Journal of the Korean Society of Marine Environment & Safety (해양환경안전학회지)

The Korean Society of Marine Environment and safety (해양환경안전학회)
권호 표지
DOI QR코드

DOI QR Code

A Prediction of Marine Traffic Volume using Artificial Neural Network and Time Series Analysis

인공신경망과 시계열 분석을 이용한 해상교통량 예측

  • Yoo, Sang-Lok (Graduate school of Mokpo National Maritime University) ;
  • Kim, Jong-Su (Division of Marine System Engineering, Korea Maritime and Ocean University) ;
  • Jeong, Jung-Sik (Division of International Maritime Transportation Science, Mokpo National Maritime University) ;
  • Jeong, Jae-Yong (Division of International Maritime Transportation Science, Mokpo National Maritime University)
  • 유상록 (목포해양대학교 대학원) ;
  • 김종수 (한국해양대학교 기관시스템공학부) ;
  • 정중식 (목포해양대학교 국제해사수송과학부) ;
  • 정재용 (목포해양대학교 국제해사수송과학부)
  • Received : 2013.11.04
  • Accepted : 2014.02.25
  • Published : 2014.04.28
Download PDF
⟨ Previous Next ⟩

Abstract

Unlike the existing regression analysis, this study anticipated future marine traffic volume using time series analysis and artificial neural network model. Especially, it tried to anticipate future marine traffic volume by applying predictive value through time series analysis on artificial neural network model as an additional input variable. This study used monthly observed values of Incheon port from 1996 to 2013. In order for the verification of the forecasting of the model, value for 2013 is anticipated from the built model with observed values from 1996 to 2012 and a proper model is decided by comparing with the actual observed values. Marine traffic volume of Incheon port showed more traffic than average for May and November by 5.9 % and 4.5 % respectably, and January and August showed less traffic than average by 8.6 % and 4.7 % in 2015. Thus, it is found that Incheon port has difference in monthly traffic volume according to the season. This study can be utilized as a basis to reflect the characteristics of traffic according to the season when investigating marine traffic field observation.

본 연구는 기존의 회귀분석과는 달리 시계열 분석과 인공신경망 모형을 이용하여 장래 해상교통량을 예측하였다. 특히, 시계열 분석을 통한 예측값을 인공신경망 모형에 추가 입력변수로 적용하여 장래 해상교통량 예측을 제고하고자 하였다. 본 연구는 인천항의 1996년부터 2013년까지 월별 관측값을 대상으로 하였다. 모형의 예측력 검증을 위해 1996년부터 2012년까지 관측값을 대상으로 구축한 모형으로부터 2013년을 예측하여 실제 관측값과의 비교로 적합한 모형을 판별하였다. 인천항의 2015년 장래 해상교통량은 매월 평균 교통량보다 5월과 11월에 각 5.9 %, 4.5 % 많았으며, 1월과 8월은 매월 평균 교통량보다 각 8.6 %, 4.7 % 적은 것으로 예측되었다. 따라서 인천항은 계절에 따른 월별 교통량의 차이를 확인할 수 있다. 본 연구는 해상교통 현장관측 조사시 계절에 따른 교통량의 특성을 반영할 수 있는 기초 자료로 활용될 수 있다.

Keywords

References

  1. Akaike, H.(1978), A Bayesian Analysis of the minimum AIC Procedure, Annals of the Institute of Mathematical Statistics, pp. 9-14.
  2. Box, G. E. P., G. M. Jenkins and G. C. Reinsel(2008), Time Series Analysis: Forecasting and Control, A John Wiley and Sons Inc., pp. 79-86, pp. 103-113.
  3. Choi, S. H(2011), Neural Network Model for Prediction of Damage Cost from Storm and Flood, Journal of KIISE : Software and Applications, Vol. 38, No.3, pp. 115-123.
  4. Funahashi(1989), On the Approximate Realization of Continuous Mapping by Neural Networks, Neural Networks, Vol. 2, pp. 183-192. https://doi.org/10.1016/0893-6080(89)90003-8
  5. Gu, J. Y., S. J. Kim, E. K. Jang and S. W. Kim(2004), A Study on the Opimal width of the Main Span in the 2nd Bridge of Incheon, Journal of Korean Navigation and Port Research, Vol. 28, No. 10, pp. 933-940. https://doi.org/10.5394/KINPR.2004.28.10.933
  6. Hornik, K.(1989), Multilayer Feedforward Networks are Universal Approximators, Neural Networks, Vol. 2, pp. 359-366. https://doi.org/10.1016/0893-6080(89)90020-8
  7. Jang, S. C., S. M. Seok, J. S. Lee, S. W. Lee and B. H. Ahn(2005), Traffic-Flow Forecasting using ARIMA, Neural Network and Judgement Adjustment, Proceedings of The Korean Operations Research and Management Science Society Spring Conference, pp. 793-797.
  8. Kang, M. S., Y. W. Kim and H. Jeong(2012), Predicition System of Floating Body Motion using Artficial Neural Networks, Joint Conference of the Korean Association of Ocean Science and Technology Societies, pp. 1041-1050.
  9. Kang, S. W.(2012), A Study of Hull Form Design and Performance Predicition using Neural Networks, Proceedings of Korean Institute of Intelligent Systems Fall Conference, Vol. 22, No. 2, pp. 61-64.
  10. Kim, J. H., S. G. Gug and M. C. Kim(2006), Estimation on the Future Traffic Volumne and Analysis on Crossing Situation Risk for Gamcheon Harbor, Journal of Korean Navigation and Port Research, Vol. 30, No. 8, pp. 617-622. https://doi.org/10.5394/KINPR.2006.30.8.617
  11. Kim, J. G. and Y. D. Kim(2013), The Estimation of the Future Marine Traffic Volume at Expected Port which is an Additional Whart Construction, Proceedings of the Korean Society of Marine Environment Fall Conference, pp. 224-225.
  12. Kim, K. W., J. W. Jang and I. S. Cho(2011), A Study on Technique and Investigating Criterion for Improving Investigating Technique of Marine Traffic Volume, Proceedings of the Korean Society of Marine Environment Fall Conference, pp. 153-155.
  13. Lee, D. W., H. M. Lee, J. W. Seo, S. H. Yoo and Y. H. Youn(2005), Storm Surge Prediction using Artificial Neural Network, Journal of Korean Meteorological Society, Vol. 41, No. 5, pp. 661-670.
  14. Park, S., K. J. Kim, J. S. Lee and S. R. Lee(2011), Red Tide Prediction using Neural Network and SVM, The Institute of Electronics Engineers of Korea-Signal Processing, Vol. 48, No. 5, pp. 39-45.
  15. Quan, H. C., B. G. Lee, C. S. Lee and J. W. Ko(2011), The Landslide Probablility Analysis using Logistic Regression Analysis and Artficial Neural Network Methods in Jeju, Journal of the Kroean Society for Geo-Spatial Inforamtion System, Vol. 19, No. 3, pp. 33-40.
  16. Shin, C. H., J. S. Kang, S. N. Park and J. H. Lee(2008), A Study on the Forecast of Port Traffic using Hybrid ARIMA-Neural Network Model, Journal of Navigation and Port Research, Vol. 32, No. 1, pp. 81-88. https://doi.org/10.5394/KINPR.2008.32.1.081
  17. Shin, C. H. and S. H. Jeong(2011), A Study on Application of ARIMA and Neural Networks for Time Series Forecasting of Port Traffic, Journal of Navigation and Port Research, Vol. 35, No. 1, pp. 83-91. https://doi.org/10.5394/KINPR.2011.35.1.83
  18. SK Gas(2011), Maritime Traffic Safety Audit Report of SK 3 Wharf and SK Gas Wharf Expansion, Chapter 6, pp. 5-26.
  19. Ulsan Port Authority(2013), Maritime Traffic Safety Audit Report of Construction at Namhwa Lighters Wharf in Ulsan Port, Chapter 4, pp. 18-22.
  20. Yoo, S. R., Y. S. Park, J. S. Jeong, C. S. Kim and J. Y. Jeong(2013), A Forecast Method of Marine Traffic Volume through Time Series Analysis, Journal of the Korean Society of Marine Environment, Vol. 19, No. 6, pp. 612-620. https://doi.org/10.7837/kosomes.2013.19.6.612

Cited by

  1. A Novel Data Prediction Model using Data Weights and Neural Network based on R for Meaning Analysis between Data vol.18, pp.4, 2015, https://doi.org/10.9717/kmms.2015.18.4.524
  2. Analysis of Highway Traffic Indices Using Internet Search Data vol.33, pp.1, 2015, https://doi.org/10.7470/jkst.2015.33.1.14
  3. Demand forecasting model development through big data analysis pp.1572-9362, 2019, https://doi.org/10.1007/s10660-019-09337-8
  4. ANN-based Evaluation Model of Combat Situation to predict the Progress of Simulated Combat Training vol.22, pp.7, 2014, https://doi.org/10.9708/jksci.2017.22.07.031
  5. 우포늪 수위 자료의 시계열 모형화 및 잔차 분석 vol.21, pp.1, 2014, https://doi.org/10.17663/jwr.2019.21.1.066