The Journal of The Korea Institute of Intelligent Transport Systems (한국ITS학회 논문지)

The Korea Institute of Intelligent Transport Systems (한국ITS학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on the Traffic Volume Correction and Prediction Using SARIMA Algorithm

SARIMA 알고리즘을 이용한 교통량 보정 및 예측

  • Han, Dae-cheol (Dept. of Highway & Transportation Research, Korea Institute of Civil Eng, and Building Technology) ;
  • Lee, Dong Woo (Dept. of Urban Policy and Administration, Incheon National University) ;
  • Jung, Do-young (Dept. of Highway & Transportation Research, Korea Institute of Civil Eng, and Building Technology)
  • 한대철 (한국건설기술연구원 도로교통연구본부) ;
  • 이동우 (인천대학교 도시과학대학 도시행정학과) ;
  • 정도영 (한국건설기술연구원 도로교통연구본부)
  • Received : 2021.08.17
  • Accepted : 2021.11.02
  • Published : 2021.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, a time series analysis technique was applied to calibrate and predict traffic data for various purposes, such as planning, design, maintenance, and research. Existing algorithms have limitations in application to data such as traffic data because they show strong periodicity and seasonality or irregular data. To overcome and supplement these limitations, we applied the SARIMA model, an analytical technique that combines the autocorrelation model, the Seasonal Auto Regressive(SAR), and the seasonal Moving Average(SMA). According to the analysis, traffic volume prediction using the SARIMA(4,1,3)(4,0,3) 12 model, which is the optimal parameter combination, showed excellent performance of 85% on average. In addition to traffic data, this study is considered to be of great value in that it can contribute significantly to traffic correction and forecast improvement in the event of missing traffic data, and is also applicable to a variety of time series data recently collected.

본 연구에서는 도로교통분야의 계획, 설계, 유지관리, 연구 등 다양한 목적으로 활용되고 있는 교통량 데이터의 정확도 확보를 위해 시계열 분석 기법을 적용하여 교통량 데이터의 보정 및 예측을 수행하였다. 기존 알고리즘의 경우 주기성 및 계절성이 강하거나 불규칙한 데이터에 한계를 보이고 있어 교통량 데이터와 같은 자료에 적용하기에는 한계가 있다. 이러한 한계점을 극복하고 보완하기 위해 ARIMA 모형에 자기상관 모형인 SAR(Seasonal Auto Regressive)과 계절 이동평균 모형인 SMA(Seasonal Moving Average)가 결합된 분석 기법인 SARIMA 모형을 적용하였다. 분석결과 최적 파라미터 조합인 SARIMA(4,1,3)(4,0,3) 12 모형을 활용한 교통량 예측 결과 평균 85% 정도의 우수한 성능을 보였다. 본 연구를 통해서 교통량 데이터의 결측 발생 시 교통량 보정 및 예측의 정확도를 높일 수 있으며, 교통량 데이터 외에도 계절성에 영향을 받는 시계열 데이터에 적용이 가능하다.

Keywords

References

  1. Castro-Neto M., Jeong Y. S., Jeong M. K. and Han L. D.(2009), "SVR for short-term traffic flow prediction under typical and atypical traffic conditions," Expert Syst. Appl., vol. 36, no. 3, pp.6164-6173. https://doi.org/10.1016/j.eswa.2008.07.069
  2. Hamed M. M., Al-Masaeid H. R. and Bani Said Z. M.(1995), "Short-term prediction of traffic volume in urban arterial," J. Transp. Eng., vol. 121, no. 3, pp.269-1254.
  3. Kim B. S., Kim S. W., Fang Y. and Wong T. F.(2010), "Feedback-assisted MAC protocol for real time traffic in high rate wireless personal area networks," Wireless Networks, vol. 16, no. 4, pp.1109-1121. https://doi.org/10.1007/s11276-009-0191-0
  4. Korea Institute for Health and Social Affairs(2018), A Study on anomaly detection based on Machine Learning, pp.81-84.
  5. Korea Institute of Civil Engineering and Building Technology(2008), A Study on the Improvement and Evaluation of Information Reliability, pp.45-55.
  6. Lee S. and Fambro D. B.(1999), "Application of subset autogressive integrated moving average model for short-term freeway traffic volume forecasting," Transport. Res. Part C: Emerg. Technol., vol. 1678, no. 1, pp.179-188.
  7. Lee S. B.(2019), Development of Dynamic Traffic Volume Estimation Model Using DSRC Prove Data, Doctoral Dissertation, Seoul National University, p.12.
  8. Lee S. H. and Shin J. M.(2013), "A Study on Imputing the Missing Values of Continuous Traffic Counts," Journal of the Korean Society of Civil Engineers, vol. 33, no. 5, pp.2009-2019. https://doi.org/10.12652/Ksce.2013.33.5.2009
  9. Li L., Su X. N., Zhang Y., Lin Y. and Li Z. H.(2015), "Trend modeling for traffic time series analysis:An integrated study," IEEE Trans. Intell. Transport. Syst., vol. 16, no. 6, pp.3430-3439. https://doi.org/10.1109/TITS.2015.2457240
  10. Li L., Xiaonan S., Yi Z., Yuetong L. and Zhiheng L.(2015), "Trend Modeling for Traffic Time Series Analysis: An Integrated Study," IEEE Transactions on Intelligent Transportation Systems, vol. 16, no. 6, p.3430. https://doi.org/10.1109/TITS.2015.2457240
  11. Satish S., Pawan L. and Ming Z.(2003), "Effect of Missing Value Imputations on Traffic Parameters Estimations from Permanent Traffic Counts," Transportation Research Board 80th Annual Meeting, Washington, D.C., pp.1-33.
  12. Satish S., Pawan L. and Zhong M.(2003), "Effect of Missing Value IMputations on Traffic Parameters Estimations from Permanet Traffic Counts," TRB 2003 Annual Meeting CD-ROM, p.1.
  13. Steffen M. and Bartz-Beielstein T.(2017), "Time Series Missing Value Imputation in R," Contributed Research Article, The R Journal, vol. 9, no. 1, pp.207-218. https://doi.org/10.32614/rj-2017-009
  14. Turner S. M., Lomax T. and Margiotta R.(2001), Monitoring Urban Roadway in 2000:Using Archived Operations Data for Reliability and Mobility Measurement, Texas Transportation Institute, College, TX.
  15. Zhong M. and Sharma S.(2009), "Development of improved models for imputing missing traffic counts," The Open Transportation Journal, vol. 3, no. 1, pp.35-48. https://doi.org/10.2174/1874447800903010035
  16. Zhou Y. C. and Meng P. C.(2019), "Diagnosis of causes for high railway traffic based on Bayesian network," Math. Model. Eng. Probl., vol. 6, no. 1, pp.136-140. https://doi.org/10.18280/mmep.060118