Estimating Traffic Volume Based on Sampling Expansion Technique and Geographically Weighted Poisson Regression

doi:10.11908/j.issn.0253-374x.19523

Home > Archive>Volume 48, Issue 7, 2020 >1016-1022. DOI:10.11908/j.issn.0253-374x.19523

Estimating Traffic Volume Based on Sampling Expansion Technique and Geographically Weighted Poisson Regression
DOI:
                        10.11908/j.issn.0253-374x.19523
                    
CSTR:
                        [cstr]
                    
Author:
                        JING Yi1JING Yi
Key Laboratory of Road and Traffic Engineering of the Ministry of Education，Tongji University，Shanghai 201804，China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site
LIN Hangfei1LIN Hangfei
Key Laboratory of Road and Traffic Engineering of the Ministry of Education，Tongji University，Shanghai 201804，China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site

                    
Affiliation:Key Laboratory of Road and Traffic Engineering of the Ministry of Education，Tongji University，Shanghai 201804，China
Clc Number:U491.2
Fund Project:

Article

Figures

Metrics

Reference [21]

Related [20]

Cited by

Materials

Comments

Abstract:

A method combining sampling expansion with geographically weighted Poisson regression (GWPR) was proposed to estimate the road network traffic volume with limited observation values. Firstly, a sampling expansion method based on the spatial similarity was employed to correct the imbalance missing data. Then, the GWPR was employed to estimate the hourly traffic volume of the lane considering the influence of the geometric characteristics of the road and the built environment. Results show that: compared with traditional linear models and GWPR with the original sample set, the proposed combination model has the best estimation performance. In addition, the local spatial heterogeneity of the relationship between independent variables and traffic volume is also well captured.

Key words:traffic volume estimation;imbalanced sample;geographically weighted Poisson regression(GWPR);sampling expansion;Sydney coordinated adaptive traffic system(SCATS)

Reference

[1] XIAO X, CHEN Y S, YUAN Y. Estimation of missing flow at junctions using control plan and floating car data[C]// 18th Euro Working Group on Transportation. Delft: Ewgt, 2015: 113-123.

[2] Federal Highway Administration. Traffic monitoring guide[R]. Washington D C: Federal Highway Administration, 2012.

[3] ANDERSON M D, SHARFI K, GHOLSTON S E. Direct demand forecasting model for small urban communities using multiple linear regression[J]. Transportation Research Record, 2006, 1981: 114.

[4] ZHAO F, CHUNG S. Contributing factors of annual average daily traffic in a Florida county - exploration with geographic information system and regression models[J]. Transportation Research Record, 2001, 1769: 113.

[5] MORLEY D W, GULLIVER J. Methods to improve traffic flow and noise exposure estimation on minor roads[J]. Environmental Pollution, 2016, 216: 746.

[6] SEKULA P, MARKOVIC N, VANDER LAAN Z, et al. Estimating historical hourly traffic volumes via machine learning and vehicle probe data: a Maryland case study[J]. Transportation Research Part C-Emerging Technologies, 2018, 97: 147.

[7] CASTRO-NETO M, JEONG Y, JEONG M K, et al. AADT prediction using support vector regression with data-dependent parameters[J]. Expert Systems with Applications, 2009, 36(2): 2979.

[8] WU J Q, XU H. Annual average daily traffic prediction model for minor roads at intersections[J]. Journal of Transportation Engineering Part A-Systems, 2019, 145(10): 100.

[9] EOM J K, PARK M S, HEO T Y, et al. Improving the prediction of annual average daily traffic for nonfreeway facilities by applying a spatial statistical method[J]. Artificial Intelligence and Advanced Computing Applications, 2006 (1968): 20.

[10] SELBY B, KOCKELMAN K M. Spatial prediction of traffic levels in unmeasured locations: applications of universal kriging and geographically weighted regression[J]. Journal of Transport Geography, 2013, 29: 24.

[11] WANG X K, KOCKELMAN K M. Forecasting network data spatial interpolation of traffic counts from texas data[J]. Transportation Research Record, 2009, 2105: 100.

[12] YU H T, PENG Z R. Exploring the spatial variation of ridesourcing demand and its relationship to built environment and socioeconomic factors with the geographically weighted Poisson regression[J]. Journal of Transport Geography, 2019, 75: 147.

[13] BRUNSDON C, FOTHERINGHAM A S, CHARLTON M E. Geographically weighted regression: a method for exploring spatial nonstationarity[J]. Geographical Analysis, 1996, 28(4): 281.

[14] YANG H T, LU X Z, CHERRY C, et al. Spatial variations in active mode trip volume at intersections: a local analysis utilizing geographically weighted regression[J]. Journal of Transport Geography, 2017, 64: 184.

[15] ZHAO F, PARK N. Using geographically weighted regression models to estimate annual average daily traffic[J]. Transportation Research Record, 2004(1879): 99.

[16] TAJMAJER T, SPLAWINSKA M, WASILEWSKI P, et al. Predicting annual average daily highway traffic from large data and very few measurements[C]// 2016 Ieee International Conference on Big Data. Washington D C:

[17] CHEN P, HU S H, SHEN Q, et al. Estimating traffic volume for local streets with imbalanced data[J]. Transportation Research Record, 2019, 2673: 598.

[18] LESAGE J,PACE R K. Introduction to spatial econometrics [M]. Boca Raton:Chapman and Hall,2009.

[19] WANG C H, CHEN N. A geographically weighted regression approach to investigating the spatially varied built-environment effects on community opportunity[J]. Journal of Transport Geography, 2017, 62: 136.

[20] 杨浦区统计局. 2017年杨浦统计年鉴[R]. 上海:上海杨浦区统计局, 2017.

[21] SCATS. Why choose SCATS? [EB/OL]. [2019-9-15]. https://www.scats.com.au/why-choose-scats-performance.html.

Get Citation

JING Yi, LIN Hangfei. Estimating Traffic Volume Based on Sampling Expansion Technique and Geographically Weighted Poisson Regression[J].同济大学学报(自然科学版),2020,48(7):1016~1022

Copy

Article Metrics

Abstract:605
PDF: 1171
HTML: 359
Cited by: 0

History

Received:December 13,2019
Revised:
Adopted:
Online: August 04,2020
Published:

Get Citation

Share

Article Metrics

History

Article QR Code