A Smartphone-Based Real-Time Simple Activity Recognition

This paper explores a physical activity monitoring application in smartphones. The combination of smartphone application and sensors could perform as a biomedical sensor to monitor physical activities. Thai 3 Axis (TH3AX) was developed as a real-time physical activities monitoring application such as standing, walking, and running. The smartphone was attached to right hip of 10 young, healthy adult subjects to collect accelerometer data to determine threshold range for each activity. After finding thresholds, the results were used as range for a predictive model of activity recognition. The second experiment was scheduled with 6 young healthy subjects performed three physical activities (standing, walking, and running) to evaluate TH3AX application. Then, a diagnostic test was computed to test TH3AX's sensitivity, specificity, and accuracy. Results showed that TH3AX sensitivity, specificity, and accuracy are 0.981, 0.988, and 0.986, respectively.