Abstract
The ubiquity of consumer devices with sensing and computational capabilities, such as smartphones and smartwatches, has increased interest in their use in human activity recognition for healthcare monitoring applications, among others. When developing such a system, researchers rely on input data to train recognition models. In the absence of openly available datasets that meet the model requirements, researchers face a hard and time-consuming process to decide which sensing device to use or how much data needs to be collected. In this paper, we explore the effect of the amount of training data on the performance (i.e., classification accuracy and activity-wise F1-scores) of a CNN model by performing an incremental cross-subject evaluation using data collected from a consumer smartphone and smartwatch. Systematically studying the incremental inclusion of subject data from a set of 22 training subjects, the results show that the model’s performance initially improves significantly with each addition, yet this improvement slows down the larger the number of included subjects. We compare the performance of models based on smartphone and smartwatch data. The latter option is significantly better with smaller sizes of training data, while the former outperforms with larger amounts of training data. In addition, gait-related activities show significantly better results with smartphone-collected data, while non-gait-related activities, such as standing up or sitting down, were better recognized with smartwatch-collected data.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Banos, O., et al.: Window size impact in human activity recognition. Sensors 14(4), 6474–6499 (2014). https://doi.org/10.3390/s140406474
Chen, H., et al.: Assessing impacts of data volume and data set balance in using deep learning approach to human activity recognition. In: IEEE International Conference on Bioinformatics and Biomedicine, pp. 1160–1165. IEEE (2017). https://doi.org/10.1109/BIBM.2017.8217821
Chen, W., et al.: Sensecollect: we need efficient ways to collect on-body sensor-based human activity data! Proc. ACM Interact. Mobile Wearable Ubiquitous Technol. 5(3), 1–27 (2021). https://doi.org/10.1145/3478119
Coviello, G., Avitabile, G.: Multiple synchronized inertial measurement unit sensor boards platform for activity monitoring. IEEE Sens. J. 20(15), 8771–8777 (2020). https://doi.org/10.1109/JSEN.2020.2982744
De-La-Hoz-Franco, E., Ariza-Colpas, P., Quero, J.M., Espinilla, M.: Sensor-based datasets for human activity recognition-a systematic review of literature. IEEE Access 6, 59192–59210 (2018). https://doi.org/10.1109/ACCESS.2018.2873502
Demrozi, F., et al.: Human activity recognition using inertial, physiological and environmental sensors: a comprehensive survey. IEEE Access 8, 210816–210836 (2020). https://doi.org/10.1109/ACCESS.2020.3037715
Gholamiangonabadi, D., Kiselov, N., Grolinger, K.: Deep neural networks for human activity recognition with wearable sensors: leave-one-subject-out cross-validation for model selection. IEEE Access 8, 133982–133994 (2020). https://doi.org/10.1109/ACCESS.2020.3010715
Hossin, M., Sulaiman, M.N.: A review on evaluation metrics for data classification evaluations. International journal of data mining & knowledge management process 5(2), 1 (2015). https://doi.org/10.5121/ijdkp.2015.5201
Jaén-Vargas, M., et al.: Effects of sliding window variation in the performance of acceleration-based human activity recognition using deep learning models. PeerJ Comput. Sci. 8, e1052 (2022). https://doi.org/10.7717/peerj-cs.1052
Lara, O.D., Labrador, M.A.: A survey on human activity recognition using wearable sensors. IEEE Commun. Surv. Tutor. 15(3), 1192–1209 (2012). https://doi.org/10.1109/SURV.2012.110112.00192
Leightley, D., Darby, J., Li, B., McPhee, J.S., Yap, M.H.: Human activity recognition for physical rehabilitation. In: IEEE International Conference on Systems, Man, and Cybernetics, pp. 261–266 (2013). https://doi.org/10.1109/SMC.2013.51
Li, H., Shrestha, A., Heidari, H., Le Kernec, J., Fioranelli, F.: Bi-lstm network for multimodal continuous human activity recognition and fall detection. IEEE Sens. J. 20(3), 1191–1201 (2019). https://doi.org/10.1109/JSEN.2019.2946095
Mann, H.B., Whitney, D.R.: On a test of whether one of two random variables is stochastically larger than the other. The annals of mathematical statistics, pp. 50–60 (1947)
Matey-Sanz, M.: Reproducible Package for Analysis and Impact of Training Set Size in Cross-Subject Human Activity Recognition (Jul 2023). https://doi.org/10.5281/zenodo.8163542
Matey-Sanz, M., et al.: Instrumented timed up and go test using inertial sensors from consumer wearable devices. In: 20th International Conference on Artificial Intelligence in Medical, Proceedings, pp. 144–154. Springer (2022). https://doi.org/10.1007/978-3-031-09342-5_14
Mills, D.L.: Internet time synchronization: the network time protocol. IEEE Trans. Commun. 39(10), 1482–1493 (1991). https://doi.org/10.1109/26.103043
Moënne-Loccoz, N., Brémond, F., Thonnat, M.: Recurrent bayesian network for the recognition of human behaviors from video. In: Crowley, J.L., Piater, J.H., Vincze, M., Paletta, L. (eds.) ICVS 2003. LNCS, vol. 2626, pp. 68–77. Springer, Heidelberg (2003). https://doi.org/10.1007/3-540-36592-3_7
Narayana, P.A., et al.: Deep-learning-based neural tissue segmentation of mri in multiple sclerosis: effect of training set size. J. Magn. Reson. Imaging 51(5), 1487–1496 (2020). https://doi.org/10.1002/jmri.26959
Oluwalade., B., et al.: Human activity recognition using deep learning models on smartphones and smartwatches sensor data. In: Proc. of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies, HEALTHINF, pp. 645–650. INSTICC, SciTePress (2021). https://doi.org/10.5220/0010325906450650
Ramezan, C.A., et al.: Effects of training set size on supervised machine-learning land-cover classification of large-area high-resolution remotely sensed data. Remote Sensing 13(3), 368 (2021). https://doi.org/10.3390/rs13030368
Saez, Y., Baldominos, A., Isasi, P.: A comparison study of classifier algorithms for cross-person physical activity recognition. Sensors 17(1), 66 (2016). https://doi.org/10.3390/s17010066
Sandha, S.S., et al.: Time awareness in deep learning-based multimodal fusion across smartphone platforms. In: IEEE/ACM Fifth International Conference on IoT Design and Implementation, pp. 149–156. IEEE (2020). https://doi.org/10.1109/IOTDI49375.2020.00022
Sansano, E., et al.: A study of deep neural networks for human activity recognition. Comput. Intell. 36(3), 1113–1139 (2020). https://doi.org/10.1111/coin.12318
Vallat, R.: Pingouin: statistics in python. J. Open Source Soft. 3(31), 1026 (2018). https://doi.org/10.21105/joss.01026
Yazdansepas, D., et al.: A multi-featured approach for wearable sensor-based human activity recognition. In: IEEE International Conference on Healthcare Informatics, pp. 423–431 (2016). https://doi.org/10.1109/ICHI.2016.81
Acknowledgments
M. Matey-Sanz and A. González-Pérez are funded by the Spanish Ministry of Universities [grants FPU19/05352 and FPU17/03832]. This study was supported by project PID2020-120250RB-I00 (SyMptOMS-ET) funded by MCIN/AEI/10.13039/501100011033.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 Springer Nature Switzerland AG
About this paper
Cite this paper
Matey-Sanz, M., Torres-Sospedra, J., González-Pérez, A., Casteleyn, S., Granell, C. (2024). Analysis and Impact of Training Set Size in Cross-Subject Human Activity Recognition. In: Vasconcelos, V., Domingues, I., Paredes, S. (eds) Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. CIARP 2023. Lecture Notes in Computer Science, vol 14469. Springer, Cham. https://doi.org/10.1007/978-3-031-49018-7_28
Download citation
DOI: https://doi.org/10.1007/978-3-031-49018-7_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-49017-0
Online ISBN: 978-3-031-49018-7
eBook Packages: Computer ScienceComputer Science (R0)