Abstract
Fall detection based on machine learning algorithms require data samples that have larger risks to gather than other similar topics such as the recognition of Activities of Daily Life (ADL). In this work we aim to detect falls using wrist devices, which have sensors such as accelerometers, gyroscopes and/or magnetometers. In this context, we aim to reduce risks and add a larger number of data samples to an existing fall detection dataset, by using simulated wrist band devices. We resort to two simulation approaches for data augmentation: (i) Virtual characters based on Motion Capture technology aimed at computer games, and (ii) fall simulation by the application of forces on an animated character. We present an evaluation of the data augmentation, which selects the real-life samples as the testing set. On the selected machine learning algorithms, k Nearest Neighbors and Decision Tree got classification improvements by using the augmented data, which shows the promising results of created samples for fall detection.
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
Notes
- 1.
Referred to as Inertial Measurement Unit (IMU).
- 2.
Fainting due to cardiovascular abnormalities.
- 3.
Samples that are not close to the training samples in the feature space.
References
Adadi, A.: A survey on data-efficient algorithms in big data era. J. Big Data 8(1), 1–54 (2021)
Berkson, J.: Application of the logistic function to bio-assay. J. Am. Stat. Assoc. 39(227), 357–365 (1944)
Breiman, L., Friedman, J.H., Olshen, R.A., Stone, C.J.: Classification and regression trees. Routledge (2017)
Casilari, E., Lora-Rivera, R., García-Lagos, F.: A study on the application of convolutional neural networks to fall detection evaluated with multiple public datasets. Sensors 20(5), 1466 (2020)
Casilari, E., Santoyo-Ramón, J.A., Cano-García, J.M.: Umafall: a multisensor dataset for the research on automatic fall detection. Procedia Comput. Sci. 110, 32–39 (2017). 14th International Conference on Mobile Systems and Pervasive Computing (MobiSPC 2017) / 12th International Conference on Future Networks and Communications (FNC 2017)/Affiliated Workshops
Collado-Villaverde, A., Cobos, M., Muñoz, P., Barrero, D.F.: A simulator to support machine learning-based wearable fall detection systems. Electronics 9(11), 1831 (2020)
Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995)
Fisher, R.A.: The use of multiple measurements in taxonomic problems. Ann. Eugen. 7(2), 179–188 (1936)
Fix, E., Hodges, J.J.: Discriminatory analysis. nonparametric discrimination: consistency properties. Technical report, University of California, Berkeley (1951)
Fuster, V.: Changing demographics: a new approach to global health care due to the aging population (2017)
Galvão, Y.M., Ferreira, J., Albuquerque, V.A., Barros, P., Fernandes, B.J.: A multimodal approach using deep learning for fall detection. Expert Syst. Appl. 168, 114226 (2021)
Jaipuria, N., et al.: Deflating dataset bias using synthetic data augmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops (2020)
Kraft, D., Srinivasan, K., Bieber, G.: Deep learning based fall detection algorithms for embedded systems, smartwatches, and IoT devices using accelerometers. Technologies 8(4), 72 (2020)
Luna-Perejón, F., Domínguez-Morales, M.J., Civit-Balcells, A.: Wearable fall detector using recurrent neural networks. Sensors 19(22), 4885 (2019)
Martínez-Villaseñor, L., Ponce, H., Brieva, J., Moya-Albor, E., Núñez-Martínez, J., Peñafort-Asturiano, C.: Up-fall detection dataset: a multimodal approach. Sensors 19(9), 1988 (2019)
Pezoa, F., Reutter, J.L., Suarez, F., Ugarte, M., Vrgoč, D.: Foundations of JSON schema. In: Proceedings of the 25th International Conference on World Wide Web, pp. 263–273. International World Wide Web Conferences Steering Committee (2016)
de Quadros, T., Lazzaretti, A.E., Schneider, F.K.: A movement decomposition and machine learning-based fall detection system using wrist wearable device. IEEE Sens. J. 18(12), 5082–5089 (2018)
Quadros, T., et al.: Development and evaluation of an elderly fall detection system based on a wearable device located at wrist. Master’s thesis, Universidade Tecnológica Federal do Paraná (2017)
Santoyo-Ramón, J.A., Casilari, E., Cano-García, J.M.: Analysis of a smartphone-based architecture with multiple mobility sensors for fall detection with supervised learning. Sensors 18(4), 1155 (2018)
Shorten, C., Khoshgoftaar, T.M.: A survey on image data augmentation for deep learning. J. Big Data 6(1), 1–48 (2019)
Sucerquia, A., López, J.D., Vargas-Bonilla, J.F.: Real-life/real-time elderly fall detection with a triaxial accelerometer. Sensors 18(4), 1101 (2018)
Sucerquia, A., López, J.D., Vargas-Bonilla, J.F.: SisFall: a fall and movement dataset. Sensors 17(1), 198 (2017)
Vaz., E., Cardoso., H., Moreno., P.: Evaluation of fall detection approaches based on virtual devices: leveraging on motion capture data in unity environments. In: Proceedings of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies - BIOSIGNALS, pp. 50–56. INSTICC, SciTePress (2022)
Wang, H., Tao, D., Yu, N., Qu, X.: Understanding consumer acceptance of healthcare wearable devices: an integrated model of UTAUT and TTF. Int. J. Med. Inform. 139, 104156 (2020)
Zhao, Y., Gao, Y., Zhai, J., Li, D.: A data augmentation strategy for skeleton-based fall detection. In: 2021 China Automation Congress (CAC), pp. 7188–7193 (2021)
Acknowledgements
This publication has been partially funded by the project LARSyS - FCT Project UIDB/50009/2020 and the project and by the project IntelligentCare - Intelligent Multimorbidity Management System (Reference LISBOA-01-0247-FEDER-045948), which is co-financed by the ERDF - European Regional Development Fund through the Lisbon Portugal Regional Operational Program - LISBOA 2020 and by the Portuguese Foundation for Science and Technology - FCT under CMU Portugal
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Carvalho, I., Vaz, E., Cardoso, H., Moreno, P. (2023). Data Augmentation Based on Virtual Wrist Devices for Fall Detection. In: Roque, A.C.A., et al. Biomedical Engineering Systems and Technologies. BIOSTEC 2022. Communications in Computer and Information Science, vol 1814. Springer, Cham. https://doi.org/10.1007/978-3-031-38854-5_9
Download citation
DOI: https://doi.org/10.1007/978-3-031-38854-5_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-38853-8
Online ISBN: 978-3-031-38854-5
eBook Packages: Computer ScienceComputer Science (R0)