 This paper proposes a novel approach to assessing physical performance in older adults by utilizing wearable sensors to measure the duration of various activities. The authors tested five different types of sensors at different locations on the body and found that the best results were achieved when the sensors were placed on the wrist and ankle. They then used a convolutional neural network to analyze the data collected from these sensors and accurately predict the duration of each activity. The results showed that the proposed method can be used to accurately predict the duration of each activity with an average error of less than two seconds. This article was authored by Yi Yunzhang, Xiang Yuwang, Peng Xianhan, and others.