Activity‐based model based on multi‐day cellular data: Considering the lack of personal attributes and activity type

• Published in: IET intelligent transport systems Vol. 17; no. 12; pp. 2474 - 2492
• Main Authors: Guo, Yudong, Yang, Fei, Yan, Haomin, Xie, Siyuan, Liu, Haode, Dai, Zhuang
• Format: Journal Article
• Language: English
• Published: Wiley 01.12.2023
• Subjects: demand forecasting; traffic; traffic and demand managing; traveller information
• ISSN: 1751-956X; 1751-9578
• DOI: 10.1049/itr2.12425

Cellular data is a sequence of base station‐interaction data that records user ID, timestamp, location area code (LAC), and cell identity (CID). With long observation periods, the data allows traffic planners to analyze coarse‐granularity user travel behaviours at low costs. However, utilizing cellular data for urban planning is not an easy task as the data lacks user socioeconomic attributes due to privacy issues. The data is also challenging to recognize user activity types. This paper proposed an activity‐based model (ABM) with skeleton schedule constraints for multi‐day cellular data. The model first infers the activity pattern and home location. Then it predicts start time, duration, and locations separately for primary and secondary activities. Next, the model infers the travel mode and path considering user multi‐day travel behaviour, path non‐linear coefficient, and transfers. Finally, a time adjustment module is proposed to avoid time conflicts in consecutive activities. The proposed activity‐based model is validated at activity, travel, and path levels. Results show that the proposed model can effectively predict activities and has much higher stability than existing ABMs based on travel surveys. We proposed an improved ABM framework for the multi‐day cellular data. The model makes up for the lack of personal socioeconomic attributes and activity types in cellular data. It also considers the skeleton schedules of users and leverages multiple machine learning algorithms to predict the activity start times, locations, and durations. This study provides new insights for improving ABMs for big data.