Datasets for Human Activity Recognition: A Comparative Analysis

Authors

DOI:

https://doi.org/10.47756/aihc.y10i1.198

Keywords:

Human Activity Recognition, Human–Computer Interaction, Public Datasets, Data Imbalance

Abstract

Human activity recognition is a key area in human–computer interaction because it enables systems to understand people’s actions and respond through implicit interaction, without requiring direct commands. This article presents a comparative analysis of six widely used public datasets, considering factors such as participant diversity, variety of activities, types of sensors, and capture conditions. The results show that although these datasets have driven the development of more accurate models, they still present limitations related to the lack of diversity and class imbalance, which affects the generalization ability of systems in real-world contexts. The need to design more inclusive and representative datasets that reflect the complexity of human interaction and support the development of fairer, more robust, and more adaptive human activity recognition systems is highlighted.

Downloads

Download data is not yet available.

Author Biographies

Luis Felipe Beltrán Mercado, Instituto Tecnológico de Sonora (ITSON)

He holds a Master's degree in Engineering Sciences, specializing in Control and Systems, and a degree in Mechatronics Engineering from the Technological Institute of Sonora (ITSON). He is currently pursuing a PhD in Engineering Sciences, with a specialization in Computer Science, at ITSON, where he focuses on human activity recognition through deep learning models and the analysis of large volumes of data. His areas of interest include signal processing, simulations, and the development of advanced tools in Artificial Intelligence.

Jessica Beltrán Márquez, Centro de Investigación en Matemáticas Aplicadas de la Universidad Autonoma de Coahuila

I have a PhD degree in Computer Science from CICESE, México. As part of my doctoral dissertation, I worked with auditory information to infer the context of older adults. My overall research goal is to advance research in activity and behavior estimation to support the development of pervasive applications, particularly in the domain of healthcare. I am interested in Machine Learning, Signal Processing, Feature Extraction, Context-Aware Computing and Information Retrieval. I received M.Sc. in Computer Science from CICESE, México. As part of my master’s thesis, I worked with image processing and classification for identifying tattoos as part of a soft biometric application. I received my Bachelor’s degree in Electronic Engineering at Sonora Institute of Technology, México. Currently, I am working as Researcher Professor at the Research Center of Applied Math (CIMA) from the Autonomus University of Coahuila (UAdeC).

Luis A. Castro, Instituto Tecnológico de Sonora (ITSON)

Luis Castro works as a full professor at the Dept. of Computing and Design at the Sonora Institute of Technology (ITSON), Mexico. He holds a Ph.D. in Informatics from the University of Manchester, UK. Castro's main research interests are Community Informatics; Intelligent Systems; Human-Computer Interaction; Interaction Design; and Ubiquitous and Mobile Computing. Dr. Castro has participated in several projects aimed at designing technology for vulnerable populations. Dr. Castro is a professional member of the ACM and a member of the National System of Researchers from the National Council for Science and Technology in Mexico (SNI-CONACYT). He is the former president of the Mexican Association on Human-Computer Interaction (AMexIHC), the former president of the Society of Mexican Students in the United Kingdom, and a former member of the board of the Mexican Association on Computer Science.

References

Ann, O. C. and Theng, L. B. 2014. Human activity recognition: A review. In 2014 IEEE International Conference on Control System, Computing and Engineering (ICCSCE 2014), 389–393. https://doi.org/10.1109/ICCSCE.2014.7072750 DOI: https://doi.org/10.1109/ICCSCE.2014.7072750

Khowaja, S. A., Yahya, B. N., and Lee, S.-L. 2020. CAPHAR: context-aware personalized human activity recognition using associative learning in smart environments. Human-centric Computing and Information Sciences 10, 35. https://doi.org/10.1186/s13673-020-00240-y DOI: https://doi.org/10.1186/s13673-020-00240-y

Ye, X., Sakurai, K., Nair, N.-K. C., and Wang, K. I.-K. 2024. Machine learning techniques for sensor-based human activity recognition with data heterogeneity—A review. Sensors 24, 7975. https://doi.org/10.3390/s24247975 DOI: https://doi.org/10.3390/s24247975

De-La-Hoz-Franco, E., Ariza-Colpas, P., Quero, J. M., and Espinilla, M. 2018. Sensor-based datasets for human activity recognition —a systematic review of literature. IEEE Access 6, 59192–59210. https://doi.org/10.1109/ACCESS.2018.2873502 DOI: https://doi.org/10.1109/ACCESS.2018.2873502

Anguita, D., Ghio, A., Oneto, L., Parra, X., and Reyes-Ortiz, J. L. 2013. A public domain dataset for human activity recognition using smartphones. In Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), 437–442. https://doi.org/10.3390/s20082200 DOI: https://doi.org/10.3390/s20082200

Reiss, A. and Stricker, D. 2012. Introducing a new benchmarked dataset for activity monitoring. In 2012 16th International Symposium on Wearable Computers, 108–109. https://doi.org/10.1109/ISWC.2012.13 DOI: https://doi.org/10.1109/ISWC.2012.13

Roggen, D. et al. 2010. Collecting complex activity datasets in highly rich networked sensor environments. In 2010 Seventh International Conference on Networked Sensing Systems (INSS), 233–240. https://doi.org/10.1109/INSS.2010.5573462 DOI: https://doi.org/10.1109/INSS.2010.5573462

Sztyler, T. and Stuckenschmidt, H. 2016. On-body localization of wearable devices: An investigation of position-aware activity recognition. In 2016 IEEE International Conference on Pervasive Computing and Communications (PerCom), 1–9. https://doi.org/10.1109/PERCOM.2016.7456521 DOI: https://doi.org/10.1109/PERCOM.2016.7456521

Dentamaro, V., Gattulli, V., Impedovo, D., and Manca, F. 2024. Human activity recognition with smartphone-integrated sensors: A survey. Expert Systems with Applications 246, 123143. https://doi.org/10.1016/j.eswa.2024.123143 DOI: https://doi.org/10.1016/j.eswa.2024.123143

Lopez-Nava, I. H., Valentín-Coronado, L. M., Garcia-Constantino, M., and Favela, J. 2020. Gait activity classification on unbalanced data from inertial sensors using shallow and deep learning. Sensors 20, 4756. https://doi.org/10.3390/s20174756 DOI: https://doi.org/10.3390/s20174756

Cruciani, F., Cleland, I., Nugent, C., McCullagh, P., Synnes, K. and Hallberg, J. Automatic annotation for human activity recognition in free living using a smartphone. Sensors 18, 7 (2018), Article 2203. https://doi.org/10.3390/s18072203 DOI: https://doi.org/10.3390/s18072203

Zhang, J., Li, J. and Wang, W. A class-imbalanced deep learning fall detection algorithm using wearable sensors. Sensors 21, 19 (2021), Article 6511. https://doi.org/10.3390/s21196511 DOI: https://doi.org/10.3390/s21196511

Owusu-Adjei, M., Ben Hayfron-Acquah, J., Frimpong, T. and Abdul-Salaam, G. Imbalanced class distribution and performance evaluation metrics: A systematic review of prediction accuracy for determining model performance in healthcare systems. PLOS Digital Health 2, 11 (2023), e0000290. https://doi.org/10.1371/journal.pdig.0000290 DOI: https://doi.org/10.1371/journal.pdig.0000290

Bulling, A., Blanke, U. and Schiele, B. A tutorial on human activity recognition using body-worn inertial sensors. ACM Computing Surveys 46, 3 (2014), Article 33. https://doi.org/10.1145/2499621 DOI: https://doi.org/10.1145/2499621

Cheng, L., Guan, Y., Zhu, K. and Li, Y. Recognition of human activities using machine learning methods with wearable sensors. In Proc. IEEE 7th Annual Computing and Communication Workshop and Conference (CCWC 2017) (2017), 1–7. https://doi.org/10.1109/CCWC.2017.7868369 DOI: https://doi.org/10.1109/CCWC.2017.7868369

Gu, F., Chung, M.-H., Chignell, M., Valaee, S., Zhou, B. and Liu, X. A survey on deep learning for human activity recognition. ACM Computing Surveys 54, 8 (2021), Article 177, 1–34. https://doi.org/10.1145/3472290 DOI: https://doi.org/10.1145/3472290

Dang, L.M., Min, K., Wang, H., Piran, M.J., Lee, C.H. and Moon, H. Sensor-based and vision-based human activity recognition: A comprehensive survey. Pattern Recognition 108 (2020), Article 107561. https://doi.org/10.1016/j.patcog.2020.107561 DOI: https://doi.org/10.1016/j.patcog.2020.107561

Logacjov, A., Bach, K., Kongsvold, A., Bårdstu, H.B. and Mork, P.J. HARTH: A human activity recognition dataset for machine learning. Sensors 21, 23 (2021), Article 7853. https://doi.org/10.3390/s21237853 DOI: https://doi.org/10.3390/s21237853

Baños, O., Damas, M., Pomares, H., Rojas, I., Tóth, M.A. and Amft, O. A benchmark dataset to evaluate sensor displacement in activity recognition. In Proc. ACM Conference on Ubiquitous Computing (UbiComp 2012) (2012), 1026–1035. https://doi.org/10.1145/2370216.2370437 DOI: https://doi.org/10.1145/2370216.2370437

Benos, L., Tsaopoulos, D., Tagarakis, A.C., Kateris, D. and Bochtis, D. Optimal sensor placement and multimodal fusion for human activity recognition in agricultural tasks. Applied Sciences 14, 18 (2024), Article 8520. https://doi.org/10.3390/app14188520 DOI: https://doi.org/10.3390/app14188520

Reyes-Ortiz, J.-L., Oneto, L., Samà, A., Parra, X. and Anguita, D. Transition-aware human activity recognition using smartphones. Neurocomputing 171 (2016), 754–767. https://doi.org/10.1016/j.neucom.2015.07.085 DOI: https://doi.org/10.1016/j.neucom.2015.07.085

Lara, O.D. and Labrador, M.A. A survey on human activity recognition using wearable sensors. IEEE Communications Surveys & Tutorials 15, 3 (2013), 1192–1209. https://doi.org/10.1109/SURV.2012.110112.00192 DOI: https://doi.org/10.1109/SURV.2012.110112.00192

Stisen, A. et al. Smart devices are different: Assessing and mitigating mobile sensing heterogeneities for activity recognition. In Proc. 13th ACM Conference on Embedded Networked Sensor Systems (SenSys 2015) (2015), 127–140. https://doi.org/10.1145/2809695.2809718 DOI: https://doi.org/10.1145/2809695.2809718

Jimale, A.O. and Mohd Noor, M.H. Subject variability in sensor-based activity recognition. Journal of Ambient Intelligence and Humanized Computing 14, 4 (2023), 3261–3274. https://doi.org/10.1007/s12652-021-03465-6 DOI: https://doi.org/10.1007/s12652-021-03465-6

Duggal, R., Freitas, S., Dhamnani, S., Chau, D.H. and Sun, J. HAR: Hardness aware reweighting for imbalanced datasets. In Proc. IEEE International Conference on Big Data (Big Data 2021) (2021), 735–745. https://doi.org/10.1109/BigData52589.2021.9671807 DOI: https://doi.org/10.1109/BigData52589.2021.9671807

Alharbi, F., Ouarbya, L. and Ward, J.A. Comparing sampling strategies for tackling imbalanced data in human activity recognition. Sensors 22, 4 (2022), Article 1373. https://doi.org/10.3390/s22041373 DOI: https://doi.org/10.3390/s22041373

Varga, D. Exposing data leakage in Wi-Fi CSI-based human action recognition: A critical analysis. Inventions 9, 4 (2024), Article 90. https://doi.org/10.3390/inventions9040090 DOI: https://doi.org/10.3390/inventions9040090

Dua, N., Singh, S.N., Challa, S.K., Semwal, V.B. and Sai Kumar, M.L.S. A survey on human activity recognition using deep learning techniques and wearable sensor data. In Proc. International Conference on Machine Learning, Image Processing, Network Security and Data Sciences (2022), 52–71. https://doi.org/10.1007/978-3-031-24352-3_5 DOI: https://doi.org/10.1007/978-3-031-24352-3_5

Wang, L., Gjoreski, H., Murao, K., Okita, T. and Roggen, D. Summary of the Sussex-Huawei locomotion-transportation recognition challenge. In Proc. ACM International Joint Conference on Pervasive and Ubiquitous Computing and Wearable Computers (UbiComp 2018) (2018), 1521–1530. https://doi.org/10.1145/3267305.3267519 DOI: https://doi.org/10.1145/3267305.3267519

Plötz, T., Hammerla, N.Y. and Olivier, P. Feature learning for activity recognition in ubiquitous computing. In Proc. 22nd International Joint Conference on Artificial Intelligence (IJCAI 2011) (2011), 1729–1734. https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-290

Bächlin, M. et al. Wearable assistant for Parkinson’s disease patients with the freezing of gait symptom. IEEE Transactions on Information Technology in Biomedicine 14, 2 (2010), 436–446. https://doi.org/10.1109/TITB.2009.2036165 DOI: https://doi.org/10.1109/TITB.2009.2036165

Baños, O., Garcia, R., Holgado-Terriza, J.A., Damas, M., Pomares, H. and Rojas, I. mHealthDroid: A novel framework for agile development of mobile health applications. In Proc. 6th International Workshop on Ambient Assisted Living and Active Ageing (2014), 91–98. https://doi.org/10.1007/978-3-319-13105-4_14 DOI: https://doi.org/10.1007/978-3-319-13105-4_14

Anguita, D., Ghio, A., Oneto, L., Parra, X. and Reyes-Ortiz, J.L. Human activity recognition on smartphones using a multiclass hardware-friendly support vector machine. In Proc. International Workshop on Ambient Assisted Living (2012), 216–223. https://doi.org/10.1007/978-3-642-35395-6_30 DOI: https://doi.org/10.1007/978-3-642-35395-6_30

Vavoulas, G., Chatzaki, C., Malliotakis, T., Pediaditis, M. and Tsiknakis, M. MobiAct Dataset: Recognition of Activities of Daily Living and Fall Detection Using Smartphones. In Proc. International Conference on Information and Communication Technologies for Ageing Well and e-Health (2016), 143–151. https://doi.org/10.5220/0005792401430151 DOI: https://doi.org/10.5220/0005792401430151

Malekzadeh, M., Clegg, R.G., Cavallaro, A. and Haddadi, H. Mobile sensor data anonymization. In Proc. International Conference on Internet of Things Design and Implementation (IoTDI 2018) (2018), 49–58. https://doi.org/10.1145/3302505.3310068 DOI: https://doi.org/10.1145/3302505.3310068

Sikder, N. and Nahid, A.-A. KU-HAR: An open dataset for heterogeneous human activity recognition. Pattern Recognition Letters 146 (2021), 46–54. https://doi.org/10.1016/j.patrec.2021.02.024 DOI: https://doi.org/10.1016/j.patrec.2021.02.024

Weiss, G.M. WISDM smartphone and smartwatch activity and biometrics dataset. UCI Machine Learning Repository (2019). https://doi.org/10.24432/C5HK59

Alam, G., McChesney, I., Nicholl, P. and Rafferty, J. Open datasets in human activity recognition research—Issues and challenges: A review. IEEE Sensors Journal 23, 22 (2023), 26952–26980. https://doi.org/10.1109/JSEN.2023.3317645 DOI: https://doi.org/10.1109/JSEN.2023.3317645

Ali, A., Anam, S. and Ahmed, M.M. Shannon entropy in artificial intelligence and its applications based on information theory. Journal of Applied Emerging Sciences 13, 1 (2023), 9–17.

Hayat, A., Morgado-Dias, F., Bhuyan, B.P. and Tomar, R. Human activity recognition for elderly people using machine and deep learning approaches. Information 13, 6 (2022), Article 275. https://doi.org/10.3390/info13060275 DOI: https://doi.org/10.3390/info13060275

Magurran, A.E. Measuring biological diversity. John Wiley & Sons (2013).

Abdi, H. Coefficient of variation. In Encyclopedia of Research Design, Vol. 1 (2010), 169–171. https://doi.org/10.4135/9781412961288.n56 DOI: https://doi.org/10.4135/9781412961288.n56

Bouton-Bessac, E., Meegahapola, L. and Gatica-Perez, D. Your Day in Your Pocket: Complex Activity Recognition from Smartphone Accelerometers. In Proc. International Conference on Pervasive Computing Technologies for Healthcare (PervasiveHealth 2022) (2022), 247–258. https://doi.org/10.1007/978-3-031-34586-9_17 DOI: https://doi.org/10.1007/978-3-031-34586-9_17

Downloads

Published

2025-11-30

How to Cite

[1]
Beltrán Mercado, L.F. et al. 2025. Datasets for Human Activity Recognition: A Comparative Analysis. Avances en Interacción Humano-Computadora. 10, 1 (Nov. 2025), 23–32. DOI:https://doi.org/10.47756/aihc.y10i1.198.

Issue

Vol. 10 No. 1 (2025): Regular Issue, 2025

Section

Research Papers

License

Copyright (c) 2025 Luis Felipe Beltrán Mercado, Jessica Beltrán Márquez, Luis A. Castro

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

AMexIHC make every effort to ensure the accuracy and rigour of all the information (the "Content") contained in out publications. However,  AMexIHC and our representatives make no representations or warranties whatsoever as to the accuracy, completeness, or suitability for any purpose of the Content. Any opinions and views expressed in this publication are the opinions and views of the authors, and are not the views of or endorsed by AMexIHC. The accuracy of the Content should not be relied upon and should be independently verified with primary sources of information.

 

Funding data