CONFIDENCE LEVEL of A MOTION FEEDBACK SYSTEM for ANALYZING EXERCISE TRAINING EFFICACY

ABSTRACT

The increase in aged population is a global trend. Inculcating healthy behaviors such as regular exercises in the elderly has a significant impact on the financial and medical burden globally. Moreover, air pollution and the outbreak of the coronavirus disease 19 (COVID-19) pose a serious threat to public health. In order to improve the health conditions of the population, this study developed a motion feedback system named MoveV that can be used for several indoor training exercises. This system provides instant motion feedback by synchronizing exercise training videos on the website using a motion analysis algorithm that is applicable on smartphones, and a cloud database platform is used to record health behaviors. Feature extraction is performed based on force intensity, motion velocity, and exercise direction. The resultant accuracy of the motion feedback system was tested by a motion science expert and presented as the confidence level. For perfect movement, a confidence level of up to 90.5% was achieved, indicating that the MoveV system was able to record users' exercise frequency and distinguish whether the user was performing well in the exercise movements. The proposed system is convenient and does not incur additional expenditure by purchasing any new device. Furthermore, it provides visual and voice feedback, companionship, and exercise motivation to the users, all of which are important factors when using online exercise platforms.