Gated Recurrent Unit Based On Feature Attention Mechanism For Physical Behavior Recognition Analysis

Wen Ying

doi:10.6180/jase.202303_26(3).0007

Gated Recurrent Unit Based On Feature Attention Mechanism For Physical Behavior Recognition Analysis

Computer Science and Information Engineering

Wen Ying This email address is being protected from spambots. You need JavaScript enabled to view it.¹

¹Sports Teaching and Research Department, Harbin Finance University, Harbin,150000, China

Received: April 11, 2022
Accepted: June 10, 2022
Publication Date: June 11, 2022

Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: ||https://doi.org/10.6180/jase.202303_26(3).0007

ABSTRACT

In order to overcome the problem that traditional machine learning methods rely heavily on artificial feature selection and have low recognition accuracy in the field of human behavior recognition, a deep learning model based on multi-layer recurrent neural network (RNN) and feature attention mechanism is proposed. The feature of sensor data is automatically extracted to realize physical motion recognition. Feature attention mechanism is used to analyze the correlation between historical information and input features, and extract important features. Temporal attention mechanism independently selects historical information of Gated Recurrent Unit (GRU) network at key time points to improve the stability of long-term prediction effect. This model uses multi-scale convolutional neural network and GRU to extract features from sensor data. The feature matrix is spliced in the matrix dimension and then the feature classification is completed by Softmax. Experimental results show that the accuracy of human physical behavior recognition based on public human behavior recognition (HAR) data set is 97.87%. The proposed model achieves better accuracy and avoids complex signal preprocessing stage.

Keywords: RNN, GRU, feature attention mechanism, physical behavior recognition, Softmax

REFERENCES

[1] B. Sun, N. Yuan, S. Li, S. Wu, and N. Wang, (2021) “Human behaviour recognition with mid-level representations for crowd understanding and analysis" IET Image Processing 15(14): 3414–3424. DOI: 10.1049/ipr2.12147.
[2] Y. He, (2021) “Athlete human behavior recognition based on continuous image deep learning and sensors"Wireless Networks: DOI: 10.1007/s11276-021-02721-z.
[3] F. Zahid, Z. Ong, S. Khoo, and M. Salleh, (2021) “Inertial sensor based human behavior recognition in modal testing using machine learning approach" Measurement Science and Technology 32(11): DOI: 10.1088/1361-6501/ac1612.
[4] G. Gao, Z. Li, Z. Huan, Y. Chen, J. Liang, B. Zhou, and C. Dong, (2021) “Human behavior recognition model based on feature and classifier selection" Sensors 21(23): DOI: 10.3390/s21237791.
[5] D. Li, H. Jahan, X. Huang, and Z. Feng, (2021) “Human action recognition method based on historical point cloud trajectory characteristics" Visual Computer: DOI: 10.1007/s00371-021-02167-6.
[6] A. Jisi and S. Yin, (2021) “A new feature fusion network for student behavior recognition in education" Journal of Applied Science and Engineering (Taiwan) 24(2): 133–140. DOI: 10.6180/jase.202104_24(2).0002.
[7] M. Sajjad, S. Zahir, A. Ullah, Z. Akhtar, and K. Muhammad, (2020) “Human Behavior Understanding in Big Multimedia Data Using CNN based Facial Expression Recognition" Mobile Networks and Applications 25(4): 1611–1621. DOI: 10.1007/s11036-019-01366-9.
[8] Y.-H. Byeon, D. Kim, J. Lee, and K.-C. Kwak, (2021) “Ensemble Three-Stream RGB-S Deep Neural Network for Human Behavior Recognition under Intelligent Home Service Robot Environments" IEEE Access 9: 73240–73250. DOI: 10.1109/ACCESS.2021.3077487.
[9] S. Khowaja and S.-L. Lee, (2020) “Semantic Image Networks for Human Action Recognition" International Journal of Computer Vision 128(2): 393–419. DOI: 10.1007/s11263-019-01248-3.
[10] Y.-L. Hsueh,W.-N. Lie, and G.-Y. Guo, (2020) “Human Behavior Recognition from Multiview Videos" Information Sciences 517: 275–296. DOI: 10.1016/j.ins.2020.01.002.
[11] K. Zhou, T. Wu, C. Wang, J. Wang, and C. Li. “Skeleton Based Abnormal Behavior Recognition Using Spatio-Temporal Convolution and Attention-Based LSTM”. In: 174. cited By 3. 2020, 424–432. DOI: 10.1016/j.procs.2020.06.110.
[12] X. Zhang, (2021) “Application of human motion recognition utilizing deep learning and smart wearable device in sports" International Journal of System Assurance Engineering and Management 12(4): 835–843. DOI: 10.1007/s13198-021-01118-7.
[13] A. Shirian, S. Tripathi, and T. Guha, (2022) “Dynamic Emotion Modeling With Learnable Graphs and Graph Inception Network" IEEE Transactions on Multimedia 24: 780–790. DOI: 10.1109/TMM.2021.3059169.
[14] V. Polepally, N. Reddy, M. Sindhuja, N. Anjali, and K. Reddy. “A Deep Learning Approach for Prediction of Stock Price Based on Neural Network Models: LSTM and GRU”. In: cited By 0. 2021. DOI: 10.1109/ICCCNT51525.2021.9579782.
[15] W. Huang and F. Zhou, (2020) “DA-CapsNet: dual attention mechanism capsule network" Scientific Reports 10(1): DOI: 10.1038/s41598-020-68453-w.
[16] N. Sikder and A.-A. Nahid, (2021) “KU-HAR: An open dataset for heterogeneous human activity recognition" Pattern Recognition Letters 146: 46–54. DOI: 10.1016/j.patrec.2021.02.024.
[17] H. Yin, J.Wang, J. Lin, D. Han, C. Ying, and Q. Meng, (2021) “A Memory-Attention Hierarchical Model for Driving-Behavior Recognition and Motion Prediction" International Journal of Automotive Technology 22(4): 895–908. DOI: 10.1007/s12239-021-0081-8.
[18] F.-C. Lin, H.-H. Ngo, C.-R. Dow, K.-H. Lam, and H. Le, (2021) “Student behavior recognition system for the classroom environment based on skeleton pose estimation and person detection" Sensors 21(16): DOI: 10.3390/s21165314.
[19] P. Chonggao, (2021) “Simulation of student classroom behavior recognition based on cluster analysis and random forest algorithm" Journal of Intelligent and Fuzzy Systems 40(2): 2421–2431. DOI: 10.3233/JIFS-189237.
[20] Y. Guo and X. Wang, (2021) “Applying TS-DBN model into sports behavior recognition with deep learning approach" Journal of Supercomputing 77(10): 12192–12208. DOI: 10.1007/s11227-021-03772-x.
[21] Y. Pan, X. Zhao, Z. Xu, J. Li, Y. Li, and L. Liu, (2021) “Research on Abnormal Behavior Recognition of Buses Based on Improved Support Vector Machine" Journal of Advanced Transportation 2021: DOI: 10.1155/2021/2020882.