Performance Analysis of Deep Learning based Human Activity Recognition Methods

Authors

  • Mst. Farzana Aktter Pabna University of Science and Technology, Bangladesh
  • Md Anwar Hossain Pabna University of Science and Technology, Bangladesh https://orcid.org/0000-0001-5949-1180
  • Sohag Sarker Pabna University of Science and Technology, Bangladesh
  • AFM Zainul Abadin Pabna University of Science and Technology, Bangladesh
  • Mirza AFM Rashidul Hasan University of Rajshahi, Bangladesh https://orcid.org/0000-0001-5425-9112

DOI:

https://doi.org/10.33736/jaspe.4639.2022

Keywords:

Human Activity Recognition, Artificial Neural Network, Convolutional Neural Network, Long Short-term Memory

Abstract

Human Activity Recognition (HAR) is one of the most important branches of human-centered research activities. Along with the development of artificial intelligence, deep learning techniques have gained remarkable success in computer vision. In recent years, there is a growing interest in Human Activity Recognition systems applied in healthcare, security surveillance, and human motion-based activities. A HAR system is essentially made of a wearable device equipped with a set of sensors (like accelerometers, gyroscopes, magnetometers, heart-rate sensors, etc.). Different methods are being applied for improving the accuracy and performance of the HAR system. In this paper, we implement Artificial Neural Network (ANN), and Convolutional Neural Network (CNN) in combination with Long Short-term Memory (LSTM) methods with different layers and compare their outputs towards the accuracy in the HAR system. We compare the accuracy of different HAR methods and observed that the performance of our proposed model of CNN 2 layers with LSTM 1 layer is the best.

Author Biographies

Md Anwar Hossain, Pabna University of Science and Technology, Bangladesh

Associate Professor

Department of Information and Communication Engineering

 

Sohag Sarker, Pabna University of Science and Technology, Bangladesh

Associate Professor

Department of Information and Communication Engineering

AFM Zainul Abadin, Pabna University of Science and Technology, Bangladesh

Assistant Professor

Department of Information and Communication Engineering

Mirza AFM Rashidul Hasan, University of Rajshahi, Bangladesh

Professor

Department of Information and Communication Engineering

References

Ronao C.A. & Cho SB. (2015). Deep Convolutional Neural Networks for Human Activity Recognition with Smartphone Sensors. In: Arik S., Huang T., Lai W., Liu Q. (eds) Neural Information Processing. ICONIP 2015. Lecture Notes in Computer Science, vol 9492. Springer, Cham. https://doi.org/10.1007/978-3-319-26561-2_6

Moya Reuda, F., Grzezick, R., A. Fink, G., Feldhorst, S., & Ten Hompel, M. (2018). Convolutional Neural Networks for Human Activity Recognition Using Body-Worn Sensors, Journal of Informatics (5020026). https://doi.org/10.3390/informatics5020026

Jobanputra, C., Bavishi, J., & Doshi, N. (2019). Human activity recognition: A survey. Procedia Computer Science, 155, 698-703. https://doi.org/10.1016/j.procs.2019.08.100

Xu, W., Pang, Y., Yang, Y., & Lui, Y. (2018). Human Activity Recognition Based on Convolutional Neural Network, (2018), 24th International Conference on Pattern Recognition (ICPR) Beijing, China, August 20-24. https://doi.org/10.1109/ICPR.2018.8545435

A. Jain and V. Kanhangad, (2018). Human Activity Classification in Smartphones Using Accelerometer and Gyroscope Sensors, IEEE Sensors Journal, 18(3), 1169-1177. https://doi.org/10.1109/JSEN.2017.2782492

Yang, J., Nguyen, M. N., San, P. P., Li, X. L., & Krishnaswamy, S. (2015). Deep convolutional neural networks on multichannel time series for human activity recognition. In Twenty-fourth international joint conference on artificial intelligence (IJCAI), 3995-4001.

Wang, H., Zhao, J., Li, J., Tian, L., Tu, P., Cao, T., & Li, S. (2020). Wearable sensor-based human activity recognition using hybrid deep learning techniques. Security and communication Networks, 2020. https://doi.org/10.1155/2020/2132138

Xi, R., Hou, M., Fu, M., Qu, H., & Liu, D. (2018). Deep dilated convolution on multimodality time series for human activity recognition. In 2018 international joint conference on neural networks (IJCNN), 1-8. https://doi.org/10.1109/IJCNN.2018.8489540

Ignatov Andrey (2018). Real-time human activity recognition from accelerometer data using Convolutional Neural Networks, Applied Soft Computing, Volume 62, 2018, Pages 915-922, ISSN 1568-4946, https://doi.org/10.1016/j.asoc.2017.09.027

Alake, R (2020). Batch Normalization in Neural Networks Explained (Algorithm Breakdown) https://towardsdatascience.com/batch-normalization-in-neural-networks-1ac91516821

Dua, D. & Graff, C. (2019). UCI Machine Learning Repository. Irvine, CA: University of California, School of Information and Computer Science. http://archive.ics.uci.edu/ml

Hammerla, N. Y., Halloran, S., & Plötz, T. (2016). Deep, convolutional, and recurrent models for human activity recognition using wearables. arXiv preprint arXiv:1604.08880. https://doi.org/10.48550/arXiv.1604.08880

Song-Mi Lee, Sang Min Yoon, and Heeryon Cho. (2017). Human activity recognition from accelerometer data using Convolutional Neural Network. 2017 IEEE International Conference on Big Data and Smart Computing (BigComp), 2017, 131-134. https://doi.org/10.1109/BIGCOMP.2017.7881728

Jayabalan, A., Karunakaran, H., Murlidharan, S., & Shizume, T. (2016). Dynamic Action Recognition: A convolutional neural network model for temporally organized joint location data. https://doi.org/10.48550/arXiv.1612.06703.

Downloads

Published

2022-10-31

How to Cite

Aktter, M. F. ., Hossain, M. A., Sarker, S., Abadin, A. Z. ., & Hasan, M. A. R. (2022). Performance Analysis of Deep Learning based Human Activity Recognition Methods . Journal of Applied Science &Amp; Process Engineering, 9(2), 1197–1208. https://doi.org/10.33736/jaspe.4639.2022