Understanding passenger behaviors is of great importance in intelligent transportation and infrastructure planning. However, the passenger trajectories are actually complex temporal data, which consist of rich spatial and temporal information. What’s more, the observed passenger trajectories may be a mixture of different types of passengers with various travelling purposes. These difficulties make the prediction of passenger behaviors a challenging work. To address these problems, this paper improves the existing passenger behavior prediction methods from the following two aspects: 1) Encoding the travelling sequence with personalized semantic sensing, and 2) constructing multi-pattern prediction models to capture multiple travelling purposes and dynamics. Along this line, this paper provides a novel passenger behavior prediction model, namely, Semantic and multi-Pattern Long Short-Term Memory (SP-LSTM) model. Particularly, 1) a translation unit is designed, which is able to encode an observed travelling sequence into a structured sequence with consideration of individual travelling semantics; 2) a multi-pattern learning schematic is proposed, which first identifies the travelling patterns of passengers and then handles different patterns with different learning modules; 3) a unified learning framework is provided to integrate the semantic sensing module and multi-pattern learning module together, and present the final prediction results. To evaluate the proposed method, this paper conducts experiments on real-world passenger travelling data. Results demonstrate the superiority of SP-LSTM over both classical and the state-of-the-art methods.

Introduction

Public transportation plays an important role in daily life of residents, especially in metropolises such as New York, USA and Beijing, China. On the one hand, data mining and machine learning have undergone a rapid development in the recent years, machine-learning technology powers many aspects of modern society [1]; on the other hand, we have accumulated a large amount of transportation data, such as NYC Taxi Open Data [2], Uber Trip Data, Taxi Trip Records and so on. Hence, an opportunity of improving the public transportation service by data-driven solutions and strategies has been witnessed by many scholars such as [12]–[۱۶]. This paper focuses on modelling passenger behaviors and predicting passengers’ next stations. By doing this, we can help the government and enterprises optimize to dispatch the transportation resources, and also help the citizens to circumvent the crowded stations. As shown in Fig. 1, If travelling behaviors of passengers can be predicted precisely, a better traffic route planning can be made for workers with regular moving patterns, such as P1 and P3, and recommended routes or tourism products can be provided for travelers shown as P2.