Activity-travel pattern inference based on multi-source big data

Abstract

We provide a comprehensive review of the literature on inferring activity-travel patterns (ATP) using multi-source big data; the increasing number of publications over time on this subject, demonstrates the importance of big data in this task. Our aims are to identify the advantages and research gaps in ATP inference and to promote further developments in this field. We clarify the fundamental concepts (i.e. ATP and its components), commonly used data sources, and inference processes employed in ATP inference studies. Emphasis is placed on two prominent big data sources: mobile phone data and smart card data. We outline the various approaches involved in the inference process, and we highlight existing shortcomings in data sources, ATP inference methodologies, and result validation. Based on the review, it is evident that future research should address several limitations in ATP inference. Firstly, it is necessary to improve the comprehensive understanding of ATP and understand the interrelationships among its different components. Secondly, it is necessary to integrate different data sources and leverage their respective strengths to gain deeper insights into activity-travel behaviour. Lastly, further investigation into emerging technologies such as artificial intelligence in ATP inference is warranted to improve inference accuracy. The findings of this study could provide valuable insights for policy makers, enabling them to gain a deeper understanding of activity-travel choice behaviour and develop more effective policies related to transportation system.