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 201–300 of 800
Deep learning models for real-life human activity recognition from smartphone sensor data
Garcia-Gonzalez, D., Rivero, D., Fernández-Blanco, E., & Luaces, M. R. (2023) · Internet of Things · doi:10.1016/j.iot.2023.100925 · Cited by 41
FCBench: Cross-Domain Benchmarking of Lossless Compression for Floating-Point Data
Chen, X., Tian, J., Beaver, I., Freeman, C., Yan, Y., Wang, J., & Tao, D. (2024) · Proceedings of the VLDB Endowment · doi:10.14778/3648160.3648180 · Cited by 37
Deep clustering analysis via variational autoencoder with Gamma mixture latent embeddings
Guo, J., Fan, W., Amayri, M., & Bouguila, N. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106979 · Cited by 34
Zilelioglu, H., Khodabandelou, G., Chibani, A., & Amirat, Y. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3267243 · Cited by 32
“The framework is evaluated using a publicly available HAR dataset that includes a triaxial accelerometer and gyroscope readings [50].”
MethodYou Are Sensing, but Are You Biased?: A User Unaided Sensor Calibration Approach for Mobile Sensing
Grammenos, A., Mascolo, C., & Crowcroft, J. (2018) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3191743 · Cited by 27
“We use a dataset released alongside paper [36] which has records of accelerometer and gyroscope traces from multiple users and devices while performing dierent activities.”
InfluentialDos and Don'ts in Mobile Phone Sensing Middleware: Learning from a Large-Scale Experiment
Issarny, V., Mallet, V., Nguyen, K., Raverdy, P.-G., Rebhi, F., & Ventura, R. (2016) · International Middleware Conference · doi:10.1145/2988336.2988353 · Cited by 34
“While mobile phones increasingly embed sensors, the intrinsic performance of the sensors varies across mobile devices [41].”
BackgroundEk, S., Portet, F., Lalanda, P., & Vega, G. (2022) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2022.101714 · Cited by 35
“The Heterogeneity Human Activity Recognition (HHAR) dataset [12] accounts for 4.”
BackgroundDeep embedded clustering with distribution consistency preservation for attributed networks
Zheng, Y., Jia, C., Yu, J. J., & Li, X. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.109469 · Cited by 30
In-depth analysis of design & development for sensor-based human activity recognition system
Choudhury, N. A., & Soni, B. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-16423-5 · Cited by 30
Vuong, T. H., Doan, T., & Takasu, A. (2023) · Sensors · doi:10.3390/s23249721 · Cited by 33
AlMuhaideb, S., AlAbdulkarim, L., AlShahrani, D. M., AlDhubaib, H., & AlSadoun, D. E. (2024) · Sensors · doi:10.3390/s24165436 · Cited by 32
Karim, M. F. A., Khalid, S., Lee, S., Almutairi, S. S., Namoun, A., & Abohashrh, M. (2025) · IEEE Access · doi:10.1109/access.2025.3590073 · Cited by 36
“Stisen et al. [91] analyzed these discrepancies, highlighting the impact of mobile sensing heterogeneities on AR performance.”
Chen, K.-H., Hsu, Y.-W., Yang, J., & Jaw, F. (2017) · Instrumentation Science & Technology · doi:10.1080/10739149.2017.1363054 · Cited by 29
HierHAR: Sensor-Based Data-Driven Hierarchical Human Activity Recognition
Wang, A., Zhao, S., Zheng, C., Chen, H., Liu, L., & Chen, G. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.3023860 · Cited by 29
“Therefore, how to automate the recognition of activities remains a challenging yet rewarding topic that has attracted considerable attention from many fields and deserves further investigation [12].”
BackgroundTaghanaki, S. R., Rainbow, M. J., & Etemad, A. (2023) · IEEE Transactions on Human-Machine Systems · doi:10.1109/thms.2023.3303438 · Cited by 31
“2) We evaluate our method on three publicly available human activity datasets, MotionSense [21], human activities and postural transitions data (HAPT) [22], and heterogeneity human activity recognition (HHAR) [23].”
BackgroundMethodOnline nonparametric anomaly detection based on geometric entropy minimization
Yılmaz, Y. (2017) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit.2017.8007082 · Cited by 33
Investigating Enhancements to Contrastive Predictive Coding for Human Activity Recognition
Haresamudram, H., Essa, I., & Plötz, T. (2023) · 2023 IEEE International Conference on Pervasive Computing and Communications (PerCom) · doi:10.1109/percom56429.2023.10099197 · Cited by 27
Semi-Supervised Contrastive Learning for Human Activity Recognition
Liu, D., & Abdelzaher, T. (2021) · International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT) · doi:10.1109/dcoss52077.2021.00019 · Cited by 32
On-Board Feature Extraction from Acceleration Data for Activity Recognition
Elsts, A., McConville, R., Fafoutis, X., Twomey, N., Piechocki, R. J., Santos‐Rodríguez, R., & Craddock, I. J. (2018) · Explore Bristol Research · doi:10.5555/3234847.3234868 · Cited by 27
Motion2Vector: unsupervised learning in human activity recognition using wrist-sensing data
Bai, L., Yeung, C., Efstratiou, C., & Chikomo, M. (2019) · Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers · doi:10.1145/3341162.3349335 · Cited by 27
Gashi, S., Saeed, A., Vicini, A., Lascio, E. D., & Santini, S. (2021) · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION · doi:10.1145/3462244.3479921 · Cited by 28
“We refer to the CNN model pre-trained with the HHAR and UCI HAR dataset as S1 , S2 , respectively.”
MethodInfluentialSmart Sensors for Health Research and Improvement
Garatva, P., Terhorst, Y., Meßner, E.-M., Karlen, W., Pryss, R. C., & Baumeister, H. (2022) · Studies in neuroscience, psychology and behavioral economics · doi:10.1007/978-3-030-98546-2_23 · Cited by 27
Efficient human activity recognition with spatio-temporal spiking neural networks
Li, Y., Yin, R., Kim, Y., & Panda, P. (2023) · Frontiers in Neuroscience · doi:10.3389/fnins.2023.1233037 · Cited by 30
“We evaluate our SNNs on three widely-used HAR datasets (UCI-HAR Anguita et al., 2013, UniMB SHAR Micucci et al., 2017, HHAR Stisen et al., 2015) and compare them with ANN baselines.”
BackgroundYe, X., & Wang, K. I. (2024) · Pattern Recognition · doi:10.1016/j.patcog.2024.110811 · Cited by 34
Contrastive Self-Supervised Learning for Sensor-Based Human Activity Recognition: A Review
Chen, H., Gouin-Vallerand, C., Bouchard, K., Gaboury, S., Couture, M., Bier, N., & Giroux, S. (2024) · IEEE Access · doi:10.1109/access.2024.3480814 · Cited by 29
Stieger, S., & Reips, U. (2019) · Field Methods · doi:10.1177/1525822x18824281 · Cited by 36
Multidomain Multimodal Fusion for Human Action Recognition Using Inertial Sensors
Ahmad, Z., & Khan, N. (2019) · IEEE International Conference on Multimedia Big Data · doi:10.1109/bigmm.2019.00026 · Cited by 25
“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].”
MethodTuretta, C., Demrozi, F., & Pravadelli, G. (2024) · IEEE Access · doi:10.1109/access.2024.3496497 · Cited by 27
“1 into a single framework; • it defines precise data pre-processing steps, which minimize possible user errors; • it provides the user with baseline information about the most famous HAR datasets [14], [16], [17], [21], [22], [24], such that new approaches can be exhaustively compared with respect to existing results;…”
ResultInfluentialPAMS: A new position-aware multi-sensor dataset for human activity recognition using smartphones
Esfahani, P., & Malazi, H. T. (2017) · CSI International Symposium on Computer Architecture and Digital Systems (CADS) · doi:10.1109/cads.2017.8310680 · Cited by 28
“The researchers in [17] published a dataset that combined the smartphone and smartwatch sensors to recognize motion TABLE I: The specifications of human activity recognition datasets”
BackgroundHierarchical multi-view aggregation network for sensor-based human activity recognition
Zhang, X., Wong, Y., Kankanhalli, M., & Geng, W. (2019) · PLoS ONE · doi:10.1371/journal.pone.0221390 · Cited by 27
Exploring System Performance of Continual Learning for Mobile and Embedded Sensing Applications
Kwon, Y. D., Chauhan, J., Kumar, A., Hui, P., & Mascolo, C. (2021) · ePrints Soton (University of Southampton) · doi:10.17863/cam.81436 · Cited by 26
Federated Meta-Learning with Attention for Diversity-Aware Human Activity Recognition
Shen, Q., Feng, H., Song, R., Song, D., & Xu, H. (2023) · Sensors · doi:10.3390/s23031083 · Cited by 32
“We then perform data segmentation to split the data into 60 10 s windows, following similar settings and lengths as existing benchmark datasets [72,73].”
MethodUmbricht, D., Cheng, W., Lipsmeier, F., Bamdadian, A., & Lindemann, M. (2020) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2020.574375 · Cited by 27
Federated Learning with Heterogeneous Labels and Models for Mobile Activity MonitoringPreprint
Gudur, G. K., & Perepu, S. K. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.02539 · Cited by 28
“The Heterogeneity Human Activity Recognition dataset [22] consists of inertial data from four different mobile phones across nine users performing six daily activities: Biking, Sitting, Standing, Walking, Stairs-Up, Stairs-Down in heterogeneous conditions.”
AutoLife: Automatic Life Journaling with Smartphones and LLMs
Xu, H., Zeng, Z., Tong, P., Li, M., & Srivastava, M. B. (2025) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3770683 · Cited by 27
Supervised and Unsupervised Transfer Learning for Activity Recognition from Simple In-home Sensors
Inoue, S., & Pan, X. (2016) · EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services (MobiQuitous) · doi:10.1145/2994374.2994400 · Cited by 27
“Many reports related to activity recognition have appeared in the literature, such as the applications to sport [1, 20, 24], skill assess-men [23, 12, 29, 13], gait detection and assessmen [2, 17], medical use [16, 18, 30, 15], and the understanding of nursing activ-itie [19, 8].”
BackgroundLearning general model for activity recognition with limited labelled data
Wen, J., & Wang, Z. (2017) · Expert Systems with Applications · doi:10.1016/j.eswa.2017.01.002 · Cited by 25
HARNet: Towards On-Device Incremental Learning using Deep Ensembles on Constrained Devices
Sundaramoorthy, P., Gudur, G. K., Moorthy, M. R., Bhandari, R. N., & Vijayaraghavan, V. (2018) · International Workshop on Embedded and Mobile Deep Learning (EMDL) · doi:10.1145/3212725.3212728 · Cited by 23
“Testing in this mode yields an F1-score of 0.80 using the accelerometer data alone which is higher than the F1-scores presented in [20] and [17], which use data from both accelerometer and gyroscope.”
BackgroundMethodInfluentialHart, A., Reis, D., Prestele, E., & Jacobson, N. C. (2022) · Journal of Medical Internet Research · doi:10.2196/34015 · Cited by 22
“Another explanation could be that random variation between participants (eg, sensor readings that differed by device [44,65]) might have concealed relevant variance.”
BackgroundStieger, S., Lewetz, D., & Reips, U. (2017) · Behavior Research Methods · doi:10.3758/s13428-017-0991-6 · Cited by 22
Estimation of Blood Alcohol Concentration From Smartphone Gait Data Using Neural Networks
Li, R., Balakrishnan, G. P., Nie, J., Li, Y., Agu, E., Grimone, K., Herman, D. S., Abrantes, A. M., & Stein, M. D. (2021) · IEEE Access · doi:10.1109/access.2021.3054515 · Cited by 24
“Fourth, smartphone sensors manufactured by different companies have been shown to generate significantly different readings (as much as 30% difference) when monitoring the same stimuli [35].”
BackgroundA closed-loop deep learning architecture for robust activity recognition using wearable sensors
Saeedi, R., Norgaard, S., & Gebremedhin, A. H. (2017) · 2017 IEEE International Conference on Big Data (Big Data) · doi:10.1109/bigdata.2017.8257960 · Cited by 20
Faridee, A. Z. M., Ramamurthy, S. R., Hossain, H. M. S., & Roy, N. (2018) · IEEE Workshop on Mobile Computing Systems and Applications (WMCSA) · doi:10.1145/3177102.3177116 · Cited by 22
“The use of heterogeneous sensors pose challenges associated with multiple sensors data stream synchronization, sensor biases, and sampling rate instability [22], which are discussed in detail in section 4.”
BackgroundMethodInfluentialYao, S., Zhao, Y., Hu, S., & Abdelzaher, T. (2018) · International Workshop on Embedded and Mobile Deep Learning (EMDL) · doi:10.1145/3212725.3212729 · Cited by 28
Confidence-based Deep Multimodal Fusion for Activity Recognition
Choi, J. H., & Lee, J. (2018) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3267305.3267522 · Cited by 22
“, OPPORTUNITY [2], HHAR [22], and Sussex-Huawei LocomotionTransportation (SHL) [8]).”
BackgroundA closer look at quality-aware runtime assessment of sensing models in multi-device environments
Min, C., Montanari, A., Mathur, A., & Kawsar, F. (2019) · ACM Conference on Embedded Networked Sensor Systems (SenSys) · doi:10.1145/3356250.3360043 · Cited by 30
“• Device Variability: Different devices have different sensing quality due to their heterogeneity [15, 34].”
BackgroundCASA: Clustered Federated Learning with Asynchronous Clients
Liu, B., Ma, Y., Zhou, Z., Shi, Y., Li, S., & Tong, Y. (2024) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3637528.3671979 · Cited by 42
Large Language Model-guided Semantic Alignment for Human Activity Recognition
Yan, H., Tan, H., Ding, Y. C., Zhou, P., Namboodiri, V., & Yang, Y. (2025) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3770652 · Cited by 31
“For cross-dataset HAR performance, we use accuracy to measure the correctness of the classification results for the four selected activities.”
A Robust Distributed Big Data Clustering-based on Adaptive Density Partitioning using Apache Spark
Hosseini, B., & Kiani, K. (2018) · Symmetry · doi:10.3390/sym10080342 · Cited by 24
“HAR is the third dataset used in this research which is a human activity recognition dataset used for clustering [56].”
MethodAT2GRU: A Human Emotion Recognition Model With Mitigated Device Heterogeneity
Khan, P., Ranjan, P., & Kumar, S. (2021) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2021.3114123 · Cited by 25
“This can slow down the training process and/or lead to inconsistency in the classification results thereby impacting on the reliability and versatility of the classification models [17], [18].”
BackgroundMethodInfluentialAdaptive graph convolutional clustering network with optimal probabilistic graph
Zhao, J., Guo, J., Sun, Y., Gao, J., Wang, S., & Yin, B. (2022) · Neural Networks · doi:10.1016/j.neunet.2022.09.017 · Cited by 24
Bursa, S. Ö., İncel, Ö. D., & Alptekin, G. I. (2023) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2023.108777 · Cited by 21
DAPPER: Label-Free Performance Estimation after Personalization for Heterogeneous Mobile Sensing
Gong, T., Kim, Y., Orzikulova, A., Liu, Y., Hwang, S. J., Shin, J., & Lee, S.-J. (2023) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3596256 · Cited by 23
A context‐awareness model for activity recognition in robot‐assisted scenarios
Rodríguez-Lera, F. J., Martín, F., Guerrero‐Higueras, Á. M., & Olivera, V. M. (2019) · Expert Systems · doi:10.1111/exsy.12481 · Cited by 21
“This research uses the information obtained in other researches (Stisen et al., 2015; Shoaib, Bosch, Incel, Scholten, & Havinga, 2016).”
MethodCycleSense: Detecting near miss incidents in bicycle traffic from mobile motion sensors
Karakaya, A.-S., Ritter, T., Bießmann, F., & Bermbach, D. (2023) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2023.101779 · Cited by 23
“Stisen et al. [31] have shown that there is major heterogeneity when it comes to the accuracy of sensor readings.”
BackgroundAn early characterisation of wearing variability on motion signals for wearables
Min, C., Mathur, A., Montanari, A., & Kawsar, F. (2019) · International Symposium on Wearable Computers · doi:10.1145/3341163.3347716 · Cited by 21
Mavropoulos, T., Symeonidis, S., Tsanousa, A., Giannakeris, P., Rousi, M., Kamateri, E., Μεδίτσκος, Γ., Ioannidis, K., Vrochidis, S., & Kompatsiaris, I. Y. (2021) · Journal of Intelligent Information Systems · doi:10.1007/s10844-021-00648-7 · Cited by 22
“For the wearable sensor analysis application, we used the Heterogeneity Human Activity Recognition (HHAR) dataset (Stisen et al. 2015) that contains accelerometer and gyroscope recordings from smartphones and smartwatches.”
MethodMultimodal Neural Network Acceleration on a Hybrid CPU-FPGA Architecture: A Case Study
Ajili, M. T., & Hara–Azumi, Y. (2022) · IEEE Access · doi:10.1109/access.2022.3144977 · Cited by 24
“Additionally, each of these techniques has their own drawbacks; RF and DT can be computationally complex, SVM is not well suited for noisy data, RBMs are difficult and slow to train, and DNNs and CNNs are not efficient for capturing temporal relationships.”
MethodInfluentialTowards a multimodal human activity dataset for healthcare
Hu, M., Luo, M., Huang, M., Meng, W., Xiong, B., Yang, X., & Sang, J. (2022) · Multimedia Systems · doi:10.1007/s00530-021-00875-6 · Cited by 21
Activity recognition in wearables using adversarial multi-source domain adaptation
Chakma, A., Faridee, A. Z. M., Khan, M. A. A. H., & Roy, N. (2020) · Smart Health · doi:10.1016/j.smhl.2020.100174 · Cited by 28
Li, J., Kang, P., Tan, T., & Shull, P. B. (2021) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2021.3118717 · Cited by 24
AugToAct: scaling complex human activity recognition with few labels
Faridee, A. Z. M., Khan, M. A. A. H., Pathak, N., & Roy, N. (2019) · Proceedings of the 16th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services · doi:10.1145/3360774.3360831 · Cited by 17
Triaxial Accelerometer-Based Falls and Activities of Daily Life Detection Using Machine Learning
Althobaiti, T., Katsigiannis, S., & Ramzan, N. (2020) · Sensors · doi:10.3390/s20133777 · Cited by 24
“HHAR [56] A+G Smartphones, Smartwatches Waist, Arm 25–30 9 0/54 0 6”
TS2ACT: Few-Shot Human Activity Sensing with Cross-Modal Co-Learning
Xia, K., Li, W., Gan, S., & Lu, S. (2023) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3631445 · Cited by 19
FusedAR: Energy-Positive Human Activity Recognition Using Kinetic and Solar Signal Fusion
Sandhu, M. M., Khalifa, S., Geissdoerfer, K., Jurdak, R., Portmann, M., & Kusý, B. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3268687 · Cited by 23
“2-s segments [37], which is a typical time duration required”
BackgroundHierarchical Residual Encoding for Multiresolution Time Series Compression
Barbarioli, B., Mersy, G., Sintos, S., & Krishnan, S. (2023) · Proceedings of the ACM on Management of Data · doi:10.1145/3588953 · Cited by 19
“Our data sets are from four different projects within the UCI repository and in each case we used a subset of the entire data as described: Heterogeneity activity recognition data set [42], from which we used four different data sets 53.”
MethodEffective Heterogeneous Federated Learning via Efficient Hypernetwork-based Weight Generation
Shin, Y., Lee, K., Lee, S., Choi, Y. R., Kim, H., & Ko, J. (2024) · ACM Conference on Embedded Networked Sensor Systems (SenSys) · doi:10.1145/3666025.3699326 · Cited by 33
“Smart devices such as smartphones, smartwatches, and wearable sensors capture high-fidelity data, enabling robust machine learning model development [56, 65].”
Transfer learning algorithms for autonomous reconfiguration of wearable systems
Saeedi, R., Ghasemzadeh, H. G., & Gebremedhin, A. H. (2016) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2016.7840648 · Cited by 20
An Active Sleep Monitoring Framework Using Wearables
Hossain, H. M. S., Ramamurthy, S. R., Khan, M. A. A. H., & Roy, N. (2018) · ACM Transactions on Interactive Intelligent Systems · doi:10.1145/3185516 · Cited by 22
“The major type of heterogeneity that is evident is the different sampling frequencies of these devices (Stisen et al. 2015).”
BackgroundCache-oblivious High-performance Similarity Join
Perdacher, M., Plant, C., & Böhm, C. (2019) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/3299869.3319859 · Cited by 19
harAGE: A Novel Multimodal Smartwatch-based Dataset for Human Activity Recognition
Mallol-Ragolta, A., Semertzidou, A., Pateraki, M., & Schuller, B. W. (2021) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg52635.2021.9666947 · Cited by 22
Dataset of acceleration signals recorded while performing activities of daily living
Climent-Pérez, P., Muñoz-Antón, Á. M., Poli, A., Spinsante, S., & Flórez‐Revuelta, F. (2022) · Data in Brief · doi:10.1016/j.dib.2022.107896 · Cited by 19
LLM4HAR: Generalizable On-device Human Activity Recognition with Pretrained LLMs
Hong, Z., Song, Y., Li, Z., Yu, A., Zhong, S., Ding, Y. C., He, T., & Zhang, D. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3711896.3737226 · Cited by 35
A Survey on Understanding and Representing Privacy Requirements in the Internet-of-Things
Ogunniye, G., & Kökciyan, N. (2023) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.14000 · Cited by 22
“For instance, human activity recognition (HAR) system (Stisen et al., 2015) which is a system for interpreting human motion (e.g. gestures or behaviors that are recorded by sensors) has been deployed in a wide range of domains, including smart homes (Pham & Olivier, 2009), healthcare (Taylor et…”
BackgroundCombining Public Human Activity Recognition Datasets to Mitigate Labeled Data Scarcity
Presotto, R., Ek, S., Civitarese, G., Portet, F., Lalanda, P., & Bettini, C. (2023) · IEEE International Conference on Smart Computing · doi:10.1109/smartcomp58114.2023.00022 · Cited by 25
Deep Learning in the Recognition of Activities of Daily Living Using Smartwatch Data
Cavalcante, A. F., Kunst, V. H. D. L., Chaves, T., de Souza, J. D. T., Ribeiro, I. M., Quintino, J. P., da Silva, F. Q. B., Santos, A. L. M., Teichrieb, V., & Gama, A. E. F. D. (2023) · Sensors · doi:10.3390/s23177493 · Cited by 22
Liu, Y., Li, D., Wang, J., Li, B., & Hang, B. (2024) · Information Processing & Management · doi:10.1016/j.ipm.2023.103638 · Cited by 22
MESEN: Exploit Multimodal Data to Design Unimodal Human Activity Recognition with Few Labels
Xu, L., Gu, C., Tan, R., He, S., & Chen, J. (2023) · ACM Conference on Embedded Networked Sensor Systems (SenSys) · doi:10.1145/3625687.3625782 · Cited by 26
“HHAR dataset [35].”
Unsupervised Deep Embedding for Fuzzy Clustering
Zhang, R., Duan, Y., Nie, F., Wang, R., & Li, X. (2024) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2024.3462545 · Cited by 20
“3 visualizes some samples of experimental datasets. a) HHAR [46]: The sensor dataset known as heterogeneity human activity recognition comprises 12 099 samples from smartphones and smartwatches.”
Activity recognition in manual manufacturing: Detecting screwing processes from sensor data
Günther, L. C., Kärcher, S., & Bauernhansl, T. (2019) · Procedia CIRP · doi:10.1016/j.procir.2019.03.288 · Cited by 16
Finding the Stars in the Fireworks: Deep Understanding of Motion Sensor Fingerprint
Li, X., Liu, H., Zhang, L., Wu, Z., Xie, Y., Chen, G., Wan, C., & Liang, Z. (2019) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2019.2933269 · Cited by 18
“[32] investigate mobile sensing heterogeneities for HAR (human activity recognition).”
Fomichev, M., Hesse, J., Almon, L., Lippert, T., Han, J. Y., & Hollick, M. (2021) · International Conference on Mobile Systems, Applications, and Services · doi:10.1145/3458864.3467883 · Cited by 18
STranGAN: Adversarially-learnt Spatial Transformer for scalable human activity recognition
Faridee, A. Z. M., Chakma, A., Misra, A., & Roy, N. (2021) · Smart Health · doi:10.1016/j.smhl.2021.100226 · Cited by 21
LabelForest: Non-Parametric Semi-Supervised Learning for Activity Recognition
Ma, Y., & Ghasemzadeh, H. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33014520 · Cited by 19
“The upper bound is computed as mentioned in Section 5, and the overall accuracy appears to be significantly lower on the Phone dataset than that of the other two datasets, where the average accuracy is 86.3% for the Phone dataset, 97.1% for the HART dataset and 96.9% for the SmartSock dataset.”
BackgroundInfluentialA Weighted Late Fusion Framework for Recognizing Human Activity from Wearable Sensors
Tsanousa, A., Μεδίτσκος, Γ., Vrochidis, S., & Kompatsiaris, I. Y. (2019) · International Conference on Information, Intelligence, Systems & Applications (IISA) · doi:10.1109/iisa.2019.8900725 · Cited by 22
Earthquake Early Warning and Beyond
Kong, Q., Lv, Q., & Allen, R. M. (2019) · IEEE Workshop on Mobile Computing Systems and Applications (WMCSA) · doi:10.1145/3301293.3302377 · Cited by 18
“bile devicesandotherlow-costsensorscanprovideinsightstotheMyShake project. [6] investigated performance of several low-cost accelerometers in terms of recording motions in the laboratory environment. [21] evaluated sensor biases, sampling rate heterogeneity and instability using 36 different devices, as well as their…”
Warehouse LSTM-SVM-Based ECG Data Classification With Mitigated Device Heterogeneity
Khan, P., Ranjan, P., Singh, Y., & Kumar, S. (2021) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2021.3116428 · Cited by 17
Kumar, P., & Suresh, S. (2022) · Procedia Computer Science · doi:10.1016/j.procs.2022.10.208 · Cited by 24
Self-supervised graph autoencoder with redundancy reduction for community detection
Wang, X., Shen, G., Zhang, Z., Lai, S., Zhu, S., Chen, Y., & Quan, D. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127703 · Cited by 17
Modality aware contrastive learning for multimodal human activity recognition
Dixon, S., Yao, L., & Davidson, R. (2024) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.8020 · Cited by 19
Alam, M. A. U., Roy, N., Gangopadhyay, A., & Galik, E. M. (2016) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2016.06.015 · Cited by 18
SemLinker: automating big data integration for casual users
Alrehamy, H., & Walker, C. (2018) · Journal Of Big Data · doi:10.1186/s40537-018-0123-x · Cited by 21
“The collection include 3 datasets that contain sensor (accelerometer and gyroscope) streams generated by smart phone and smart watches carried by human subjects and are collected from two human activity recognition experiments [49, 50].”
BackgroundA Signal-Level Transfer Learning Framework for Autonomous Reconfiguration of Wearable Systems
Saeedi, R., & Gebremedhin, A. H. (2018) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2018.2878673 · Cited by 18
“investigate sensor heterogeneity in activity recognition systems [37].”
BackgroundMethodSmartphone Zombie Context Awareness at Crossroads: A Multi-Source Information Fusion Approach
Zhuang, Y., & Fang, Z. (2020) · IEEE Access · doi:10.1109/access.2020.2998129 · Cited by 17
“Meanwhile, pedestrian’s intermediate transition postures would produce biomechanical effects, causing user-induced uncertainties in sensor data [65].”
BackgroundDiamantaris, M., Marcantoni, F., Ioannidis, S., & Polakis, J. (2020) · ACM Transactions on Privacy and Security · doi:10.1145/3403947 · Cited by 22
HarMI: Human Activity Recognition Via Multi-Modality Incremental Learning
Zhang, X., Yu, H., Yang, Y., Gu, J., Li, Y., Zhuang, F., Yu, D., & Ren, Z. (2021) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2021.3085602 · Cited by 24
Moccia, S., Solbiati, S., Khornegah, M., Bossi, F., & Caiani, E. G. (2022) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2022.106753 · Cited by 20
Energy- and Mobility-Aware Scheduling for Perpetual Trajectory Tracking
Sommer, P., Geissdoerfer, K., Jurdak, R., Kusý, B., Liu, J., Zhao, K., McKeown, A., & Westcott, D. A. (2019) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2019.2895336 · Cited by 17
“Note that all folds after the split are still consecutive samples to avoid the over-estimation effect mentioned in [34].”
BackgroundToward Projected Clustering With Aggregated Mapping
Zhang, H., Zhu, Y., & Li, X. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3274989 · Cited by 18
“The experiments are conducted on totally 12 datasets, including Heterogeneity Human Activity Recognition ( HHAR [51]) dataset, 20NEWS dataset, 5 UCI datasets ( Isolet , Segment , Breast , Control , and Palm ) [52] and 5 image datasets ( COIL20 [53], USPS [54], UMIST [55], MSRA [56], and test set of…”
MethodMulti-modal data clustering using deep learning: A systematic review
Raya, S. P., Orabi, M., Afyouni, I., & Aghbari, Z. A. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128348 · Cited by 18
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.