DOI QR코드

DOI QR Code

Forecasting the Busan Container Volume Using XGBoost Approach based on Machine Learning Model

기계 학습 모델을 통해 XGBoost 기법을 활용한 부산 컨테이너 물동량 예측

  • Received : 2024.01.22
  • Accepted : 2024.02.12
  • Published : 2024.02.29

Abstract

Container volume is a very important factor in accurate evaluation of port performance, and accurate prediction of effective port development and operation strategies is essential. However, it is difficult to improve the accuracy of container volume prediction due to rapid changes in the marine industry. To solve this problem, it is necessary to analyze the impact on port performance using the Internet of Things (IoT) and apply it to improve the competitiveness and efficiency of Busan Port. Therefore, this study aims to develop a prediction model for predicting the future container volume of Busan Port, and through this, focuses on improving port productivity and making improved decision-making by port management agencies. In order to predict port container volume, this study introduced the Extreme Gradient Boosting (XGBoost) technique of a machine learning model. XGBoost stands out of its higher accuracy, faster learning and prediction than other algorithms, preventing overfitting, along with providing Feature Importance. Especially, XGBoost can be used directly for regression predictive modelling, which helps improve the accuracy of the volume prediction model presented in previous studies. Through this, this study can accurately and reliably predict container volume by the proposed method with a 4.3% MAPE (Mean absolute percentage error) value, highlighting its high forecasting accuracy. It is believed that the accuracy of Busan container volume can be increased through the methodology presented in this study.

항만 성능에 대한 정확한 평가는 컨테이너 물동량은 매우 중요한 요소이며, 효과적인 항만 개발 및 운영 전략에 대한 정확한 예측이 필수적이다. 하지만 해양 산업의 급격한 변화로 인해 컨테이너 물동량 예측의 정확성이 향상되기는 어렵다. 이를 해결하기 위해 사물인터넷(IoT)을 이용한 항만 성능에 미치는 영향을 분석하여 부산항의 경쟁력과 효율성을 향상시키기 위해 적용이 필요하다. 이에 본 연구에서는 부산항의 미래 컨테이너 물동량을 예측하기 위한 예측 모델을 개발하는 것을 목표로 이를 통해 항만 관리 기관의 개선된 의사 결정과 항만 생산성을 향상시키는 데 초점을 맞추고 있다. 항만 컨테이너 물동량을 예측하기 위해 본 연구에서는 기계 학습 모델의 Extreme Gradient Boosting (XGBoost) 기법을 도입하였다. XGBoost는 다른 알고리즘에 비해 높은 정확도, 빠른 학습 및 예측 속도,과적합을 방지하고 Feature Importance 제공하는 장점이 돋보인다. 특히 XGBoost는 회귀 예측 모델링에 직접 사용할 수 있어 기존 연구에서 제시된 물동량 예측 모델의 정확도 향상에 도움이 된다. 이를 통해 본 연구는 4.3% MAPE (Mean absolute percenture error) 값으로 제안된 방법이 컨테이너 물동량을 정확하고 신뢰성 있게 예측할 수 있다. 본 연구에서 제시한 방법론을 통해서 부산 컨테이너물동량의 정확성을 높일 수 있을 것으로 판단된다.

Keywords

Acknowledgement

This research was supported by "Regional Innovation Strategy (RIS)" through the National Research Foundation of Korea(NRF) funded by the Ministry of Education(MOE)(2023RIS-007).

References

  1. I.Chatterjee and G.S.Cho, "Development of a Machine Learning-Based Framework for Predicting Vessel Size Based on Container Capacity," Applied Science, Vol.12, No.19, pp.1-18, 2022. https://doi.org/10.3390/app12199999
  2. I.Chatterjee and G.S.Cho, "Port Container Terminal Quay Crane Allocation, Based on Simulation and Machine Learning Method," Sensors and Materials, Vol.34, No.2 , pp.843-853, 2022. https://doi.org/10.18494/SAM3645
  3. S.J.Ko and S.J.Kim, "A Study on Pipeline Design Methods for Providing Secure Container Image Registry," Journal of Internet of Things and Convergence, Vol.9, No.3, pp.21-26, 2023.
  4. T.K.Kim, "IoT (Internet of Things)-based Smart Trash Can," Journal of Internet of Things and Convergence, Vol.6, No.1, pp.17-22, 2020.
  5. T.K.Kim, "Self-powered Wireless Bus Information and Disaster Information System based on Internet of Things (IoT)," Journal of Internet of Things and Convergence, Vol.8, No.1, pp.17-22, 2022.
  6. D.H.Kim and K.B.Lee, "Forecasting the Container Volumes of Busan Port using LSTM," Journal of Korea Port Economic Association, Vol.36, No.2, pp.53-62, 2020. https://doi.org/10.38121/kpea.2020.06.36.2.53
  7. G.D.Yi, "Forecasting the Container throughput of the Busan Port using a Seasonal Multiplicative ARIMA Model," Journal of Korea Port Economic Association, Vol.29, No.3, pp.1-23, 2013.
  8. E.J.Lee, D.H.Kim and H.R.Bae, "Container Volume Prediction using Time-Series Decomposition with a Long Short-Term Memory Models," Applied Sciences, Vol.11, No.19, 8995, 2021. https://doi.org/10.3390/app11198995
  9. S.Filom, A.M.Amiri and S.Razavi, "Applications of Machine Learning Methods in Port Operations-A Systematic Literature Review," Transportation Research Part E: Logistics and Transportation Review, Vol.161, 102722, 2022. https://doi.org/10.1016/j.tre.2022.102722
  10. D.Tarwidi, S.R.Pudjaprasetya, D.Adytia and M.Apri, "An Optimized XGBoost-based Machine Learning Method for Predicting Wave Run-up on a Sloping Beach," MethodsX, Vol.10, 102119, 2023.
  11. T.Chen and C.Guestrin, "Xgboost: A Scalable Tree Boosting System," Proceedings of the 22nd ACM Sigkdd International Conference on Knowledge Discovery and Data Mining, pp.785-794, 2016.
  12. G.S.Cho, "Application of Shared Logistics Operation Platform of ICT-based Logistics Companies," Journal of Internet of Things and Convergence, Vol.8, No.5, pp.27-31, 2022.
  13. C.S.Bojer and J.P.Meldgaard, "Kaggle Forecasting Competitions: An Overlooked Learning Opportunity," International Journal of Forecasting, Vol.37, No.2, pp.587-603, 2021. https://doi.org/10.1016/j.ijforecast.2020.07.007
  14. A.D.Myttenaere, B.Golden, B.L.Grand and F.Rossi, "Mean Absolute Percentage Error for Regression Models," Neurocomputing, Vol.192, pp.38-48, 2016. https://doi.org/10.1016/j.neucom.2015.12.114
  15. N.G.Divergences, "WORLD ECONOMIC OUTLOOK," World Economic Outlook, 2023.