DOI QR코드

DOI QR Code

단계적 회귀분석과 인공신경망 모형을 이용한 광양항 석탄·철광석 물동량 예측력 비교 분석

A Comparative Analysis of the Forecasting Performance of Coal and Iron Ore in Gwangyang Port Using Stepwise Regression and Artificial Neural Network Model

  • 조상호 (한국해양대학교 대학원 해운경영학과) ;
  • 남형식 (한국해양대학교 해운경영학부) ;
  • 류기진 (한국해양대학교 대학원 해운경영학과) ;
  • 류동근 (한국해양대학교 해운경영학부)
  • Cho, Sang-Ho (Graduate School of Korea Maritime Ocean University) ;
  • Nam, Hyung-Sik (Shipping Management, Korea Maritime Ocean University) ;
  • Ryu, Ki-Jin (Graduate School of Korea Maritime Ocean University) ;
  • Ryoo, Dong-Keun (Division of Shipping Management, Korea Maritime Ocean University)
  • 투고 : 2019.09.02
  • 심사 : 2020.03.26
  • 발행 : 2020.06.30

초록

항만의 주요 정책 및 향후 운영계획 수립 시 정확한 물동량 예측에 관한 연구는 매우 중요하며 이러한 중요성으로 인해 관련 연구가 활발히 수행되고 있다. 본 논문에서는 국내 최대 석탄 및 철광석 처리 항만인 광양항을 대상으로 단계적 회귀분석과 인공신경망모형을 활용하여 모형간 예측력을 비교하였다. 2009년 1월부터 2019년 1월까지 총 121개월의 월별자료를 활용하였으며 석탄 및 철광석 물동량에 영향을 주는 요인을 선정하여 공급관련요인과 시장·경제관련요인으로 분류하였다. 단계적 회귀분석 결과, 광양항 석탄 물동량 예측모형의 경우, 입항선박 톤수, 석탄가격 및 대미환율이 최종변수로 선정되었고 철광석 물동량 예측모형의 경우, 입항선박 톤수, 철광석가격이 최종변수로 선정되었다. 인공신경망모형의 경우, 모델 성능에 영향을 미치는 다양한 Hyper-parameters를 조정하며 최적 모델을 선정하는 시행착오법을 사용하였다. 분석결과 인공신경망모형이 단계적 회귀분석에 비해 우수한 예측성능을 나타내었으며 예측 모형별 예측값과 실측값을 그래프 상 비교 시에도 인공신경망모형이 단계적 회귀분석에 비해 고·저점을 유사하게 나타냈다.

It is very important to forecast freight volume accurately to establish major port policies and future operation plans. Thus, related studies are being conducted because of this importance. In this paper, stepwise regression analysis and artificial neural network model were analyzed to compare the predictive power of each model on Gwangyang Port, the largest domestic port for coal and iron ore transportation. Data of a total of 121 months J anuary 2009-J anuary 2019 were used. Factors affecting coal and iron ore trade volume were selected and classified into supply-related factors and market/economy-related factors. In the stepwise regression analysis, the tonnage of ships entering the port, coal price, and dollar exchange rate were selected as the final variables in case of the Gwangyang Port coal volume forecasting model. In the iron ore volume forecasting model, the tonnage of ships entering the port and the price of iron ore were selected as the final variables. In the analysis using the artificial neural network model, trial-and-error method that various Hyper-parameters affecting the performance of the model were selected to identify the most optimal model used. The analysis results showed that the artificial neural network model had better predictive performance than the stepwise regression analysis. The model which showed the most excellent performance was the Gwangyang Port Coal Volume Forecasting Artificial Neural Network Model. In comparing forecasted values by various predictive models and actually measured values, the artificial neural network model showed closer values to the actual highest point and the lowest point than the stepwise regression analysis.

키워드

참고문헌

  1. Cho, C. H.(2008), "Forecasting the Cement Traffic Volume at the Port of Donghae", Korea Logistics Review, Vol. 18, No. 1, pp. 33-53.
  2. Jeon, C. Y. and Song, J. M.(2007), "A Study on Application of the Port Cargo Throughput Forecast by the Neural Network Model", Journal of Shipping and Logistics, Vol. 53, pp. 65-82.
  3. Kim, C. B.(2015), "Forecasting the Seaborne Trade Volume using Intervention Multiplicative Seasonal ARIMA and Artificial Neural Network Model", Journal of Korea Port Economic Association, Vol. 31, No. 1, pp. 69-84.
  4. Kim, J. E. et al.(2018), "An introduction of new time series forecasting model for oil cargo volume", Journal of Korea Port Economic Association, Vol. 34, No. 1, pp. 81-98. https://doi.org/10.38121/kpea.2018.03.34.1.81
  5. Korea Mineral Resource Information Service(2019a), Iron Ore & Energy Statistics, https://www.kores.net
  6. Korea Mineral Resource Information Service(2019b), Market Outlook Indicator for mineral resources, https://www.kores.net
  7. Lim, S. S. and Yun, H. S.(2018), "An Analysis on Determinants of the Capesize Freight Rate and Forecasting Models", Journal of Navigation and Port Research, Vol. 42, No. 6, pp. 539-545. https://doi.org/10.5394/KINPR.2018.42.6.539
  8. Ministry of Oceans and Fisheries(2019), Gwangyang Port Logistics Information System, http://www.spidc.go.kr
  9. Paliwal, M. and Kumar, U. A.(2009), "Neural networks and statistical techniques: A review of applications," Expert Systems with Applications, Vol. 36, No. 1, pp. 2-17. https://doi.org/10.1016/j.eswa.2007.10.005
  10. Park, S. I. et al.(2012), "Forecasting the Steel Cargo Volumes in Incheon Port using System Dynamics", Journal of Korea Port Economic Association, Vol. 28, No. 2, pp. 75-93.
  11. Shepperd, M. and MacDonell, S.(2012), "Evaluating prediction systems in software project estimation," Information and Software Technology, Vol. 54, No. 8, pp. 820-827. https://doi.org/10.1016/j.infsof.2011.12.008
  12. Shin, C. H. and Jeong, S. H.(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
  13. Silhavy, R., Silhavy, P. and Prokopova, Z.(2017), "Analysis and selection of a regression model for the Use Case Points method using a stepwise approach," Journal of Systems and Software, Vol. 125, pp. 1-14. https://doi.org/10.1016/j.jss.2016.11.029
  14. Statistics Korea(2019), Index of mining and manufacturing industrial product, http://kostat.go.kr
  15. Van Dorseser, J. C. M. et al(2012), Very Long Term Forecast of the Port Throughput in the Le Havre -Hamburg Range up to 2100. EJTIR, 12(1), pp. 88-110.
  16. Zeng, Q. and Qu, C.(2014), "An approach for Baltic Dry Index analysis based on empirical mode decomposition," Maritime Policy & Management. Routledge, Vol. 41, No. 3, pp. 224-240. https://doi.org/10.1080/03088839.2013.839512
  17. Zhang, G., Patuwo, B. E. and Hu, M. Y.(1998), "Forecasting with artificial neural networks: The state of the art," International Journal of Forecasting, Vol. 14, No. 1, pp. 35-62. https://doi.org/10.1016/S0169-2070(97)00044-7