Ms. Kaixuan Chen

Ph.D. candidate

UNSW Sydney

Ms. Kaixuan Chen is a Ph.D. student at the School of Computer Science and Engineering, University of New South Wales (UNSW) since March 2017. Her research interests include data mining, machine learning, and their applications to Internet of Things (IoT), Human Activity Recognition (HAR) and Brain Computer Interface (BCI). She earned a Bachelor's degree from Xi'an Jiaotong University (XJTU) in 2015, majoring in Telecommunication Engineering.

Human activity recognition is a fundamental technique popular in healthcare and surveillance domains. Wearable physical sensor signal processing-based activity recognition has been widely applied to ubiquitous applications and profoundly revolutionized our daily lives, thanks to its high resistance to environmental variation without significantly violating individual privacy. Multi-modality is an important feature of sensor-based activity recognition. We consider two inherent characteristics of human activities, the spatially-temporally varying salience of features and the relations between activities and corresponding body part motions. Based on these, we propose a multi-agent spatial-temporal attention model. The spatial-temporal attention mechanism helps intelligently select informative modalities and their active periods. And the multiple agents in the proposed model represent activities with collective motions across body parts by independently selecting modalities associated with single motions. With a joint recognition goal, the agents share gained information and coordinate their selection policies to learn the optimal recognition model.