Detecting Door Operations Using Wearable Devices

Shunya Taniguchi, Hangli Ge, Takeo Hamada, Takashi Michikata, Noboru Koshizuka

Abstract: Recording indoor human activities such as room occupancy is important to control the COVID-19 pandemic. Logs of human activities can be recorded using wearable devices, provided that the action of entering or exiting a room can be recognized based on the operation of doors. However, relatively few studies on human activity recognition have considered the detection of door operations using wearable devices. In this study, we propose a new deep learning-based technique to detect door operations. We developed a smartwatch application to collect and label multiple forms of data. To evaluate the proposed approach, we conducted an experiment in which we collected data during 4 door operations (2 types of doors with 2 activities, including entering and exiting) using the application. The collected data were then used to train deep learning models. The experimental results show that the average F1 scores ranged from 0.787 to 0.909 when acceleration and angular velocity data were used, which suggests that the proposed technique can detect door operations sufficiently well.