Similarity-ranking method based on semantic computing for a context-aware system
Motoki Yokoyama, Yasushi Kiyoki, Tetsuya Mita · 2016
Among the enormous variety of data in recent years, transportation data contain significant potential for understanding the information requirements and intention of passengers. In this paper, we propose a new information ranking method for passenger intention prediction and service recommendation. The method includes three main features, which include (1) predicting the intention of a used based on his/her current context, (2) selecting a subspace for service recommendation, and (3) ranking the services by the highest relevant order. By comparing the predicted results with a straightforward computation method, the experimental studies show the effectiveness and efficiency of the proposed method. The paper also describes the simplicity of our method over existing subspace selection methods.