A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Inferring the trip purposes and uncovering spatio-temporal activity patterns from dockless shared bike dataset in Shenzhen, China
Abstract Trip purpose is closely related to travel patterns and plays an important role in urban planning and transportation management. Recently, there has been a growing interest in investigating the spatio-temporal patterns of dockless shared-bike usage and its influencing mechanisms. Few, however, have focused on revealing the travel patterns by inferring the purpose of dockless shared-bike trips at the individual level. We present a framework for inferring the purpose of dockless shared-bike users, based on gravity model and Bayesian rules, and conduct it in Shenzhen, China. We consider the comprehensive factors including distance, time, environment, activity type proportion, and service capacity of points of interest (POIs), the last two factors of which were usually neglected in previous transport studies. Especially, we integrated areas of interest (AOIs) and Tencent User density (TUD) social media data characterize the service capacity of POIs, which reflect the area and scale differences of different POI categories. Through the comparison between two improved models and the basic model, it is demonstrated that the introduction of activity type proportion and service capacity of POIs can improve the effectiveness of model for inferring the purposes of dockless shared-bike trips. Based on the obtained trip purposes, we further explore the spatio-temporal patterns of different activities and gain some insights into bike travel demand, which can inform scientific decisions for bicycle infrastructure planning and dockless shared- bike management.
Highlights This study presents a framework for inferring the purpose of dockless shared-bike users. The study considers comprehensive factors including distance, time, environment, activity type proportion, and POI service capacity. The results demonstrate that the model incorporating all the factors is effective for inferring the purpose of dockless shared-bike trips. The spatio-temporal patterns of different activities provide some insights into bike travel demand.
Inferring the trip purposes and uncovering spatio-temporal activity patterns from dockless shared bike dataset in Shenzhen, China
Abstract Trip purpose is closely related to travel patterns and plays an important role in urban planning and transportation management. Recently, there has been a growing interest in investigating the spatio-temporal patterns of dockless shared-bike usage and its influencing mechanisms. Few, however, have focused on revealing the travel patterns by inferring the purpose of dockless shared-bike trips at the individual level. We present a framework for inferring the purpose of dockless shared-bike users, based on gravity model and Bayesian rules, and conduct it in Shenzhen, China. We consider the comprehensive factors including distance, time, environment, activity type proportion, and service capacity of points of interest (POIs), the last two factors of which were usually neglected in previous transport studies. Especially, we integrated areas of interest (AOIs) and Tencent User density (TUD) social media data characterize the service capacity of POIs, which reflect the area and scale differences of different POI categories. Through the comparison between two improved models and the basic model, it is demonstrated that the introduction of activity type proportion and service capacity of POIs can improve the effectiveness of model for inferring the purposes of dockless shared-bike trips. Based on the obtained trip purposes, we further explore the spatio-temporal patterns of different activities and gain some insights into bike travel demand, which can inform scientific decisions for bicycle infrastructure planning and dockless shared- bike management.
Highlights This study presents a framework for inferring the purpose of dockless shared-bike users. The study considers comprehensive factors including distance, time, environment, activity type proportion, and POI service capacity. The results demonstrate that the model incorporating all the factors is effective for inferring the purpose of dockless shared-bike trips. The spatio-temporal patterns of different activities provide some insights into bike travel demand.
Inferring the trip purposes and uncovering spatio-temporal activity patterns from dockless shared bike dataset in Shenzhen, China
Li, Shaoying (author) / Zhuang, Caigang (author) / Tan, Zhangzhi (author) / Gao, Feng (author) / Lai, Zhipeng (author) / Wu, Zhifeng (author)
2021-01-26
Article (Journal)
Electronic Resource
English
Inferring trip purposes and uncovering travel patterns from taxi trajectory data
| Online Contents | 2016