Interpretable parallel recurrent neural networks with convolutional attentions for multi-modality activity modeling

Chen, K, Yao, L, Wang, X, Zhang, D, Gu, T, Yu, Z and Yang, Z 2018, 'Interpretable parallel recurrent neural networks with convolutional attentions for multi-modality activity modeling', in Proceedings of the International Joint Conference on Neural Networks (IJCNN 2018), Rio de Janeiro, Brazil, 8-13 July 2018, pp. 2082-2089.


Document type: Conference Paper
Collection: Conference Papers

Title Interpretable parallel recurrent neural networks with convolutional attentions for multi-modality activity modeling
Author(s) Chen, K
Yao, L
Wang, X
Zhang, D
Gu, T
Yu, Z
Yang, Z
Year 2018
Conference name IJCNN 2018
Conference location Rio de Janeiro, Brazil
Conference dates 8-13 July 2018
Proceedings title Proceedings of the International Joint Conference on Neural Networks (IJCNN 2018)
Publisher IEEE
Place of publication United States
Start page 2082
End page 2089
Total pages 8
Abstract Multimodal features play a key role in wearable sensor based human activity recognition (HAR). Selecting the most salient features adaptively is a promising way to maximize the effectiveness of multimodal sensor data. In this regard, we propose a "collect fully and select wisely" principle as well as an interpretable parallel recurrent model with convolutional attentions to improve the recognition performance. We first collect modality features and the relations between each pair of features to generate activity frames, and then introduce an attention mechanism to select the most prominent regions from activity frames precisely. The selected frames not only maximize the utilization of valid features but also reduce the number of features to be computed effectively. We further analyze the accuracy and interpretability of the proposed model based on extensive experiments. The results show that our model achieves competitive performance on two benchmarked datasets and works well in real life scenarios.
Subjects Pattern Recognition and Data Mining
Ubiquitous Computing
Mobile Technologies
Keyword(s) HAR
attention
deep learning
wearable sensors
DOI - identifier 10.1109/IJCNN.2018.8489767
Copyright notice © 2018 IEEE
ISBN 9781509060153
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 0 times in Scopus Article
Altmetric details:
Access Statistics: 17 Abstract Views  -  Detailed Statistics
Created: Fri, 14 Dec 2018, 16:06:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us