Trip mode identification has wide applications in transportation planning and management. The existing methods primarily use GPS data collected from mobile devices. These methods can achieve relatively high accuracy, but they have limitations in quantity, coverage, and computational complexity. This paper proposes a trip mode identification method based on mobile phone signaling data. The method mainly consists of three parts: activity node recognition, travel time computation, and clustering with a Gaussian mixed model. Experiments of the method using real mobile phone signaling data in Shanghai were performed, and the results show that the proposed method can achieve acceptable accuracy.
展开▼
