A Comparative Study of Deep Learning for Monitoring Motor Behavior in Older Adults

Elderly people need to strengthen their muscle strength and improve their balance ability to prevent falls and chronic diseases. In this study, we modified the existing image classification-based model and performed regression analysis to accurately monitor the motor movements of the elderly. We also proposed a deep learning technique to improve the performance of the model by optimizing the network structure and learning method, and compared the performance. Through this, we derived the most suitable model for monitoring the motor movements of the elderly. This study is expected to contribute to the health care and safety of the elderly.