|
|
|
| Research on an LSTM recurrent neural network algorithm for human activity recognition |
| Li Zhimin, Liu Yipeng, Zheng Haifeng, Feng Xinxin |
| College of Physics and Information Engineering, Fuzhou University, Fuzhou 350116 |
|
|
|
|
Abstract In order to overcome the problem of insufficient feature extraction and lost information incurred by the traditional machine learning based methods such as support vector machine (SVM), we propose a long short-term memory (LSTM) based neural network algorithm to recognize human activity in this paper. The proposed algorithm can not only fully extract time characteristics of human activity data but also effectively avoid the problem of gradient disappearance in traditional recurrent neural network, thus improving the accuracy of human activity recognition. In this paper, the proposed approach is trained and tested by using a WISDM dataset and ievaluated by the cross validation method. Experimental results show that the proposed method can improve the accuracy of recognition when comparing with the other machine learning algorithms such as SVM.
|
|
Received: 13 June 2018
Published: 16 November 2018
|
|
|
|
| Cite this article: |
|
Li Zhimin,Liu Yipeng,Zheng Haifeng等. Research on an LSTM recurrent neural network algorithm for human activity recognition[J]. Electrical Engineering, 2018, 19(11): 26-30.
|
|
|
|
| URL: |
|
http://dqjs.cesmedia.cn/EN/Y2018/V19/I11/26
|
[1] Jayita S, Sanjoy C, Nauman A, et al.Designing device independent two-phase activity recognition framework for smartphones[C]//Wireless and Mobile Computing, Networking and Communications, 2017: 41-45.
[2] Nunes U M, Faria D R, Peixoto P.A human activity recognition framework using max-min features and key poses with differential evolution random forests classifier[J]. Pattern Recognition Letters, 2017, 99(SI): 21-31.
[3] Jan J, Petr G, Pavel D, et al.Fast Human Activity Recognition Based on a Massively Parallel Implemen- tation of Random Forest[M]. Intelligent Information and Database Systems. Los Angeles: Springer Berlin Heidelberg, 2016.
[4] Abidine B M, Fergani L, Fergani B A.The joint use of sequence features combination and modified weighted SVM for improving daily activity recognition[J]. Pattern Analysis and Applications, 2018, 21(1): 119-138.
[5] Chen Zhenghua, Zhu Qingchang, Soh Y C, et al.Robust human activity recognition using smartphone sensors via CT-PCA and online SVM[J]. IEEE Transactions on Industrial Informatics, 2017, 13(6): 3070-3080.
[6] Uslu G, Baydere S.On the activity detection with incomplete acceleration data using iterative KNN classifier[C]//IEEE International Conference on Systems, Man, and Cybernetics, Hungary: IEEE, 2017: 3528-3533.
[7] Sani S, Wiratunga N, Massie S, et al.KNN Sampling for Personalised Human Activity Recognition[M]. Scotland: Springer-Verlag, 2017: 330-344.
[8] Abu Alsheikh M, Niyato D, Lin Shaowei, et al.Mobile big data analytics using deep learning and apache spark[J]. IEEE Network, 2016, 30(3): 22-29.
[9] Vo Q, Nguyen H, Le B, et al.Multi-channel LSTM- CNN model for Vietnamese sentiment analysis[C]// 2017 9th International Conference on Knowledge and Systems Engineering, Vietnam: IEEE, 2017: 1-6.
[10] Greff K, Srivastava R K, Koutnik J, et al.LSTM: A Search Space Odyssey[J]. IEEE Transactions on Neural Networks & Learning Systems, 2017, 28(10): 2222-2232.
[11] Kwapisz J R, Weiss G M, Moore S A, et al.Activity recognition using cell phone accelerometers[J]. Acm Sigkdd Explorations Newsletter, 2011, 12(2): 74-82. |
|
|
|
2018, Vol. 19 
