Traffic Session Identification Based on Statistical Language Model

摘要

Session identification has attracted a lot of attention as it can play an important role in discovering useful patterns. A traffic session is a sequence of camera locations orderly passed by a vehicle to achieve a certain task. Based on the observations that both navigation regularity and temporal factor are crucial in determining the session boundaries, we propose an improved statistical language model which takes both factors into consideration in this paper. Extensive experiments are conducted on a real traffic dataset to testify the effectiveness of our proposal, and the result demonstrates its effectiveness compared to other alternative methods including the timeout method and the classic language model.