Intercity Traffic Travel Mode Identification Method Based on Mobile Signalling Data

Abstract

With the popularity of mobile devices, the signalling data generated by them provides significant opportunities for studying intercity travel behaviour in terms of data scale and information continuity. However, due to the low quality of the data in spatial accuracy, temporal frequency, and traffic semantics, the accuracy of identifying individual travel modes is low and it is difficult to extend to complex traffic scenarios. In this paper, we propose a new framework for identifying individual intercity travel modes based on mobile signalling data. The framework includes components for data pre-processing, geo-information mapping, feature and attribute extraction, and travel mode recognition. We utilize a comprehensive detection model to identify users’ multimodal intercity transport behaviour. Using two modules, Random Forest Embedding (RFE) and Bidirectional Long Short-Term Memory (Bi-LSTM), the model can capture the spatiotemporal characteristics and complex multi-stage associations in intercity travel chains. A large-scale mobile phone dataset from Jiangsu Province, China, was used for verification. The results showed that, on average, the method was able to detect travel mode with 92% accuracy. This study provides valuable support for further research on individual travel behaviour and the enhancement of transportation planning.