Prediction-based Unobstructed Route Planning

With the increasing availability of human-tracking data (e.g., public transport IC card data), human mobility prediction is increasingly important. In this light, we study a novel problem of using human-tracking data to predict human mobility and to find over-crowded stations, and then planning unobstructed routes to avoid over-crowded stations. We believe that this study can bring significant benefits to users in many useful mobile applications such as route planning and recommendation, urban computing, and location based services in general. The problem is challenging by two difficulties: (1) how to detect crowded stations effectively, and (2) how to find unobstructed routes efficiently. To overcome these difficulties, we propose three human-mobility prediction methods based on uniform distribution, standard normal distribution, and priority ranking, to predict human mobility and to detect over-crowded stations. Then, we develop two probabilistic algorithms to plan unobstructed routes efficiently. The performance of the developed algorithms has been verified by extensive experiments on synthetic spatial data.