DOI QR코드

DOI QR Code

시계열 이상치 탐지 기법을 활용한 경부선 주요도시 철도 승객수의 이상치 탐색 연구

A Study on the Outliers Detection in the Number of Railway Passengers for the Gyeongbu Line From Seoul to Major Cities Using a Time Series Outlier Detection Technique

  • 이지선 (한국과학기술원 건설 및 환경공학과) ;
  • 윤윤진 (한국과학기술원 건설 및 환경공학과)
  • LEE, Jiseon (Department of Civil and Environmental Engineering, Korea Advanced Institute of Science and Technology) ;
  • YOON, Yoonjin (Department of Civil and Environmental Engineering, Korea Advanced Institute of Science and Technology)
  • 투고 : 2016.12.30
  • 심사 : 2017.12.23
  • 발행 : 2017.12.31

초록

2004년 4월 1일, 국내 최초의 고속철도(HSR)인 KTX (Korea Train eXpress)가 경부선에 도입 되었다. KTX의 등장은 경부선을 이용하는 철도 승객들의 운송수단 선택 및 도시구간별 이용객 수 변화를 가져왔다. KTX의 등장과 같은 개입사건(Intervention events)의 영향은 개입사건 전후 변화를 단순 통계량으로 분석하거나 개입 ARIMA 모델을 통해 분석 되었다. 개입 ARIMA 모델은 개입사건의 발생 시점(t)과 개입사건의 영향 형태(type) 등의 가정이 필요하다는 한계가 있었으며, 본 연구에서는 기존 연구에서의 한계점을 보완할 수 있는 시계열 이상치 탐지(time series outlier detection)를 활용하였다. 일반적으로 개입사건의 발생시기는 잘 알려져 있지 않으므로 시계열 이상치 탐지를 통해 개입사건에의 발생 시기를 추정할 수 있다. 시계열 이상치 탐지기법을 활용하여 개입의 시점과 영향 형태에 관한 가정 없이 개입사건에 대한 영향을 분석할 수 있으며, 발생된 이상치의 시점을 개입사건의 시점, 이상치의 영향을 개입사건의 영향으로 가정하였다. 데이터는 KTDB (Korea Transport Database)로 부터 KTX가 도입되기 이전인 2003년부터 2014년까지 12년 동안의 경부선(4개의 주요 도시구간 합산)을 포함한 주요 도시구간 4개의 월별데이터를 수집하여 활용하였다. 경부선 도시 구간별 이상치를 탐지 하고 그 영향을 분석한 결과, 동일한 개입사건 임에도 그 영향의 형태의 정도가 도시구간마다 다르게 나타나거나 영향이 나타나지 않았으며, 기존 연구에서 분석되지 않은 개입사건을 찾을 수 있었다.

On April 1, 2004, KTX (Korea Train eXpress), the first HSR (High-Speed Rail) in Korea, was introduced to Gyeongbu Line. The introduction of the KTX service led to a change in the number of passengers for Gyeongbu Line. Previous studies have analyzed the pre and post-event changes of the intervening events by either simple statistics or intervention ARIMA analysis. However, the intervention ARIMA model has a limitation that several assumptions such as the occurrence time and the type of intervention events are necessary. To this end, this study analyzed the effects of intervention event on the number of passengers using the Gyeongbu line based on a time series outlier detection technique which can overcome limitations in the previous studies. The time series outlier detection technique can analyze the time, effect type and size of an intervention event without the assumption of the time and effect type of the intervention event. The data were collected from the Korea Transport Database (KTDB) for twelve years from 2003 to 2014 (144 months). The analysis results showed that the size of the influence type in the same intervention events was different across the major city routes, and the intervention event which could not be found by previous study methods was also found.

키워드

참고문헌

  1. Box G. E. P., Tiao G. C. (1975), Intervention Analysis with Applications to Economic and Environmental Problems, Journal of the American Statistical Associations, 70(349), 70-77. https://doi.org/10.1080/01621459.1975.10480264
  2. Cascetta E., Coppola P. (2014), Competition on Fast Track: An Analysis of the First Competitive Market for HSR Services, Procedia-Social and Behavioral Sciences, 111, 176-185. https://doi.org/10.1016/j.sbspro.2014.01.050
  3. Chang I., Tiao G. C., Chen C. (1988), Estimation of Time Series Parameters in the Presence of Outliers, Technometrics, 30(2), 193-204. https://doi.org/10.1080/00401706.1988.10488367
  4. Chen C., Liu L. M. (1993), Joint Estimation of Model Parameters and Outlier Effects in Time Series, Journal of the American Statistical Association, 88(421), 284-297. https://doi.org/10.2307/2290724
  5. Kaiser R., Maravall A. (1999), Seasonal Outliers in Time Series.
  6. Kim H. W., Lee D. H., Park H. S. (2013), The Impact of Gyeongbu High Speed Rail Construction on Regional Economic Growth, KSCE Journal of Civil Engineering, 17(6), 1206-1212. https://doi.org/10.1007/s12205-013-0199-y
  7. Kim K. H., Kim H. S. (2011), KTX Passenger Demand Forecast With Intervention ARIMA Model, Journal of the Korean Society for Railway, 14(5), 470-476. https://doi.org/10.7782/JKSR.2011.14.5.470
  8. Kim M. S., Kim K. W., Sung S. P. (2012), A Study on the Air Travel Demand Forecasting Using Time Series ARIMA-Intervention Model, Journal of the Korean Society for Aviation and Aeronautics, 20(1), 63-74.
  9. Lee J. H., Chang J. (2006), Effects of High-speed Rail Service on Shares of Intercity Passenger Ridership in South Korea, Transportation Research Record: Journal of the Transportation Research Board, 1943, 31-42. https://doi.org/10.1177/0361198106194300105
  10. Lee S.J., Change J.S., Lee S. J., Yoon Y. W. (2013), An Analysis on Speed-Distance Comparative Advantage of Transportation Modes After the Opening of Gyeongbu High-speed Railway Project Phase II, Conference of the Korean Society for Railway, 1162-1174.
  11. Lim S. J., Lim K. W., Lee Y. I., Kim K. H. (2008), A Study on Air and High Speed Rail Modal According to the Introduction of Low Cost Carrier Air Service, J. Korean Soc. Transp., 26(4), Korean Society of Transportation, 51-61.
  12. Lopez J., Lopez M. J. (2016), Package 'tsoutliers'.
  13. Lopez-de-Lacalle (2014), J. tsoutliers R Package for Detection of Outliers in Time Series.
  14. Park M. S., Eom J. K., Heo T. Y., Song J. (2015), Intervention Analysis of the Impact of Opening a New Railway Line on Passenger Ridership in Seoul, KSCE Journal of Civil Engineering, 1-11.
  15. Park M. S., Kim Y. (2016), The Impacts of High Speed Train on the Regional Economy of Korea, Korean Journal of Applied Statistics, 29(1), 13-25. https://doi.org/10.5351/KJAS.2016.29.1.013
  16. Park S. K. (2004), The Impact of Terrorism on World Tourism, Journal of Tourism Sciences, 28(2), 77-94.
  17. Suh S., Yang K. Y. (2005), Customers' Reactions to the Introduction of High-speed Rail Service: Korean Train express, Transportation Research Record: Journal of the Transportation Research Board, 1916, 20-25. https://doi.org/10.3141/1916-03

피인용 문헌

  1. An Analysis of Mobile Food Delivery App 'Baemin' by Using Text Mining and ARIMA Model vol.22, pp.2, 2017, https://doi.org/10.9728/dcs.2021.22.2.291