[1]孙 健,陈书恺,竺寒冰.基于神经网络的交通发生量预测研究?[J].西安建筑科技大学学报:自然科学版,2015,(02):204-0209.[doi:10.15986/j.1006-7930.2015.02.010]
 SUN Jian,CHEN Shukai,ZHU Hanbing.Research on trip generation forecasting based on BP neural network[J].J.Xi’an Univ. of Arch. & Tech.:Natural Science Edition,2015,(02):204-0209.[doi:10.15986/j.1006-7930.2015.02.010]
点击复制

基于神经网络的交通发生量预测研究?()
分享到:

西安建筑科技大学学报:自然科学版[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2015年02期
页码:
204-0209
栏目:
出版日期:
2015-04-30

文章信息/Info

Title:
Research on trip generation forecasting based on BP neural network
文章编号:
1006-7930(2015)02-0204-06
作者:
孙 健12陈书恺12竺寒冰3
(1. 上海交通大学船舶海洋与建筑工程学院, 海洋工程国家重点实验室,上海200240;
2. 上海交通大学船舶海洋与建筑工程学院,上海 200240, 3. 大连海事大学交通运输管理学院,辽宁 大连 116026)
Author(s):
SUN Jian12 CHEN Shukai12 ZHU Hanbing3
(1. State Key Laboratory of Ocean Engineering, School of Naval Architecture, Ocean and Civil Engineering, Shanghai Jiao
Tong University, Shanghai 200240, China;
2. School of Naval Architecture, Ocean and Civil Engineering, Shanghai Jiao Tong University, Shanghai 200240, China,
3. College of Transportation Management, Dalian Maritime University, Dalian 116026, China)
关键词:
预测方法BP 神经网络交通发生量聚类分析主成分分析
Keywords:
forecast method BP neural network trip generation cluster analysis principal component analysis
分类号:
U491.1
DOI:
10.15986/j.1006-7930.2015.02.010
文献标志码:
A
摘要:
交通发生吸引量预测是交通规划四阶段的首要步骤,其预测结果是城市规划布局及交通设施建设发展的重要依据.为
了提高交通发生量预测准确性,利用K-means 聚类分析对交通小区进行分组;对同组内样本小区各项土地利用及人口就业
指标进行主成分分析,通过计算主成分载荷率为选择预测影响因素提供依据;针对各组样本分别建立BP 神经网络模型,以
土地利用和人口数据作为输入变量,小区交通发生量作为输出变量,以大连市城市交通调查数据为例对上述方法进行检验,
并与传统回归模型预测结果进行比较.结果表明,在数据预处理基础上建立的BP 神经网络模型具有较高预测精度.
Abstract:
Forecasting trip generation and attraction is the first component of the four-stage method in transportation planning,
which determines the urban layout and construction of traffic facilities. To improve the accuracy of trip generation forecasting,
K-means cluster analysis was used to divide traffic zones into several groups according to the population and employment. Principal
component analysis was conducted to calculate the loading rate to principal components, providing the basis for choosing the
influence factor. Finally, BP (Back Propagation) neural networks were set up to forecast trip generation; the input included land-use
and population of each traffic zone; and the output was the trip generation. The methods were testified with the traffic survey data
from city of Dalian, Liaoning province. Moreover, the results were compared with those obtained from multiple regression model. It
is indicated that the BP neural network based on data pre-process produces better results in trip generation forecasting.

参考文献/References:

[1] 薛睿, 张建华, 孙健. 公交服务可靠性研究[J], 武汉科
技大学学报:自然科学版, 2014, 37(5): 391-396.
XUE Rui, ZHANG Jianhua, SUN jian. Reliability of
public transit service [J]. Journal of Wuhan University of
Science and Technology, 2014, 37(5): 391-396.
[2] 孙健, 章立辉, 彭春露, 等. 基于元胞自动机的城市土
地利用预测模型研究-以美国Florida 州Orange County
为例 [J]. 交通运输系统工程与信息, 2012, 12(6):
85-92.
SUN Jian, ZHANG Lihui, PENG Chunlu, et al.
CA-based urban land use prediction model: a case study
on Orange County, Florida, U. S. [J], Journal of
Transportation Systems Engineering and Information
Technology 2012, 12(6): 85-92.
[3] 石飞, 王炜, 陆建. 居民出行生成预测方法的归纳和
创新[J]. 城市交通, 2005, 3(1):43-46.
SHI Fei, WANG Wei, LU Jian. Improvement and
conclusion about resident trip generation[J]. Urban
transport of China. 2005, 3(1):43-46.
[4] CERVERO R, KOCKELMAN K. Travel demand and the
3Ds: density, diversity, and design [J]. Transportation
Research Part D: Transport And Environment, 1997,
2(3): 199-219.
[5] ELIASSON J, MATTSSON L G. A model for integrated
analysis of household location and travel choices [J].
Transportation Research Part A: Policy and Practice,
2000, 34(5): 375-394.
[6] 石飞, 江薇, 王炜, 等. 基于土地利用形态的交通生成
预测理论方法研究[J]. 土木工程学报, 2005, 38(3):
115-118.
SHI Fei, JIANG Wei, WANG Wei. Research on forecast
method for traffic creating based on characteristic of land
utilizing [J]. China Civil Engineering Journal, 2005,
38(3): 115-118.
[7] 冯树民, 慈玉生. 居民出行产生量 BP 神经网络预测
方法[J]. 哈尔滨工业大学学报,2010,42(10): 1624-1627.
FENG Shumin, CI Yusheng. A forecast method for trip
generation based on BP neural network [J]. Journal of
Harbin Institute of Technology, 2010, 42(10): 1624-1627.
[8] 杨荣英, 苗张木, 沈成武. BP 神经网络主成分分析法
在交通需求预测中的应用[J]. 武汉理工大学学报:交通
科学与工程版, 2002, 26(6): 386-388.
YANG Rongying, MAIO Zhangmu, SHEN Chengwu.
Application of principal component analysis method in
BP Neural network to traffic demand and prediction [J].
Journal of Wuhan University of Technology:
Transportation Science & Engineering, 2002, 26(6):
386-388.
[9] 宴杰. 聚类分析在家庭划分中的应用方法[J]. 交通运
输工程系统工程与信息, 2007, 7(1):137-142.
YAN Jie. The application of cluster analysis approach to
family’s type division [J]. Journal of Transportation
System Engineering and Information Technology, 2007,
7(1):137-142.
[10] 邹志云, 蒋忠海, 梅亚南, 等. 大中城市居民出行强度
的聚类分析[J]. 交通运输工程与信息学报, 2007,5(2):
8-13.
ZOU Zhiyun, JIANG Zhonghai, MEI Yanan, et al.
Cluster analysis on the trip intensity of residents in large
and medium city [J]. Journal of Transportation
Engineering and Information, 2007, 5(2): 8-13.
[11] 龙东华, 邵毅明, 向红艳. 基于神经网络的停车需求预
测模型及应用[J]. 交通信息与安全, 2010, 28(5): 6-9.
LONG Donghua, SHAO Yiming, XIANG Hongyan.
Parking demand forecasting model and its application
based on neural network [J]. Journal of Transportation
Information and Safety, 2010, 28(5): 6-9.
[12] 谭晓雨. 土地利用与交通小区发生吸引量关系研究[J].
物流技术, 2012, 31(4):33-37.
TAN Xiaoyu. Study on relationship between land use and
community-based traffic generation and attraction [J].
Logistics Technology, 2012, 31(4):33-37.
[13] 孙健, 刘琼, 彭仲仁. 城市交通拥挤成因及时空演化规
律分析-以深圳市为例, 交通运输系统工程与信息,
2011, 11(5): 86-93.
SUN Jian, LIU Qiong, PENG Zhongren. Research and
analysis on causality and spatial-temporal evolution of
urban traffic congestions-a case study on Shenzhen of
China [J], Journal of Transportation Systems Engineering
and Information Technology, 2011, 11(5): 86-93.
[14] 卓金武, 魏永生. Matlab 在数学建模中的应用[M]. 北
京: 北京航空航天大学出版社, 2011.
ZHUO Jinwu, WEI Yongsheng. MATLAB in
mathematical modeling[M]. Beijing: Beihang University
Press, 2011.
[15] RUMELHART D E, MCCLELLAND J L. Parallel
distributed processing: explorations in the microstructure
of cognition [M]. The MIT Press, Cambridge, MA. 1986.
[16] ZHANG L, PENG Z, SUND J, et al. Rule-based
forecasting of traffic flow for large-scale road networks
[J].Transportation Research Record: Journal of the
Transportation Research Board, 2012, 2279: 3-11.

备注/Memo

备注/Memo:
收稿日期:2014-06-30 修改稿日期:2015-04-15
基金项目:国家自然科学基金项目(71101109);北京大学-美国林肯土地政策研究院论文资助项目(DS20140901);长沙理工大学公路工程教育部重
点实验室开放基金项目(kfj120108)
作者简介:孙健(1977 - ),男,博士,特别研究员,博士生导师,土地利用与城市交通规划.E-mail: danielsun@sjtu.edu.cn
更新日期/Last Update: 2015-09-01