Abstract

This experiment examined the physical activity recognition model to access the relationship between sensors, the single tri-axial accelerometer and single tri-axial gyroscope, and fitness recognition (sitting, standing, walking, and running). We experimented with sixteen students (62.5% male and 37.5% female, age between eighteen through twenty- three year old) of the Informatics school at Walailak University. We had the experimental setup to evaluate model performance for baseline models, booting ensemble model, and begging ensemble model. When we measured model's performance, we found the follows results. First, the baseline models performance has the highest accuracy level with KNN: k-Nearest Neighbor with k = 9 is 95.47%. Second, The Boosting ensemble models performance has the highest accuracy level with C5.0: C5.0 is 95.63%. Third, The Bagging ensemble models performance has the highest accuracy level with RF: Random Forest is 95.69%. Fourth, The Stacking ensemble models performance has the highest accuracy level with KNN is 95.52%. So, we concluded that RF has the highest performance with accuracy level at 95.69%. In the future work, we planned to get more accuracy model by adding more features from another sensor, heart rate. Mining data collected from sensors provide valuable result in the physical activity recognition area. The improvement in performance is required especially in the healthcare field. The more increasing of using the wearable device, the broader opportunity in the data mining research area can be.