Deep Dilation on Multimodality Time Series for Human Activity Recognition
| Autor: | Mingsheng Fu, Hong Qu, Rui Xi, Mengshu Hou, Ming Li, Charles Roland Haruna, Daibo Liu |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
human activity recognition
General Computer Science Computer science Feature extraction feature representation Inference 02 engineering and technology Machine learning computer.software_genre Convolutional neural network Activity recognition Discriminative model 020204 information systems 0202 electrical engineering electronic engineering information engineering General Materials Science Dilation operation multimodality time series business.industry Deep learning General Engineering deep learning Softmax function Probability distribution 020201 artificial intelligence & image processing lcsh:Electrical engineering. Electronics. Nuclear engineering Artificial intelligence business lcsh:TK1-9971 computer |
| Zdroj: | IEEE Access, Vol 6, Pp 53381-53396 (2018) |
| ISSN: | 2169-3536 |
| DOI: | 10.1109/access.2018.2870841 |
| Popis: | Providing accurate information on people's activities and behaviors plays an important role in innumerable applications, such as medical, security, and entertainment. In recent years, deep learning has been applied in human activity recognition, and achieved a better performance. However, if the spatial dependency of inter-sensors is considered, it is possible to enhance the discriminative ability. In this paper, we present a novel deep learning framework for human activity recognition problems. First, on the basis of our previous work, we utilize dilated convolutional neural network to extract features of inter-sensors and intra-sensors. Since the extracted features are local and short-temporal, it is necessary to utilize RNN to model the long-temporal dependencies. However, duo to that LSTM and GRU often rely on the completely previous computations, it will result in slow inference and hard convergence. Hence, inspired by the idea of dilation operation, we present a novel recurrent model to learn the temporal dependencies at different time scales. Then, at the topmost layer, a fully-connected layer with softmax function is utilized to generate a class probability distribution, and the predicted activity is obtained. Eventually, we evaluate the proposed framework in two open human activity datasets, OPPORTUNITY and PAMAP2. Results demonstrate that the proposed framework achieves a higher classification performance than the state-of-the-art methods. Moreover, it takes the least time to recognize an activity. Besides, it also performs faster and easier to converge in the training stage. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|