摘要：In these days, smart-phone becomes a major personal communication device and more and more hardware including various sensors as well as software including various applications tend to be mounted on it. In this paper, we propose a classification scheme that classifies ambulatory movements of the user and the floor where the user exists with a smart-phone. In the proposed scheme, ambulatory movements of the user are classified by exploiting the barometer and the accelerometer, while the GPS data is used to classifies the floor information. With the proposed scheme, various motions, such as walking, stop, up and down motions with elevator or stairs, are distinguished by utilizing the data from the barometer and the accelerometer. When the user enters a building, the building information is confirmed with the GPS information and the smart-phone can classify ambulatory movements and the floor information of the user. An Android application is developed for the performance evaluation of the proposed scheme. The proposed scheme is evaluated with experiments at general building in university and the accuracy of the proposed scheme is more than 94% for floor estimation, although there is still works to improve the estimation of movements.
