Taxi trips distribution modeling based on Entropy-Maximizing theory: A case study in Harbin city—China

Understanding Origin–Destination distribution of taxi trips is very important for improving effects of transportation planning and enhancing quality of taxi services. This study proposes a new method based on Entropy-Maximizing theory to model OD distribution in Harbin city using large-scale taxi GP...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Physica A Ročník 493; s. 430 - 443
Hlavní autoři: Tang, Jinjun, Zhang, Shen, Chen, Xinqiang, Liu, Fang, Zou, Yajie
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier B.V 01.03.2018
Témata:
[formula omitted]-means clustering method
Entropy-Maximizing model
Generalized cost function
Taxi GPS data
Traffic distribution
Taxi GPS data
K-means clustering method
Traffic distribution
Entropy-Maximizing model
Generalized cost function
ISSN:0378-4371, 1873-2119
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Understanding Origin–Destination distribution of taxi trips is very important for improving effects of transportation planning and enhancing quality of taxi services. This study proposes a new method based on Entropy-Maximizing theory to model OD distribution in Harbin city using large-scale taxi GPS trajectories. Firstly, a K-means clustering method is utilized to partition raw pick-up and drop-off location into different zones, and trips are assumed to start from and end at zone centers. A generalized cost function is further defined by considering travel distance, time and fee between each OD pair. GPS data collected from more than 1000 taxis at an interval of 30 s during one month are divided into two parts: data from first twenty days is treated as training dataset and last ten days is taken as testing dataset. The training dataset is used to calibrate model while testing dataset is used to validate model. Furthermore, three indicators, mean absolute error (MAE), root mean square error (RMSE) and mean percentage absolute error (MPAE), are applied to evaluate training and testing performance of Entropy-Maximizing model versus Gravity model. The results demonstrate Entropy-Maximizing model is superior to Gravity model. Findings of the study are used to validate the feasibility of OD distribution from taxi GPS data in urban system. •This study proposes Entropy-Maximizing theory to model OD distribution.•K-means clustering method is utilized to finish zones partition.•A generalized cost function is defined by considering travel distance, time and fee.•Three indicators are applied to evaluate performance of proposed model.•The results demonstrate Entropy-Maximizing model is superior to traditional Gravity model.
ISSN:0378-4371
1873-2119
DOI:10.1016/j.physa.2017.11.114