Understanding and Improving Recurrent Networks for Human Activity Recognition by Continuous Attention
Zeng, Ming; Gao, Haoxiang; Yu, Tong; Mengshoel, Ole Jakob; Langseth, Helge; Lane, Ian; Liu, Xiaobing
Chapter
Accepted version
Åpne
Permanent lenke
http://hdl.handle.net/11250/2596034Utgivelsesdato
2018Metadata
Vis full innførselSamlinger
Originalversjon
10.1145/3267242.3267286Sammendrag
Deep neural networks, including recurrent networks, have been successfully applied to human activity recognition. Unfortunately, the final representation learned by recurrent networks might encode some noise (irrelevant signal components, unimportant sensor modalities, etc.). Besides, it is difficult to interpret the recurrent networks to gain insight into the models' behavior. To address these issues, we propose two attention models for human activity recognition: temporal attention and sensor attention. These two mechanisms adaptively focus on important signals and sensor modalities. To further improve the understandability and mean Fl score, we add continuity constraints, considering that continuous sensor signals are more robust than discrete ones. We evaluate the approaches on three datasets and obtain state-of-the-art results. Furthermore, qualitative analysis shows that the attention learned by the models agree well with human intuition.