Human activity recognition model based on Decision tree

In daily life, people carry smartphones every where. The sensors included in smartphones can tell us much information. Activity recognition by smartphone can be used for healthcare and sports management. People carry smartphones in different positions, such as the pocket of the trousers, hands or bags. We use accelerometer embedded in the smartphones to classify five activities, such as staying still, walking, running, and going upstairs and downstairs. This work analysis behavior data from accelerometer, extract various features, choose highly correlated features, and construct an activity recognition model based on location-independent smartphone. We construct models based on ( behavior, position) vector, position and behavior. Compare all these models, behavior based recognition model gain the highest accuracy and lest time-consuming, which can effectively identify human behavior.