The number of older adults in Korea is increasing, along with the number of depressed older patients. The causes of depression in older adults include social isolation with negligible interaction with others, irregular nutritional habits, and self-negligence, i.e., they do not engage in any activity. These factors, self-negligence, social isolation, and irregular nutritional habits, are defined as inherent health risks, and in this study, we detected them. These factors can only be derived through long-term monitoring, but the current monitoring system for older adults is severely limited as it focuses only on emergencies, such as "falls." Therefore, in this study, the goal was to perform long-term monitoring using a camera. In order to capture the physical characteristics of the older adults, the ETRI-Activity3D data were used for training, and the skeleton-based action recognition algorithm Posec3d was used. By defining 90 frames as the time taken for one action, we built a monitoring system to enable long-term monitoring of older adult by performing multiple action detection in one video. A reliable monitoring system, with 98% accuracy, 98% precision, 99% recall, and 98% F1, was successfully established for health monitoring of older adults. This older adult monitoring technology is expected to improve the quality of medical services in a medical environment as well as the objective, activities of daily living test, which does not depend on the observer through daily life detection.
© 2022. The Author(s).