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 F1 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.
@article{arxiv.1810.04038,
title = {Understanding and Improving Recurrent Networks for Human Activity Recognition by Continuous Attention},
author = {Ming Zeng and Haoxiang Gao and Tong Yu and Ole J. Mengshoel and Helge Langseth and Ian Lane and Xiaobing Liu},
journal= {arXiv preprint arXiv:1810.04038},
year = {2018}
}
Comments
8 pages. published in The International Symposium on Wearable Computers (ISWC) 2018