貨櫃在國際海運運輸服務物流中扮演著至關重要的角色。然而，運輸過程中的諸多不確定因素，如惡劣天氣、海象變化、吊卸過程意外或貨物包裝不固等，致使偶有貨櫃損壞之情形發生。這些損壞的貨櫃通常需要被暫時堆放在貨櫃場中，因而佔用有限之儲運空間。此外，根據損壞的嚴重性，船公司必須投入大量人力資源來評估貨櫃損壞的程度，以便優先處理損壞較輕的貨櫃，但評估過程往往十分耗時。至於損壞的原因，也需進一步釐清以確定責任歸屬。

本研究旨在開發一個自動化系統，結合圖像擴增(Data Augmentation)與遷移學習微調(Fine-Tuning)的深度學習方法，對損壞原因進行快速且準確的分類。實驗證明，這套系統在不同預訓練模型的基礎上進行微調後，準確率提升了6\%至18\%，其中最佳準確率達到98.84\%。此系統不僅加快了整體貨櫃的維修流程，同時亦為船公司提供了一個可靠的依據，以便向相關方追究責任或進行損失分攤，從而更有效地管理運營風險，並提高整體營運效益。

Containers play a crucial role in the logistics of international maritime transport services. However, uncertain factors such as weather conditions, sea states, handling processes, or improper packing of goods can occasionally result in container damage, leading to the temporary storage of damaged containers in container terminals, thus occupying limited storage space. Additionally, depending on the severity of the damage, shipping companies need to allocate manpower to evaluate the extent of the damage in order to prioritize containers with minor issues, but this assessment process is often time-consuming. Further investigation is also required to clarify the causes of damage to determine liability.

This study seeks to develop an automated system that combines image augmentation and fine-tuning of transfer learning within a deep learning framework to quickly and accurately classify the causes of container damage. The system has been proven through experiments to enhance accuracy by 6\% to 18\% upon fine-tuning on various pre-trained models, achieving an optimal accuracy of 98.84\%. The system not only accelerates the overall container repair process but also provides shipping companies with a reliable basis for pursuing accountability or loss-sharing with involved parties, thereby more effectively managing operational risks and increasing overall operational profitability.

Abstract (Chinese) - I
Acknowledgments (Chinese) - II
Abstract - IV
Acknowledgments - V
Contents - VII
List of Tables - IX
List of Figures - X
Chapter 1: Introduction - 1
Chapter 2: Related Work - 3
2.1 Machine Learning and Deep Learning - 3
2.2 Neural Networks - 4
2.3 Transfer Learning - 6
2.4 Applications of Container Images - 7
Chapter 3: Methodology - 9
3.1 Model Architecture - 9
3.2 Training Process - 13
3.2.1 Loss Function - 13
3.2.2 Optimizer - 14
3.2.3 Hyperparameter Tuning - 17
3.3 Optimization and Regularization - 18
3.3.1 Batch Normalization - 18
3.3.2 Data Augmentation - 20
3.3.3 Dropout - 21
Chapter 4: Experimental Results - 23
4.1 Environment Setup - 23
4.2 Dataset - 24
4.3 Test Results - 28
Chapter 5: Conclusion - 37
Bibliography - 39

[1] Luís A Alexandre. "3D Object Recognition Using Convolutional Neural Networks with Transfer Learning between Input Channels." In Proceedings of International Conference on Intelligent Autonomous Systems, pages 889–898, 2016.

[2] Laith Alzubaidi, Jinglan Zhang, Amjad J. Humaidi, Ayad Al-Dujaili, Ye Duan, Omran Al-Shamma, José Santamaría, Mohammed A. Fadhel, Muthana Al-Amidie, and Laith Farhan. Review of Deep Learning: Concepts, CNN Architectures, Challenges, Applications, Future Directions. Journal of Big Data, 8: 1–74, 2021.

[3] Zhila Bahrami, Ran Zhang, Rakiba Rayhana, and Zheng Liu. "Deep Learning-Based Framework for Shipping Container Security Seal Detection." In Proceedings of Joint International Conference on Informatics, Electronics & Vision (ICIEV) and International Conference on Imaging, Vision & Pattern Recognition (ICIVPR), pages 1–7, 2021.

[4] Marouane Benmoussa and Abdelhak Mahmoudi. Machine Learning for Hand Gesture Recognition Using Bag-of-Words. In Proceedings of International Conference on Intelligent Systems and Computer Vision (ISCV), pages 1–7. IEEE, 2018.

[5] James Bergstra, Rémi Bardenet, Yoshua Bengio, and Balázs Kégl. "Algorithms for Hyper-Parameter Optimization." Advances in Neural Information Processing Systems, 24, 2011.

[6] Lin Chen, Rui Li, Yige Liu, Ruixuan Zhang, and Diane Myung-kyung Woodbridge. Machine Learning-Based Product Recommendation Using Apache Spark. In Proceedings of IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computed, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation, pages 1–6. IEEE, 2017.

[7] Xue-Wen Chen and Xiaotong Lin. Big Data Deep Learning: Challenges and Perspectives. IEEE Access, 2:514–525, 2014.

[8] Michael Crawford, Taghi M. Khoshgoftaar, Joseph D. Prusa, Aaron N. Richter, and Hamzah Al Najada. Survey of Review Spam Detection Using Machine Learning Techniques. Journal of Big Data, 2, 1–24, 2015.

RR Kadhim and MY Kamil. Evaluation of Machine Learning Models for Breast Cancer Diagnosis via Histogram of Oriented Gradients Method and Histopathology Images. International Journal on Recent and Innovation Trends in Computing and Communication, 10(4), 36–42, 2022.

[9] Yu-nan Dong and Guang-sheng Liang. "Research and Discussion on Image Recognition and Classification Algorithm Based on Deep Learning." In Proceedings of International Conference on Machine Learning, Big Data and Business Intelligence (MLBDBI), pages 274–278, 2019. IEEE.

[10] Jiuxiang Gu, Zhenhua Wang, Jason Kuen, Lianyang Ma, Amir Shahroudy, Bing Shuai, Ting Liu, Xingxing Wang, Gang Wang, Jianfei Cai, and others. "Recent Advances in Convolutional Neural Networks." Pattern Recognition, 77: 354–377, 2018.

[11] William Grant Hatcher and Wei Yu. "A Survey of Deep Learning: Platforms, Applications and Emerging Research Trends." IEEE Access, 6: 24411–24432, 2018.

[12] Benradi Hicham, Chater Ahmed, and Lasfar Abdelali. Face Recognition Method combining SVM Machine Learning and Scale Invariant Feature Transform. In Proceedings of International Conference on Innovation, Modern Applied Science & Environmental Studies, 2022.
[13] Geoffrey Hinton, Nitish Srivastava, and Kevin Swersky. "Neural Networks for Machine Learning." Coursera - video lectures, 2012. Lecture 6A: “Overview of Mini-Batch Gradient Descent”.

[14] Gao Huang, Zhuang Liu, Laurens Van Der Maaten, and Kilian Q Weinberger. "Densely Connected Convolutional Networks." In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 4700–4708, 2017.

[15] Mahbub Hussain, Jordan J. Bird, and Diego R. Faria. "A Study on CNN Transfer Learning for Image Classification." In Proceedings of Advances in Computational Intelligence System, pages 191–202, 2019. Springer, 2019.

[16] Sergey Ioffe and Christian Szegedy. "Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift." In Proceedings of International Conference on Machine Learning (ICML), pages 448–456, 2015.

[17] Rania R. Kadhim and Mohammed Y. Kamil. Evaluation of Machine Learning Models for Breast Cancer Diagnosis via Histogram of Oriented Gradients Method and Histopathology Images. International Journal on Recent and Innovation Trends in Computing and Communication, 10(4), 36–42, 2022

[18] Aditya Khamparia and Karan Mehtab Singh. "A Systematic Review on Deep Learning Architectures and Applications." Expert Systems, 36(3): e12400, 2019.

[19] Hee E. Kim, Alejandro Cosa-Linan, Nandhini Santhanam, Mahboubeh Jannesari, Mate E Maros, and Thomas Ganslandt. "Transfer Learning for Medical Image Classification: A Literature Review." BMC Medical Imaging, 22(1): 69, 2022.


[20] Diederik P. Kingma and Jimmy Ba. "Adam: A Method for Stochastic Optimization." arXiv:1412.6980, 2014.

[21] Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. Deep Learning. Nature, 521(7553), 436–444, 2015.

[22] Yann LeCun, Léon Bottou, Yoshua Bengio, and Patrick Haffner. "Gradient-Based Learning Applied to Document Recognition." In Proceedings of the IEEE, 86(11): 2278–2324, 1998.

[23] Ruijun Liu, Yuqian Shi, Changjiang Ji, and Ming Jia. "A Survey of Sentiment Analysis Based on Transfer Learning." IEEE Access, 7: 85401–85412, 2019.

[24] Andrew MacFarlane, Sondess Missaoui, and Sylwia Frankowska-Takhari. On Machine Learning and Knowledge Organization in Multimedia Information Retrieval. Knowledge Organization, 47(1), 45–55, 2020.

[25] Nijat Mehdiyev, Joerg Evermann, and Peter Fettke. A Novel Business Process Prediction Model Using a Deep Learning Method. Business & Information Systems Engineering, 62, 143–157, 2020.

[26] Riccardo Miotto, Fei Wang, Shuang Wang, Xiaoqian Jiang, and Joel T. Dudley. "Deep Learning for Healthcare: Review, Opportunities and Challenges." Briefings in Bioinformatics, 19(6): 1236–1246, 2018.
[27] Maryam M Najafabadi, Flavio Villanustre, Taghi M Khoshgoftaar, Naeem Seliya, Randall Wald, and Edin Muharemagic. Deep Learning Applications and Challenges in Big Data Analytics. Journal of Big Data, 2(1), 1–21, 2015.

[28] Keiron O'Shea and Ryan Nash. "An Introduction to Convolutional Neural Networks." arXiv:1511.08458, 2015.

[29] Boris T Polyak. "Some Methods of Speeding Up the Convergence of Iteration Methods." USSR Computational Mathematics and Mathematical Physics, 4(5): 1–17, 1964.

[30] E. Popoff, M. Besada, J. P. Jansen, S. Cope, and Steve Kanters. Aligning Text Mining and Machine Learning Algorithms with Best Practices for Study Selection in Systematic Literature Reviews. Systematic Reviews, 9(1), 1–12, 2020.

[31] David E. Rumelhart, Geoffrey E. Hinton, and Ronald J. Williams. "Learning Representations by Back-Propagating Errors." Nature, 323(6088): 533–536, 1986.

Luís A Alexandre. "3D Object Recognition Using Convolutional Neural Networks with Transfer Learning between Input Channels." In Proceedings of Intelligent Autonomous Systems, pages 889–898, 2016.

[32] V. Y. Sandeep, Snigdha Sen, and K Santosh. "Analyzing and Processing of Astronomical Images Using Deep Learning Techniques." In Proceedings of IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT), pages 1–6, 2021.

[33] D. R. Sarvamangala and Raghavendra V. Kulkarni. "Convolutional Neural Networks in Medical Image Understanding: A Survey." Evolutionary Intelligence, 15(1): 1–22, 2022.

[34] Manali Shaha and Meenakshi Pawar. "Transfer Learning for Image Classification." In Proceedings of International Conference on Electronics, Communication and Aerospace Technology (ICECA), pages 656–660, 2018.

[35] Claude Elwood Shannon. "A Mathematical Theory of Communication." The Bell System Technical Journal, 27(3): 379–423, 1948.

[36] Wei Shi, Cun Cheng, Zhi-Yuan Luo, Yan-Jie Yao, and Yu-Ying Hong. "Empty Container Verification Using Deep Learning." In Proceedings of International Conference on Wireless Communications, Networking and Applications, pages 156–160, 2017.

[37] Karen Simonyan and Andrew Zisserman. "Very Deep Convolutional Networks for Large-Scale Image Recognition." arXiv:1409.1556, 2014.

[38] Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. "Dropout: A Simple Way to Prevent Neural Networks from Overfitting." The Journal of Machine Learning Research, 15(1): 1929–1958, 2014.

[39] Pin Wang, En Fan, and Peng Wang. Comparative Analysis of Image Classification Algorithms Based on Traditional Machine Learning and Deep Learning. Pattern Recognition Letters, 141, 61–67, 2021.

[40] Karl Weiss, Taghi M. Khoshgoftaar, and DingDing Wang. "A Survey of Transfer Learning." Journal of Big Data, 3(1): 1–40, 2016.

[41] Wenming Yang, Xuechen Zhang, Yapeng Tian, Wei Wang, Jing-Hao Xue, and Qingmin Liao. "Deep Learning for Single Image Super-Resolution: A Brief Review." IEEE Transactions on Multimedia, 21(12): 3106–3121, 2019. IEEE.

[42] Ran Zhang, Zhila Bahrami, Teng Wang, and Zheng Liu. "An Adaptive Deep Learning Framework for Shipping Container Code Localization and Recognition." IEEE Transactions on Instrumentation and Measurement, 70: 1–13, 2020.

[43] Zhong-Qiu Zhao, Peng Zheng, Shou-tao Xu, and Xindong Wu. "Object Detection with Deep Learning: A Review." IEEE Transactions on Neural Networks and Learning Systems, 30(11): 3212–3232, 2019. IEEE.