Phone‐vehicle trajectory matching framework based on ALPR and cellular signalling data

With the advancement of positioning techniques, a large amount of trajectory data has been produced. Matching vehicles with mobile phones using different trajectories can benefit many applications, such as driving behaviour analysis and travel mode split. Moreover, as a privacy attack method, it can provide theoretical inspiration for privacy protection theory. To address this problem, a new trajectory matching framework for processing massive Automatic License Plate Recognition (ALPR) and cellular signalling data is proposed. Information entropy was adopted to address the movement frequency of trajectories and then the infrequent vehicles and phones that did not meet the threshold were pruned. Next, an effective matching algorithm was devised to match the trajectories of vehicles and mobile phones. Moreover, to solve the problem of obtaining a small number of matching results, a data augmentation algorithm was proposed to add new, matching records. Last, a classification model was constructed with LightGBM to determine whether the vehicle matches the phone. Experimental results on real datasets show that the framework outperforms typical techniques in terms of effectiveness and efficiency. The data obtained by data augmentation have distribution characteristics similar to those of the original data. The proposed classification model achieves an accuracy of 93.6%.