Energy-Efficient Activity Recognition on Smartphone

In recent years, with the rapid development of smart phones, smart phones have become indispensable in our life. We can monitor human activities by the built-in sensors of the smartphone, and extract useful information for human services, such as human health, life log or assistance tips. In fact, this is a very low cost and efficient method. In previous research we have classified the walking style by Decision Tree. In order to recognize the activities more precisely and comprehensively, in this paper we used Decision Tree and SVM to learn the collected data on the smartphone, meanwhile considering the energy-efficiency problem around it.