Edge Computing Framework for Wearable Sensor-Based Human Activity Recognition
Human activity recognition is done based on the observation and analysis of human behavior to understand the performed activity. With the emergence of battery powered, low cost and embedded wearable sensors, it became possible to study human activity in various real-world scenarios. Together with the development in data collection, novel machine learning based modeling approaches show huge promise in modeling human activities accurately. Edge computing framework, that is capable of executing human activity recognition models at the edge of the network, is presented in this paper. Framework architecture and its implementation on a single board computer are presented. The framework allows the implementation of various machine learning models for human activity recognition in a standardized manner. The framework is demonstrated experimentally.
KeywordsHuman activity recognition Edge computing Wearable sensors Machine learning IoT Neural networks
The authors would like to thank the Ministry of Civil Affairs of Bosnia and Herzegovina for the financial support provided for this study.
Authors acknowledge Inovatink company for providing technical, logistic and financial support for this study.
Authors would also wish to express gratitude to Bosnia and Herzegovina Future Foundation (BHFF) for providing financial support in the form of a scholarship to lead author of this study.
- 3.Al-Turjman, F.: Artificial Intelligence in IoT. Springer (2019)Google Scholar
- 7.Chen, Z., Klatzky, R., Siewiorek, D., Satyanarayanan, M., Hu, W., Wang, J., Pillai, P.: An empirical study of latency in an emerging class of edge computing applications for wearable cognitive assistance. In: Proceedings of the Second ACM/IEEE Symposium on Edge Computing - SEC 2017 (2017)Google Scholar
- 12.Acikmese, Y., Ustundag, B.C., Golubovic, E.: Towards an artificial training expert system for basketball. In: 10th International IEEE Conference on Electrical and Electronics Engineering (ELECO), pp. 1300–1304 (2017)Google Scholar
- 13.Sahinovic, S., Dzebo, A., Ustundag, B.C., Golubovic, E., Uzunovic, T.: An open and extensible data acquisition and processing platform for rehabilitation applications. Lecture Notes in Networks and Systems (2018)Google Scholar
- 14.Uzunovic, T., Golubovic, E., Tucakovic, Z., Acikmese, Y., Sabanovic, A.: Task-based control and human activity recognition for human-robot collaboration. In: IECON - 44th Annual Conference of the IEEE Industrial Electronics Society (2018)Google Scholar
- 15.Curic, M., Kevric, J.: Posture activity prediction using Microsoft Azure. In: Hadzikadic, M., Avdakovic, S. (eds.) Advanced Technologies, Systems, and Applications II. IAT 2017. Lecture Notes in Networks and Systems, vol. 28. Springer, Cham (2018)Google Scholar
- 16.Ittiyavirah, S., Allwyn Jones, S., Siddarth, P.: Analysis of different activation functions using backpropagation neural networks. J. Theor. Appl. Inf. Technol. 47, 1344–1348 (2013)Google Scholar