi:10.3390/s20185343 · Cited by 8
A Diverse Noise-Resilient DNN Ensemble Model on Edge Devices for Time-Series Data
Shubha, S. S., Sen, T., Shen, H., & Normansell, M. (2021) · IEEE International Conference on Sensing, Communication, and Networking (SECON) · doi:10.1109/secon52354.2021.9491607 · Cited by 9
Benchmarking Reservoir and Recurrent Neural Networks for Human State and Activity Recognition
Bacciu, D., Sarli, D. D., Gallicchio, C., Micheli, A., & Puccinelli, N. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-85099-9_14 · Cited by 11
MoSen: Activity Modelling in Multiple-Occupancy Smart HomesPreprint
Zhan, Y., & Haddadi, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.00235 · Cited by 9
“While multitudes of sensors extend the variety of information that could be received, the heterogeneity of the devices [71] and the increasing number of the residents [11, 28] complicate the data collection system in real settings.”
BackgroundKabir, M. R., Borshon, R. H., & Khan, R. (2025) · Array · doi:10.1016/j.array.2025.100462 · Cited by 8
Federated Learning for Human Activity Recognition on the MHealth Dataset
Sánchez, S., Machacuay, J., & Quinde, M. J. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-42505-9_19 · Cited by 7
Mercati, P., & Bhat, G. (2024) · IEEE Design and Test · doi:10.1109/mdat.2024.3432862 · Cited by 11
“The algorithm proposed in [106] leverages data clustering and interpolation to handle changes in sensor sampling rates.”
Detecting Falls Using a Wearable Accelerometer Motion Sensor
Nguyen, H. H., Mirza, F., Naeem, M. A., & Baig, M. M. (2017) · EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services (MobiQuitous) · doi:10.1145/3144457.3144484 · Cited by 7
“Using multiple sensors to collect data for evaluating the proposed algorithm is necessary when taking into account the sensing heterogeneity for activity recognition [26].”
Kim, K. M., & Kwak, J. W. (2024) · Sensors · doi:10.3390/s24010266 · Cited by 7
MNEMONIC: Multikernel contrastive domain adaptation for time-series classification
Lekshmi, R., Jose, B. R., Mathew, J., & Sanodiya, R. K. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.108255 · Cited by 7
Mullick, T., Shaaban, S., Radović, A., & Doryab, A. (2024) · JMIR AI · doi:10.2196/47805 · Cited by 8
“Mobile and wearable sensing has garnered increasing interest in areas of physical health [1,2], mental health [3-5], and activity recognition [6,7].”
BackgroundEarDA: 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
“…, and the smartphones were kept in the participants’ pockets of trousers. b) HHAR: The Heterogeneity Human Activity Recognition (HHAR) dataset [17] contains IMU signals captured between 50-200 Hz for six different activities (walking, walking upstairs, walking downstairs, standing, biking and…”
BackgroundExploring Human Mobility Correlations Using Semisupervised Hypergraph Clustering
Wang, M., Zhang, Y., Zhao, X., Wei, X., & Yin, B. (2025) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2025.3534159 · Cited by 7
“2) HHAR [36] contains 10 299 sensor recordings collected from smartphones and smartwatches, which are partitioned into six categories, i.e., biking, sitting, standing, walking, and going upstairs or downstairs.”
A Heterogeneous Clustering Approach for Human Activity Recognition
Kafle, S., & Dou, D. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-43946-4_5 · Cited by 7
“This has led to the significant research focus on Human Activity Recognition (HAR) using sensor data [15].”
BackgroundDeep Multiple Metric Learning for Time Series Classification
Chen, Z., Liu, Y., Zhu, J., Zhang, Y., Li, Q., Jin, R., & He, X. (2021) · IEEE Access · doi:10.1109/access.2021.3053703 · Cited by 8
“To show the effectiveness of DMML on heterogeneous dataset, we conduct experiments on Heterogeneity Human Activity Recognition (HHAR) dataset [53].”
MethodPellatt, L., & Roggen, D. (2021) · International Symposium on Wearable Computers · doi:10.1145/3460421.3478813 · Cited by 7
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
LaPOLeaF: Label propagation in an optimal leading forest
Xu, J. H., Li, T., Wu, Y., & Wang, G. (2021) · Information Sciences · doi:10.1016/j.ins.2021.06.010 · Cited by 7
Fall Guardian: An Intelligent Fall Detection and Monitoring System for Elderly
Ferdous, Z., Sakib, S. M. N., & Hashem, M. M. A. (2021) · International Conference on Electrical Information and Communication Technology (EICT) · doi:10.1109/eict54103.2021.9733551 · Cited by 7
The benefit of the doubt: Uncertainty aware sensing for edge computing platforms
Qendro, L., Chauhan, J., Ramos, A. G. C. P., & Mascolo, C. (2021) · arXiv · doi:10.48550/arxiv.2102.05956 · Cited by 6
“Our approach conforms to this as the best performing approach especially in the HHAR dataset.”
BackgroundInfluentialEfficient few-shot human activity recognition via meta-learning and data augmentation
Vettoruzzo, A., Bouguelia, M.-R., & Rognvaldsson, T. S. (2025) · Neural Computing and Applications · doi:10.1007/s00521-025-11408-x · Cited by 9
“A Early efforts in HAR relied on traditional machine learning methods, such as support vector machines (SVM) and decision trees [25, 44, 50], and on simple deep learning models.”
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
“Information also must be discarded when multiple heterogenous devices are used, for example when using the dataset HHAR [68].”
Hu, X., Zhang, S., Zhang, T., Han, Y. M., Wang, L., & Geng, Z. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130975 · Cited by 6
Oishi, N., Birch, P. M., Roggen, D., & Lago, P. (2026) · IEEE Sensors Journal · doi:10.1109/jsen.2026.3661047 · Cited by 9
“Moreover, it does not account for sensor bias, which is prevalent in real-world consumer devices [6].”
An Analysis of Human Activities Recognition using Smartwatches Dataset
Karim, S., Aqil, S., & Mahmood, N. (2020) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2020.0111241 · Cited by 6
“• Activity Recognition Using Active Learning [1].”
MethodInfluentialEvolutionary Neural Architecture Search and Its Applications in Healthcare
Liu, X., Li, J., Zhao, J., Cao, B., Yan, R., & Lv, Z. (2023) · Computer Modeling in Engineering & Sciences · doi:10.32604/cmes.2023.030391 · Cited by 16
Federated learning in healthcare applications
Kanhegaonkar, P., & Prakash, S. (2024) · Elsevier eBooks · doi:10.1016/b978-0-44-313233-9.00013-8 · Cited by 7
A Survey of Advances in Multimodal Federated Learning with Applications
Barry, G., Konyar, E., Harvill, B., & Johnstone, C. (2024) · Springer optimization and its applications · doi:10.1007/978-3-031-53092-0_15 · Cited by 7
Improved Attributed Graph Clustering with Representation and Structure Augmentation
Guo, J., Yin, T., Zhao, T., Zhao, J., Sun, Y., Gao, J., & Wang, Y. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650771 · Cited by 7
“To comprehensively evaluate effectiveness and superiority of the proposed IAGC-RSA, we conduct the node clustering experiments on the six public datasets, including USPS, HHAR 1 [27], Reuters 2 [28], ACM 3 [29], DBLP 4 [29], and CiteSeer 5 datasets.”
MethodCheng, C.-F., Lin, C. J., & Hu, Q.-X. (2025) · Artificial intelligence for engineering design analysis and manufacturing · doi:10.1017/s0890060424000313 · Cited by 6
“Moreover, most existing public databases are based on ADL (Anguita et al., 2013; Banos et al., 2014; Chavarriaga et al., 2013; Micucci et al., 2017; Reiss and Stricker, 2012; Stisen et al., 2015; Sztyler and Stuckenschmidt, 2016).”
CHAR: 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.”
Geng, J., Li, B., Qin, X., Li, Y., Li, L., Hou, Y., & Pan, M. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3572516 · Cited by 9
“Prior to that, the FL training at early stages follows Oort’s approach, avoiding model drift, saving the resources of mobile devices, and preparing for the overlapping in FedEx as shown in Fig.”
Differentiable 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.”
Evidentially Calibrated Source-Free Time-Series Domain Adaptation With Temporal Imputation
Ragab, M., Gong, P., Eldele, E., Zhang, W., Wu, M., Foo, C.-S., Zhang, D., Li, X., & Chen, Z. (2025) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2025.3621774 · Cited by 6
“The results reveal a clear distinction between the two approaches.”
Billet, B., & Valerie Issarny, Z. (2017) · ACM Transactions on Internet Technology · doi:10.1145/3041025 · Cited by 6
“If this step detects that the user is not moving, then a false negative can still occur, as activity recognition algorithms are not perfectly reliable [Stisen et al. 2015].”
BackgroundInfluentialEk, S., Portet, F., Lalanda, P., & Vega, G. (2021) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomworkshops51409.2021.9431080 · Cited by 7
Recognition of Human Activity from ECG and IMU Signals Using Deep Learning Networks
Mekruksavanich, S., Jantawong, P., & Jitpattanakul, A. (2022) · IEEE Region 10 Symposium (TENSYMP) · doi:10.1109/tensymp54529.2022.9864495 · Cited by 6
“Among these instruments, the accelerometer (A), gyroscope (G), and magnetometer (M) are the most frequently employed by the scientific community [16].”
BackgroundMekruksavanich, S., Jantawong, P., Hnoohom, N., & Jitpattanakul, A. (2022) · International Conference on Big Data Analytics and Practices (IBDAP) · doi:10.1109/ibdap55587.2022.9907460 · Cited by 6
“We evaluated nine CNN-based and RNN-based models to determine their effectiveness in the HHAR challenge.”
MethodInfluentialMekruksavanich, S., Jantawong, P., Hnoohom, N., & Jitpattanakul, A. (2022) · Research, Invention, and Innovation Congress: Innovative Electricals and Electronics (RI2C) · doi:10.1109/ri2c56397.2022.9910287 · Cited by 6
“Among these sensors, accelerometers (A), gyroscopes (G), and magnetometers (M) are the most often utilized [13].”
Sensor based human action recognition and known public datasets a comprehensive survey
Jaber, T. A. (2023) · AIP conference proceedings · doi:10.1063/5.0119274 · Cited by 6
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
“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.”
BackgroundMethodAugmentation Robust Self-Supervised Learning for Human Activity Recognition
Xu, C., Li, Y., Lee, D., Park, D. H., Mao, H., Do, H., Chung, J., & Nair, D. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10096151 · Cited by 9
DOMINO: 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
Forensic detection of heterogeneous activity in data using deep learning methods
Nyarko, B. N. E., Wu, B., Zhou, J., Odoom, J., Danso, S. A., & Gyarteng, E. S. A. (2023) · Intelligent Systems with Applications · doi:10.1016/j.iswa.2023.200303 · Cited by 6
Domain adaptation of time series via contrastive learning with task-specific consistency
Wu, T., Chen, Q., Zhao, D., Wang, J., & Jiang, L. (2024) · Applied Intelligence · doi:10.1007/s10489-024-05799-y · Cited by 7
Multi-Channel Time Series Decomposition Network for Generalizable Sensor-Based Activity Recognition
Pan, J., Hu, Z., Zhang, L., & Cai, X. (2024) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2024.3480119 · Cited by 8
“Remarkably, when confronted with data derived from unobserved subjects, the researchers found that the model would experience a decrease in accuracy and identified some of the reasons as differences in hardware or wearing [15], [16].”
BackgroundTowards Adaptive Asynchronous Federated Learning for Human Activity Recognition
Gajanin, R., Danilenka, A., Morichetta, A., & Nastić, S. (2024) · International Conference on the Internet of Things (IoT) · doi:10.1145/3703790.3703795 · Cited by 8
WearRF-CLA: Continuous Location Authentication with Wrist Wearables and UHF RFID
Li, A., Li, J., Han, D., Zhang, Y., Li, T., & Zhang, Y. (2022) · ACM Asia Conference on Computer and Communications Security (ASIA CCS) · doi:10.1145/3488932.3517426 · Cited by 8
“• Heterogeneity human activity recognition (HHAR) dataset [38].”
BackgroundChoudhury, N. A., & Soni, B. (2022) · IEEE India Conference · doi:10.1109/indicon56171.2022.10039755 · Cited by 6
“HHAR [11] 6 9 A,G Waist, Pouch Uncontrolled”
Hoang, V.-H., & Tran, M. (2017) · International Conference on Computational Intelligence and Security (CIS) · doi:10.1109/cis.2017.00138 · Cited by 6
“A number of the variants named with format DSI-m-L (as described in Section IV-B) of our system is designed by changing the number of filters in every convolutional layer and/or modifying the Inception-like module for evaluation on UCI Human Activity Recognition dataset [5] to find the configuration that provides best…”
MethodFinding the Stars in the Fireworks: Deep Understanding of Motion Sensor Fingerprint
Liu, H., Li, X., Zhang, L., Xie, Y., Wu, Z., Dai, Q., Chen, G., & Wan, C. (2018) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom.2018.8486226 · Cited by 6
“[24] investigate mobile sensing heterogeneities for HAR (human activity recognition).”
BackgroundNguyen, H. D., Tran, K. P., Zeng, X., Koehl, L., & Tartare, G. (2020) · Springer series in reliability engineering · doi:10.1007/978-3-030-43412-0_13 · Cited by 7
Experimentation of Human Activity Recognition by Using Accelerometer Data Based on LSTM
Sa-nguannarm, P., Elbasani, E., Kim, B., Kim, E.-H., & Kim, J. (2020) · Lecture notes in electrical engineering · doi:10.1007/978-981-15-9309-3_12 · Cited by 6
Wilson, G., Doppa, J. R., & Cook, D. J. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2207.04367 · Cited by 7
“[27] only sample either accelerometer or gyroscope sensors, our dataset includes accelerometer, gyroscope, and location readings.”
BackgroundResultInfluentialShuffled Differentially Private Federated Learning for Time Series Data Analytics
Huang, C., Jiang, C., & Chen, Z. (2023) · IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea58696.2023.10241529 · Cited by 6
“3) HHAR [27] The Heterogeneity Human Activity Recognition (HHAR) dataset records sensor readings of activities from heterogeneous smartphones.”
BackgroundFlex: Fast, Accurate DNN Inference on Low-Cost Edges Using Heterogeneous Accelerator Execution
Sen, T., Shen, H., & Iyer, A. P. (2025) · European Conference on Computer Systems · doi:10.1145/3689031.3696067 · Cited by 5
Kriara, L., Dondelinger, F., Capezzuto, L., Bernasconi, C., Lipsmeier, F., Galati, A., & Lindemann, M. (2025) · Journal of Medical Internet Research · doi:10.2196/63090 · Cited by 5
Cemiloglu, A., & Akay, B. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110788 · Cited by 5
EasySpiro: 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].”
Hierarchical human activity recognition with fusion of audio and multiple inertial sensor modalities
Yılmaz, T. A., Yatbaz, H. Y., Ever, E., & Yazici, A. (2025) · Scientific Reports · doi:10.1038/s41598-025-29801-w · Cited by 3
A Scalable Deep Network for Graph Clustering via Personalized PageRank
Zhao, Y., Li, X., Zhu, Y., Li, J., Wang, S., & Jiang, B. (2022) · Applied Sciences · doi:10.3390/app12115502 · Cited by 5
Robust Machine Learning for Low-Power Wearable Devices: Challenges and Opportunities
Bhat, G., Hussein, D., & Yamin, N. (2023) · Springer eBooks · doi:10.1007/978-3-031-40677-5_3 · Cited by 5
Information-enhanced deep graph clustering network
Liu, H., Wei, J., Wu, Y., & Liang, C. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127992 · Cited by 5
A Virtual-Label-Based Hierarchical Domain Adaptation Method for Time-Series Classification
Yang, W., Cheng, L., Ragab, M., Wu, M., Pan, S. J., & Chen, Z. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3445879 · Cited by 5
GLA-DA: Global-Local Alignment Domain Adaptation for Multivariate Time Series
Tu, G., Li, D., Lin, B., Zheng, Z., & Ng, S.-K. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-5569-1_31 · Cited by 5
PALM: Personalized Active Learning for mmWave-Based Activity Recognition
Chiang, H.-C., Wu, Y., Li, G.-H., Shirmohammadi, S., & Hsu, C.-H. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3547487 · Cited by 5
“Inertial sensors, such as accelerators and gyroscopes [22], [23], [24], [25], [26], [27], have also been adopted for HAR, as they are already installed in modern smartphones, watches, and wristbands.”
Source-free time series domain adaptation with wavelet-based multi-scale temporal imputation
Zhong, Y., Zhou, W., & Tao, L. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.107428 · Cited by 5
Sadiq, F. I., Selamat, A., Ibrahim, R. B., & Krejcar, O. (2019) · Entropy · doi:10.3390/e21050487 · Cited by 5
MyDigitalFootprint: An extensive context dataset for pervasive computing applications at the edge
Campana, M. G., & Delmastro, F. (2020) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2020.101309 · Cited by 9
A temporal-attribute attention neural network for mixed frequency data forecasting
Wu, P., Yu, H. Z., Hu, F. R., & Xie, Y. (2022) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-022-01541-7 · Cited by 5
Federated Adaptation of Reservoirs via Intrinsic Plasticity
Caro, V. D., Gallicchio, C., & Bacciu, D. (2022) · European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN) · doi:10.14428/esann/2022.es2022-98 · Cited by 5
Community Detection Fusing Graph Attention Network
Guo, R., Zou, J., Bai, Q., Wang, W., & Chang, X. (2022) · Mathematics · doi:10.3390/math10214155 · Cited by 5
A knowledge-driven activity recognition framework for learning unknown activities
Jabla, R., Khemaja, M., Buendía, F., & Faïz, S. (2022) · Procedia Computer Science · doi:10.1016/j.procs.2022.09.245 · Cited by 5
Near Lossless Time Series Data Compression Methods using Statistics and Deviation
Agrawal, V., Kuldeep, G., & Dey, D. (2022) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshps56602.2022.10008693 · Cited by 5
“These are individual household electric power consumption (sampling once in every minute) [22], Heterogeneity Human Activity Recognition [20] - smartwatch accelerometer and smartwatch gyroscope and Home activity monitoring - MOX gas sensors resistance [21] (sampling once every second).”
BackgroundCross-Domain Similarity in Domain Adaptation for Human Activity Recognition
Kasim, S., & Sheppard, J. W. (2023) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn54540.2023.10191305 · Cited by 5
SelfAct: Personalized Activity Recognition Based on Self-Supervised and Active Learning
Arrotta, L., Civitarese, G., & Bettini, C. (2024) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-63989-0_19 · Cited by 6
Iwan, I., Yahya, B. N., & Lee, S. (2025) · Frontiers of Information Technology & Electronic Engineering · doi:10.1631/fitee.2400797 · Cited by 5
“How‐ ever, there is an odd phenomenon in HHAR.”
Influential
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.