RECOGNIZING TRANSPORTATION MODE ON MOBILE PHONE USING PROBABILITY FUSION OF EXTREME LEARNING MACHINES

Abstract

As one important clue to understand people's behavior and life pattern, transportation mode (such as walking, bicycling, taking bus, driving, taking light-rail or subway, etc.) information has already widely used in mobile recommendation, route planning, social networking and health caring. This paper proposes a transportation mode recognition method using probability fusion of extreme learning machines (ELMs). Two ELM classification models are trained to recognize accelerometer data and Global Positioning System (GPS) data, respectively. Fuzzy output vectors of these two ELMs are transformed into probability vectors and fused to determine the final result. Experimental results verify that the proposed method is effective and can obtain higher recognition accuracy than traditional fusion methods.