1. Learning multi-level features for sensor-based human action recognition.
- Author
-
Xu, Yan, Shen, Zhengyang, Zhang, Xin, Gao, Yifan, Deng, Shujian, Wang, Yipei, Fan, Yubo, and Chang, Eric I-Chao
- Subjects
HUMAN behavior research ,MOBILE computing ,WIRELESS communications ,SOCIAL sciences ,WEARABLE technology - Abstract
This paper proposes a multi-level feature learning framework for human action recognition using a single body-worn inertial sensor. The framework consists of three phases, respectively designed to analyze signal-based (low-level), components (mid-level) and semantic (high-level) information. Low-level features capture the time and frequency domain property while mid-level representations learn the composition of the action. The Max-margin Latent Pattern Learning (MLPL) method is proposed to learn high-level semantic descriptions of latent action patterns as the output of our framework. The proposed method achieves the state-of-the-art performances, 88.7%, 98.8% and 72.6% (weighted F 1 score) respectively, on Skoda, WISDM and OPP datasets. [ABSTRACT FROM AUTHOR]
- Published
- 2017
- Full Text
- View/download PDF