Self-Adaptive Traffic Recommendation System Beijing City as a Case Study

Due to the widespread use of smart phones, location-based services (LBS) has become important in all aspects of human's life. LBS offer many advantages to the mobile users to retrieve information about their location. Some LBS services use the smartphone's location and service provider information to offer directions, targeted recommendations, or other location-specific information to the user. In this paper we proposed a novel location-based method that provides a traffic recommendation based on community contributed and collaborated movement history. Proposed model is designed to perform some computational processes on the data collected from real users and decide which path is better to follow to reach the desired destination from a given source location. Proposed method mine places and paths between places from the raw data and analyse these data to provide a recommendation to reach a specific target location. Proposed method is adaptable for new movement information. We use a dataset for Beijing city as a case study to proof our proposed method.