Browse > Article

A Time Series-based Algorithm for Eliminating Outliers of GPS Probe Data  

Choi, Kee-Choo (아주대학교 환경건설교통공학부)
Jang, Jeong-A (한국전자통신연구원 텔레매틱스연구단)
Publication Information
Journal of Korean Society of Transportation / v.22, no.6, 2004 , pp. 67-77 More about this Journal
Abstract
A treatment of outlier has been discussed. Outliers disrupt the reliability of information systems and they should be eliminated prior to the information and/or data fusion. A time series-based elimination algorithm were proposed and prediction interval, as a criterion of acceptable value width, was obtained with the model. Ten actual link values were used and the best model was identified as IMA(1,1). Although the actual verification was difficult in a sense that the matching process between the eliminated data and model data was not readily available, the proposed model can be successfully used in practice with some calibration efforts.
Keywords
GPS 프로브;이상치 제거;시계열 모형;ARIMA 모형;신뢰도;
Citations & Related Records
연도 인용수 순위
  • Reference
1 김원경(1998), '시계열분석', 교우사
2 ITS용어사전, http://www.itsgis.net/dictionary/dictionary02.asp?Mainpage=dictionary
3 아주대학교 교통연구센터(2002), '구간교통정보 보정 알고리즘 개발을 위한 데이터 분석', (주)SK
4 장상희(2001), '사회통계학', 박영사
5 Francois Dion and Hesham Rakha (2003), 'Estimating Spatial Travel Times using AVI Data', 2003 TRB Proceedings, Washington DC, 2003
6 Turner S(1996), 'Advanced Techniques for Travel Time Data Collection', Transportation Research Record No.1551, TRB, 57
7 아주대학교 교통연구센터(2003), '구간 교통정보 보정 알고리즘 개발 및 교통정보 신뢰도 평가', (주)SK
8 최기주 (1998), 'An Algorithm for Calculating Dynamic Link Travel Time Using GPS and Digital Road Map', ITS World Congress Proceeding, Seoul 1998