A Prediction Method of User Destination Using Historical Crowd Movement

Prediction of a moving user’s destination using location information obtained from smart devices is important in advancing information delivery services. This paper proposes a prediction method of user destination using data for each means of transportation. In the method, the number of people moving from one grid to another is calculated for the purpose of destination prediction. Then, this paper works to improve the accuracy of the prediction with data organized by means of transport. Experimental results showed that the proposed method improved the prediction accuracy by considering the mean of transportation when using crowd mobility patterns.