CARE: chewing activity recognition using noninvasive single axis accelerometer

Shuangquan Wang, Gang Zhou, Lisha Hu, Zhenyu Chen, Yiqiang Chen

Abstract: In this paper, we focus on user's Chewing Activity REcognition and present a novel recognition system named CARE. Based on the observation that during chewing the mastication muscle contracts and accordingly bulges in some degree, CARE uses a single axis accelerometer attached on the temporalis to detect the muscle bulge and recognize user's chewing activity. CARE is also able to calculate the chewing frequency through recognizing the periodic pattern of acceleration data. Experiments are conducted and the results show that CARE obtains high accuracy on both chewing activity classification and chewing frequency detection.