[논문]함수회귀분석을 통한 교통량 예측

이인주; 이영경

doi:10.5351/kjas.2021.34.5.773

함수회귀분석을 통한 교통량 예측
Functional regression approach to traffic analysis 원문보기

응용통계연구 = The Korean journal of applied statistics, v.34 no.5, 2021년, pp.773 - 794

이인주 (강원대학교 통계학과) , 이영경 (강원대학교 통계학과)

초록
AI-Helper

교통량 예측은 지방 행정의 의사결정에 매우 중요한 정보를 제공한다. 교통량 예측을 통해 교통혼잡비용을 줄이고 지역경제를 활성화 함으로써 사회적, 경제적 이익을 창출할 수 있다. 교통량은 미지의 확률적 규칙하에서 시간의 흐름에 따라 궤적을 가지며 변화하는 함수데이터의 일종이다. 본 논문에서는 세 가지 함수회귀모형을 이용하여 과거에 관측된 교통량 궤적을 기반으로 미래의 관측되지 않은 교통량 궤적을 예측하는 방법을 제시한다. 본 논문에서 소개하는 세가지 방법은 전국 고속도로 영업소 중 서울, 춘천, 강릉 세 개 영업소에서 수집된 고속도로 영업소 데이터에 적용한다. 각 영업소 별로 세가지 방법의 예측오차를 비교함으로써 영업소별 최적 교통량 예측모형을 찾는다.

Abstract ▼ AI-Helper

Prediction of vehicle traffic volume is very important in planning municipal administration. It may help promote social and economic interests and also prevent traffic congestion costs. Traffic volume as a time-varying trajectory is considered as functional data. In this paper we study three functional regression models that can be used to predict an unseen trajectory of traffic volume based on already observed trajectories. We apply the methods to highway tollgate traffic volume data collected at some tollgates in Seoul, Chuncheon and Gangneung. We compare the prediction errors of the three models to find the best one for each of the three tollgate traffic volumes.

주제어

표/그림 (12)

그림 Figure 1: FAM results of SeoulTG for the 25^th, 50^th and 75^th percentiles of RISPE. The upper panels depict the traffic on the predictor processes, the lower panels the corresponding observed (black solid curves) and estimated (blue dashed curves) traffic on response process.
표 Table 1: Mean of RISPE for SeoulTG
그림 Figure 2: SAM results of SeoulTG for the 25^th, 50^th and 75^th percentiles of RISPE. The upper panels depict the traffic on the predictor processes, the lower panels the corresponding observed (black solid curves) and estimated (green dashed curves) traffic on response process.
그림 Figure 3: SLM results of SeoulTG for the 25^th, 50^th and 75^th percentiles of RISPE. The upper panels depict the traffic on the predictor processes, the lower panels the corresponding observed (black solid curves) and estimated (red dashed curves) traffic on response process.
그림 Figure 4: FAM results of ChuncheonTG for the 25^th, 50^th and 75^th percentiles of RISPE. The upper panels depict the traffic on the predictor processes, the lower panels the corresponding observed (black solid curves) and estimated (blue dashed curves) traffic on response process.
표 Table 2: Mean of RISPE for ChuncheonTG
그림 Figure 5: SAM results of ChuncheonTG for the 25^th, 50^th and 75^th percentiles of RISPE. The upper panels depict the traffic on the predictor processes, the lower panels the corresponding observed (black solid curves) and estimated (green dashed curves) traffic on response process.
그림 Figure 6: SLM results of ChuncheonTG for the 25^th, 50^th and 75^th percentiles of RISPE. The upper panels depict the traffic on the predictor processes, the lower panels the corresponding observed (black solid curves) and estimated (red dashed curves) traffic on response process.
표 Table 3: Mean of RISPE for GangneungTG
그림 Figure 7: FAM results of GangneungTG for the 25^th, 50^th and 75^th percentiles of RISPE. The upper panels depict the traffic on the predictor processes, the lower panels the corresponding observed (black solid curves) and estimated (blue dashed curves) traffic on response process.
그림 Figure 8: SAM results of GangneungTG for the 25^th, 50^th and 75^th percentiles of RISPE. The upper panels depict the traffic on the predictor processes, the lower panels the corresponding observed (black solid curves) and estimated (green dashed curves) traffic on response process.
그림 Figure 9: SLM results of GangneungTG for the 25^th, 50^th and 75^th percentiles of RISPE. The upper panels depict the traffic on the predictor processes, the lower panels the corresponding observed (black solid curves) and estimated (red dashed curves) traffic on response process.

참고문헌 (13)

An SY (2017). A study on the optimal traffic flow by highway section. Master's thesis, Inje University.
Choo S, Lee SM, Park YI, and Yun J (2007). A study on methods for constructing weekend origin/destination travel, The Korea Transport Institute.
Hsing T and Eubank R (2015). Theoretical Foundations of Functional Data Analysis, with an Introduction to Linear Operators. Wiley.
Hunt JD, McMillan P, Stefan K, and Atkins D (2005). Nature of weekend travel by urban households, 2005 Annual Conference of the Transportation Association of Canada.
Jeon JM and Park BU (2020). Additive regression with Hilbertian responses, The Annals of Statistics, 48, 2671-2697.
Kato T (1995). Perturbation theory for linear operators. Berlin: Springer-Verlag.
Mammen E, Linton O, and Nielsen JP (1999). The existence and asymptotic properties of a backfitting projection algorithm under weak conditions, The Annals of Statistics, 27, 1443-1490.

상세보기
Muller HG and Yao F (2008). Functional additive models, Journal of the American Statistical Association, 103, 1534-1544.

상세보기
Park BU, Chen CJ, Tao W, and Muller HG (2018). Singular additive models for function to function regression, Statistica Sinica, 28, 2497-2520.

상세보기
Park MJ (2015). Traffic prediction technology development using big data, Monthly KOTI Magagine on Transport, 42-46.
Sohn C and Kim GH (2014). Influences of weather on the inbound traffic volume of a tourist destination, The Korea spatial planning review, 99-111.
Yang W, Muller HG, and Stadtmuller U (2011). Functional singular component analysis, Journal of the Royal Statistical Society: Series B Statistical Methodology, 73, 303-324.

상세보기
Yoon SY, Lee CY, Kim HJ, Yook DH, and Kim SR (2017). A study on usability of big data to enhance reliability of regional travel demand forecasting, Korea Research Institute for Human Settlements.

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증