Skip to Main Content
This paper reports on research where users' activities are logged for extended periods by wrist-worn sensors. These devices operated for up to 27 consecutive days, day and night, while logging features from motion, light, and temperature. This data, labeled via 24-hour self-recall annotation, is explored for occurrences of daily activities. An evaluation shows that using a model of the users' rhythms can improve recognition of daily activities significantly within the logged data, compared to models that exclusively use the sensor data for activity recognition.