Methods for solving the problem of human activity recognition using generative networks
DOI:
https://doi.org/10.46299/j.isjea.20240306.02Keywords:
Deep Learning, Generative Networks, Autoencoder, Variational Autoencoder, Semi-Guided LearningAbstract
Wearable devices, such as smartwatches, are capable of transmitting significant amounts of data collected by a variety of sensors. Under normal conditions, this data is unlabeled and requires the application of non-reinforcement learning methods. Generative networks, in particular variational autoencoders, have an architecture suitable for investigating the general structure of data obtained from wearable devices. The authors proposed a system consisting of a set of generative networks to recognize human activity.References
Zhang, W., Zhao, X., & Li, Z. (2019). A comprehensive study of smartphone-based indoor activity recognition via Xgboost. IEEE Access, 7, 80027-80042.
Chen, T., & Guestrin, C. (2016, August). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp. 785-794).
Chen, Y., Zhong, K., Zhang, J., Sun, Q., & Zhao, X. (2016, January). LSTM networks for mobile human activity recognition. In 2016 International conference on artificial intelligence: technologies and applications (pp. 50-53). Atlantis Press
Vennerød, C. B., Kjærran, A., & Bugge, E. S. (2021). Long short-term memory RNN. arXiv preprint arXiv:2105.06756.
Human Activity Recognition - WISDM's activity prediction dataset. Available at https://github.com/coloriz/HAR-WISDM_ar
Kingma, D. P., & Welling, M. (2019). An introduction to variational autoencoders. Foundations and Trends® in Machine Learning, 12(4), 307-392.
Normal distribution. Available at https://en.wikipedia.org/wiki/Normal_distribution
Munoz-Organero, M., & Ruiz-Blazquez, R. (2017). Time-elastic generative model for acceleration time series in human activity recognition. Sensors, 17(2), 319
Gozhyj, A. (2020). Comparative Analysis of using Recurrent Autoencoders for User Biometric Verification with Wearable Accelerometer.
Equal error rate. Available at https://en.wikipedia.org/wiki/Biometrics#Performance
MotionSense dataset. Available at https://github.com/mmalekzadeh/motion-sense
Kingma, D. P. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
Kullback–Leibler divergence. Available at https://en.wikipedia.org/wiki/Kullback%E2%80%93Leibler_divergence
Bowman, S. R., Vilnis, L., Vinyals, O., Dai, A. M., Jozefowicz, R., & Bengio, S. (2015). Generating sentences from a continuous space. arXiv preprint arXiv:1511.06349.
Mean squared error. Available at https://en.wikipedia.org/wiki/Mean_squared_error
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Denys Kalenichenko, Valeriy Danylov
This work is licensed under a Creative Commons Attribution 4.0 International License.
