|Table of Contents|

Regional mining of urban residents' travel demand based on taxi order trajectory data(PDF)

长安大学学报（自然科学版）[ISSN:1006-6977/CN:61-1281/TN]

Issue:
2022年4期
Page:
108-117
Research Field:
交通工程
Publishing date:

Info

Title:
Regional mining of urban residents' travel demand based on taxi order trajectory data
Author(s):
JIAO Ping1;  MA Ning-yuan2;  DUAN Ya-xin2;  ZHAO Jian-nan2;  GENG Xin-rui3;  SUN Lu4
(1. School of Economics and Management, Xi'an Aeronautical University, Xi'an 710077, Shaanxi, China; 2. College of Transportation Engineering, Chang'an University, Xi'an 710064, Shaanxi, China; 3. BYD Automotive Industry Co., Ltd, Shenzhen 518118, Guangdong, China; 4. Xi'an Transportation Development Research Center, Xi'an 710082, Shaanxi, China)
Keywords:
traffic engineering;  travel demand;  spatial-temporal distribution characteristic;  grey prediction model;  focus statistics algorithm;  taxi order trajectory
PACS:
U491.1
DOI:
10.19721/j.cnki.1671-8879.2022.04.011
Abstract:
In order to dig deeper into the travel characteristics of urban residents and the spatio-temporal characteristics of taxi operation, the passenger hot spots area, high-income orders areas, high average order revenue areas, and high-income passenger areas were defined as the target areas. The spatio-temporal distribution of the target areas was compared and analyzed, and the spatio-temporal distribution characteristics of urban residents' travel demand areas were mined by taking Xi'an as an example. Firstly, a regular hexagon Tyson polygon was used to mesh the target area. Secondly, six indexes which including namely total order quantity, mileage utilization rate, average revenue per hour, average passenger time, average passenger distance, and average empty driving distance were determined to establish the grey decision model. Then the time period with high taxi operating efficiency in Xi'an was obtained, and the target area was extracted based on the focus statistical algorithm.The results show that taxi operating efficiency in Xi'an is higher in 08:01 to 09:00, 14:01 to 15:00, 17:01 to 18:00 and 21:01 to 22:00. The distribution of high-income order areas represents the distribution of residents' long-distance travel demand, and its spatio-temporal variation changes little, which mainly aggregate near transportation hubs. Most of the areas with high average order revenue areas are outside the main urban area ofXi'an, and the travel demand of residents is difficult to meet. Due to the influence of traffic congestion and other factors, the passenger hot spots area of taxis are not completely high-income areas. The research results can be used as references to analyze the travel characteristics of residents in Xi'an, the income improvement of taxi drivers, and the policy formulation of urban public transport planning departments.5 tabs, 9 figs, 24 refs.

References:

[1] QI H,LIU P P.Mining taxi pick-up hotspots based on spatial clustering[C]//IEEE.Proceedings of 2018 IEEE Smart World,Ubiquitous Intelligence & Computing,Advanced & Trusted Computing,Scalable Computing & Communications,Cloud & Big Data Computing,Internet of People and Smart City Innovation.New York:IEEE,2018:1711-1717.
[2]HUANG Z H,GAO S B,CAI C X,et al.A rapid density method for taxi passengers hot spot recognition and visualization based on DBSCAN+[J].Scientific Reports,2021,11:9420.
[3]张 煊,刘 勇,侯全华,等.基于GIS热点技术的低碳出行街区建成环境特征探析[J].长安大学学报(自然科学版),2018,38(1):89-97.
ZHANG Xuan,LIU Yong,HOU Quan-hua,et al.Characteristics of built environment in low-carbon travel block based on GIS hotspot technology[J].Journal of Chang'an University(Natural Science Edition),2018,38(1):89-97.
[4]曲昭伟,王 鑫,宋现敏,等.基于出租车GPS大数据的城市热点出行路段识别方法[J].交通运输系统工程与信息,2019,19(2):238-246.
QU Zhao-wei,WANG Xin,SONG Xian-min,et al.Urban hotspot travel section identification method based on taxi GPS large data[J].Journal of Transportation Systems Engineering and Information Technology,2019,19(2):238-246.
[5]YU H,CHEN X F,LI Z N,et al.Taxi-based mobility demand formulation and prediction using conditional generative adversarial network-driven learning approaches[J].IEEE Transactions on Intelligent Transportation Systems,2019,20(10):3888-3899.
[6]NIU K,CHENG C,CHANG J L,et al.Real-time taxi-passenger prediction with L-CNN[J].IEEE Transactions on Vehicular Technology,2019,68(5):4122-4129.
[7]RODRIGUES F,MARKOU I,PEREIRA F C.Combining time-series and textual data for taxi demand prediction in event areas:A deep learning approach[J].Information Fusion,2019,49:120-129.
[8]SHEN J W,LIU X T,CHEN M.Discovering spatial and temporal patterns from taxi-based floating car data:A case study from Nanjing[J].GIScience & Remote Sensing,2017,54(5):617-638.
[9]YU H,LI Z N,ZHANG G H,et al.Extracting and predicting taxi hotspots in spatiotemporal dimensions using conditional generative adversarial neural networks[J].IEEE Transactions on Vehicular Technology,2020,69(4):3680-3692.
[10]DONG Y Q,ZHANG Z,FU R,et al.Revealing New York taxi drivers' operation patterns focusing on the revenue aspect[C]//IEEE.Proceedings of 12th World Congress on Intelligent Control and Automation(WCICA).New York: IEEE,2016:1052-1057.
[11]QIN G Y,LI T N,YU B,et al.Mining factors affecting taxi drivers' incomes using GPS trajectories[J].Transportation Research Part C,2017,79:103-118.
[12]YUAN C W,GENG X R,MAO X H.Taxi high-income region recommendation and spatial correlation analysis[J].IEEE Access,2020,8:139529-139545.
[13]OOSTENDORP R,GEBHARDT L.Combining means of transport as a users' strategy to optimize traveling in an urban context:Empirical results on intermodal travel behavior from a survey in Berlin[J].Journal of Transport Geography,2018,71:72-83.
[14]CHENG L,DE VOS J,SHI K B,et al.Do residential location effects on travel behavior differ between the elderly and younger adults?[J].Transportation Research Part D,2019,73:367-380.
[15]魏海涛,肖天聪,胡宝生,等.基于出租车GPS数据的居民出行行为和城市空间结构分析:以北京市为例[J].上海城市规划,2020(1):69-76.
WEI Hai-tao,XIAO Tian-cong,HU Bao-sheng,et al.Analysis of residents travel behavior and urban spatial structure based on Beijing taxi GPS data[J].Shanghai Urban Planning Review,2020(1):69-76.
[16]HE B,LIU K,XUE Z,et al.Spatial and temporal characteristics of urban tourism travel by taxi:A case study of Shenzhen[J].ISPRS International Journal of Geo-Information,2021,10(7):445.
[17]张俊涛,武 芳,张 浩.利用出租车轨迹数据挖掘城市居民出行特征[J].地理与地理信息科学,2015,31(6):104-108.
ZHANG Jun-tao,WU Fang,ZHANG Hao.Urban residents travel characteristics mining utilizing taxi trajectory data[J].Geography and Geo-Information Science,2015,31(6):104-108.
[18]郑林江,赵 欣,蒋朝辉,等.基于出租车轨迹数据的城市热点出行区域挖掘[J].计算机应用与软件,2018,35(1):1-8.
ZHENG Lin-jiang,ZHAO Xin,JIANG Zhao-hui,et al.Mining urban attractive areas using taxi trajectory data[J].Computer Applications and Software,2018,35(1):1-8.
[19]冯慧芳,周丹凤.基于GPS轨迹挖掘的城市空间动态交互特征研究[J].交通运输系统工程与信息,2020,20(3):163-168.
FENG Hui-fang,ZHOU Dan-feng.Dynamic interaction of urban space based on GPS trajectory mining[J].Journal of Transportation Systems Engineering and Information Technology,2020,20(3):163-168.
[20]吴华意,黄 蕊,游 兰,等.出租车轨迹数据挖掘进展[J].测绘学报,2019,48(11):1341-1356.
WU Hua-yi,HUANG Rui,YOU Lan,et al.Recent progress in taxi trajectory data mining[J].Acta Geodaetica et Cartographica Sinica,2019,48(11):1341-1356.
[21]CHEN L,GAO Y,ZHU D,et al.Quantifying the scale effect in geospatial big data using semi-variograms[J].PLoS One,2019,14(11):e0225139.
[22]谢乃明.灰色系统建模技术研究[D].南京:南京航空航天大学,2008.
XIE Nai-ming.Research on the methods of grey systems modeling[D].Nanjing:Nanjing University of Aeronautics and Astronautics,2008.
[23]党耀国,刘思峰,刘 斌.基于区间数的多指标灰靶决策模型的研究[J].中国工程科学,2005,7(8):31-35.
DANG Yao-guo,LIU Si-feng,LIU Bin.Study on the multi-attribute decision model of grey target based on interval number[J].Engineering Science,2005,7(8):31-35.
[24]刘思峰,杨英杰.灰色系统研究进展(2004～2014)[J].南京航空航天大学学报,2015,47(1):1-18.
LIU Si-feng,YANG Ying-jie.Advances in grey system research(2004 to 2014)[J].Journal of Nanjing University of Aeronautics & Astronautics,2015,47(1):1-18.

Memo

Memo:
-
Last Update: 2022-07-20