臺灣博碩士論文加值系統

港埠運量預測對港口營運及物流效率和競爭力之提升至關重要。本研究提出一個結合粒子群優化演算法（PSO）及線性迴歸（LR）的混合模型，簡稱PSO-LR，來對高雄港（台灣 最繁忙的貨櫃港口之一）的貨櫃吞吐量進行預測。利用數年來的歷史貨櫃吞吐量數據，我們首先以 PSO-LR 來優化LR模型參數並進行貨櫃運量之預測。本研究架構包括資料收集、預處理、使用 PSO 的模型訓練、驗證和效能評估。經由PSO-LR模型與 LR 的模型所產生的預測數據進行比較，結果顯示PSO-LR 較LR模型有較高之預測準確性。本研究豐富了港口管理優化技術的知識體系，並提出一個具體之模型來預測港埠的貨櫃運量。

Accurate throughput prediction is important for ports to enhance efficiency and competitiveness in maritime logistics. In this study, we propose a novel model, PSO-LR, which combines Particle Swarm Optimization (PSO) with Linear regression (LR) as a predictive model for container throughput at Kaohsiung Port, one of the busiest container ports in Taiwan. Leveraging historical container throughput data spanning several years, we employ PSO to optimize the parameters of the LR model and forecast container throughput at Kaohsiung port. The research framework encompasses data collection, preprocessing, model training using PSO, validation, and performance evaluation. We compare the PSO-LR with the standard LR model to assess the effectiveness of PSO in improving predictive accuracy by analyzing the trends and patterns of the predictive model. The results show that the PSO-LR outperforms the standard LR model. The findings contribute to the body of knowledge on optimization techniques in port management and provide valuable insights for practitioners seeking to enhance port efficiency and performance.

Abstract 2
ACKNOWLEDGMENTS 4
Chapter 1 INTRODUCTION 9
1.1 Background and Statement 9
1.2 Objectives and Motivation 9
1.3 Thesis Structure 10
1.4 Acronyms 11
Chapter 2 LITERATURE REVIEW 12
2.1 Challenges and Trends in Container Port Management 12
2.2 Predictive Analytics and Machine Learning in Port Operations 13
2.3 Applications of Predictive Analytics and Machine Learning 14
2.4 Implications for Port Operations 15
Chapter 3 RESEARCH METHODOLOGY 16
3.1 Data Collection 16
3.3.1 Data sources 16
3.1.2 Container data type 16
3.1.3 Container data of Kaohsiung Port 17
3.2 Pearson correlation 18
3.3 Linear Regression Model 19
3.4 Particle Swarm Optimization (PSO) 21
3.4.1 PSO introduction 21
3.4.2 Steps involved in implementing PSO for predictive modeling 21
3.4.3 Components of PSO 23
3.4.3 Velocity Update 23
3.4.5 Position Update 23
3.4.6 Position Update for Slope and Intercept 24
3.4.7 PSO parameter 24
3.5 Mean Square Error (MSE) 25
3.6 Weighted Mean Squared Error (WMSE) 26
3.6.1 WMSE Formula 26
3.6.2 Useful in scenarios for WMSE 27
3.7 Objective function value 27
3.7.1 Objective function formula 27
3.7.2 Interpretation and Use cases 28
3.8 Software Environment 28
Chapter 4 RESULTS 30
4.1 Analyzing Pearson Correlation Results 30
4.1.1 Observations: 30
4.1.2 The reasons for focusing on 2014 to 2023: 30
4.2 Prediction results 31
4.2.1 Model Application and Evaluation 31
4.2.2 PSO-LR and LR model performance 31
Chapter 5 ANALYSIS AND DISCUSSION 35
5.1 Interpretation of Results 35
5.2 Contributions 36
5.3 Limitation 36
Chapter 6 CONCLUSION AND FUTURE WORK 38
6.1 Conclusion 38
6.2 Future work 38
References 39

Balci, G., Cetin, I. B., & Tanyeri, M. (2018). Differentiation of container shipping services in Turkey. Transport Policy, 61, 26-35.
Chicco, D., Warrens, M. J., & Jurman, G. (2021). The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation. Peerj computer science, 7, e623.
Chiraphadhanakul, S., Dangprasert, P., & Avatchanakorn, V. (1997, October). Genetic algorithms in forecasting commercial banks deposit. In 1997 IEEE International Conference on Intelligent Processing Systems (Cat. No. 97TH8335) (Vol. 1, pp. 116-121). IEEE.
Chou, C. C., Chu, C. W., & Liang, G. S. (2008). A modified regression model for forecasting the volumes of Taiwan’s import containers. Mathematical and Computer Modelling, 47(9-10), 797-807.
Eckerson, W. W. (2007). Predictive analytics. Extending the Value of Your Data Warehousing Investment. TDWI Best Practices Report, 1, 1-36.
Feng, H., Grifoll, M., & Zheng, P. (2019). From a feeder port to a hub port: The evolution pathways, dynamics and perspectives of Ningbo-Zhoushan port (China). Transport Policy, 76, 21-35.
Forrest, S. (1996). Genetic algorithms. ACM computing surveys (CSUR), 28(1), 77-80.
Gao, Y., Luo, M., & Zou, G. (2016). Forecasting with model selection or model averaging: a case study for monthly container port throughput. Transportmetrica A: Transport Science, 12(4), 366-384.
Grifoll, M., Karlis, T., & Ortego, M. I. (2018). Characterizing the evolution of the container traffic share in the Mediterranean Sea using hierarchical clustering. Journal of Marine Science and Engineering, 6(4), 121.
Ha, M. H., Yang, Z., & Lam, J. S. L. (2019). Port performance in container transport logistics: A multi-stakeholder perspective. Transport Policy, 73, 25-40.
Holland, J. H. (1975). University of Michigan Press. Ann Arbor.
Hsu, H. P. (2016). Solving feeder assignment and component sequencing problems for printed circuit board assembly using particle swarm optimization. IEEE Transactions on Automation Science and Engineering, 14(2), 881-893.
Huang, J., Chu, C. W., & Tsai, Y. C. (2020). Container throughput forecasting for international ports in Taiwan. Journal of Marine Science and Technology, 28(5), 15.
Huang, W. C., Chang, H. H., & Wu, C. T. (2008). A model of container transshipment port competition: an empirical study of international ports in Taiwan. Journal of Marine Science and technology, 16(1), 3.
Jeong, B., Jung, H. S., & Park, N. K. (2002). A computerized causal forecasting system using genetic algorithms in supply chain management. Journal of Systems and Software, 60(3), 223-237.
Ju, Y. J., Kim, C. E., & Shim, J. C. (1997). Genetic-based fuzzy models: interest rate forecasting problem. Computers & industrial engineering, 33(3-4), 561-564.
Kennedy, J., & Eberhart, R. (1995, November). Particle swarm optimization. In Proceedings of ICNN'95-international conference on neural networks (Vol. 4, pp. 1942-1948). ieee.
Kim, D., & Kim, C. (1997). Forecasting time series with genetic fuzzy predictor ensemble. IEEE Transactions on Fuzzy systems, 5(4), 523-535.
Kim, D. H., & Lee, K. (2020). Forecasting the Container volumes of Busan port USING LSTM. Journal of Korea Port Economic Association, 36(2), 53-62.
Laurikkala, J. (2001). Improving identification of difficult small classes by balancing class distribution. In Artificial Intelligence in Medicine: 8th Conference on Artificial Intelligence in Medicine in Europe, AIME 2001 Cascais, Portugal, July 1–4, 2001, Proceedings 8 (pp. 63-66). Springer Berlin Heidelberg.
Lee Rodgers, J., & Nicewander, W. A. (1988). Thirteen ways to look at the correlation coefficient. The American Statistician, 42(1), 59-66.
Mahesh, B. (2020). Machine learning algorithms-a review. International Journal of Science and Research (IJSR). [Internet], 9(1), 381-386.
Marill, K. A. (2004). Advanced statistics: linear regression, part I: simple linear regression. Academic emergency medicine, 11(1), 87-93.
Munim, Z. H., Fiskin, C. S., Nepal, B., & Chowdhury, M. M. H. (2023). Forecasting container throughput of major Asian ports using the Prophet and hybrid time series models. The Asian Journal of Shipping and Logistics, 39(2), 67-77.
Ng, S. T., Skitmore, M., & Wong, K. F. (2008). Using genetic algorithms and linear regression analysis for private housing demand forecast. Building and Environment, 43(6), 1171-1184.
Onut, S., Tuzkaya, U. R., & Torun, E. (2011). Selecting container port via a fuzzy ANP-based approach: A case study in the Marmara Region, Turkey. Transport Policy, 18(1), 182-193.
Peng, W. Y., & Chu, C. W. (2009). A comparison of univariate methods for forecasting container throughput volumes. Mathematical and computer modelling, 50(7-8), 1045-1057.
Rawson, A., Brito, M., Sabeur, Z., & Tran-Thanh, L. (2021). A machine learning approach for monitoring ship safety in extreme weather events. Safety science, 141, 105336.
Shankar, S., Ilavarasan, P. V., Punia, S., & Singh, S. P. (2020). Forecasting container throughput with long short-term memory networks. Industrial management & data systems, 120(3), 425-441.
Stavroulakis, P. J., & Papadimitriou, S. (2017). Situation analysis forecasting: the case of European maritime clusters. Maritime Policy & Management, 44(6), 779-789.
Twrdy, E., & Batista, M. (2016). Modeling of container throughput in Northern Adriatic ports over the period 1990–2013. Journal of Transport Geography, 52, 131-142.
Wiegand, J. (2004). Eclipse: A platform for integrating development tools. IBM Systems Journal, 43(2), 371-383.
Yap, W. Y., & Ho, J. (2023). Port strategy and performance: empirical evidence from major container ports and implications for the role of data analytics. Maritime Policy & Management, 50(5), 608-628.
Yeom, C. U., & Kwak, K. C. (2019). Incremental granular model improvement using particle swarm optimization. Symmetry, 11(3), 390.
Zheng, D. X., Ng, S. T., & Kumaraswamy, M. M. (2004). Applying a genetic algorithm-based multiobjective approach for time-cost optimization. Journal of Construction Engineering and management, 130(2), 168-176.
Ziran, J., Chunfang, P., Huayou, Z., Chengjin, W., & Shilin, Y. (2022). Temporal and spatial evolution and influencing factors of the port system in Yangtze River Delta Region from the perspective of dual circulation: Comparing port domestic trade throughput with port foreign trade throughput. Transport Policy, 118, 79-90.