臺灣博碩士論文加值系統

本論文主要探討醫療用品的辨識方法，可應用於傷患救護的即時影像辨識、影像錄製後的內容物件辨識，及可提供成往後醫護新手的學習教材，用以減少醫療糾紛及加快醫療救護新手學習的時間。坊間有很多成熟的技術可用於影像物件辨識，且廣泛應用於生活中，傳統的方法如RNN及CNN，因預處理需要大量時間，後來即衍生出YOLO，藉以加快運算的時間，另外也提高辨識的準確度。本論文中，將藉以YOLOv7自動辨識醫療用品的類別，來回饋給用戶知曉使用到什麼樣的醫療物品，以避免醫療糾紛的產生，及讓醫護新手在學習時，可更了解相關醫療用品的使用範疇，達到提升日後操作的準確性。

This paper mainly discusses the identification method of medical supplies, which can be applied to real-time image and after image recording recognition, and can provide learning materials for future medical novice to reduce medical disputes and speed up medical rescue. There are many mature technologies in the market that can be used for real-time image object recognition, and are widely used in life. Traditional methods such as RNN and CNN require a lot of time for preprocessing, so YOLO was later derived to speed up the calculation time, and also improve recognition accuracy. In this paper, YOLOv7 will be used to automatically identify the type of medical supplies, and give feedback to users to know what medical supplies are used, so as to avoid the occurrence of medical disputes, and let medical novice students learn more about related medical supplies. order to improve the accuracy of future operations.

摘要
ABSTRACT
致謝
目錄
圖目錄
表目錄
第一章、 緒論
1.1 前言
1.2 研究動機
1.3 研究架構
第二章、基礎理論
2.1、人工智慧之介紹與演進
2.2、機器學習之介紹
2.3、人工神經網路之介紹
2.4、深度學習之介紹
2.5、卷積神經網路之介紹
2.6、目標檢測演進與介紹
2.7、 YOLO歷代演進
2.8、IMAGE LABEL之介紹
2.9、LABELIMG之介紹
第三章、實驗方法與流程
3.1、實驗方法
3.2、實驗流程
3.3、環境架構
3.3.1、影像選擇與蒐集
3.3.2、LABELIMG物件標註
3.4、 開始訓練
第四章、實驗結果與討論
4.1、實驗結果之效能比較
4.2、實驗結果之混淆矩陣比較
4.3、實驗結果之量化指標比較
4.3.1、PRECISION實驗結果比較
4.3.2、RECALL實驗結果比較
4.3.3、F1-SCORE實驗結果比較
4.3.4、MAP實驗結果比較
4.4 物件辨識結果
第五章、 結論
參考文獻

Winston, Patrick Henry., Artificial intelligence. Addison-Wesley Longman Publishing Co., Inc., 1984.
[李開復 and 王詠剛, 人工智慧來了. 遠見天下文化出版股份有限公司, 2017.
Mirjalili, Seyedali, and Seyedali Mirjalili, "Genetic algorithm," Evolutionary Algorithms and Neural Networks: Theory and Applications, pp. 43-55, 2019.
Liao, Shu-Hsien., "Expert system methodologies and applications—a decade review from 1995 to 2004," vol. 28, no. 1, pp. 93-103, 2005.
Bishop, Chris M., "Neural networks and their applications," vol. 65, no. 6, pp. 1803-1832, 1994.
Barker, J., Marxer, R., Vincent, E., & Watanabe, S, "The third ‘CHiME’speech separation and recognition challenge: Dataset, task and baselines," 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 504-511, 2015.
Mitchell, Tom M., and Tom M. Mitchell., Machine learning. New York: McGraw-hill, 1997.
Cunningham, P., Cord, M., & Delany, S. J., "Supervised learning," Machine learning techniques for multimedia, pp. 21-49, 2008.
Kaelbling, Leslie Pack, Michael L. Littman, and Andrew W. Moore., "Reinforcement learning: A survey," vol. 4, pp. 237-285, 1996.
Barlow, Horace B., "Unsupervised learning," vol. 1, no. 3, pp. 295-311, 1989.
探討機器學習與深度學習之差異, “https://www.wpgdadatong.com/cn/blog/detail/40668”.
Yegnanarayana, Bayya., Artificial neural networks. PHI Learning Pvt. Ltd., 2009.
Schuldt, Christian, Ivan Laptev, and Barbara Caputo., "Recognizing human actions: a local SVM approach," In Proceedings of the 17th International Conference on Pattern Recognition, vol. 3, pp. 32-36, 2004.
Sherstinsky, Alex., "Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network," Physica D: Nonlinear Phenomena, vol. 404, p. 132306, 2020.
Albawi, Saad, Tareq Abed Mohammed, and Saad Al-Zawi., "Understanding of a convolutional neural network," 2017 international conference on engineering and technology (ICET)., pp. 1-6, 2017.
Y.-H. Siao., 完整解析AI人工智慧-大和有話說, ”https://dahetalk.com/”, 2018.
LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton., "Deep learning," vol. 521, no. 7553, pp. 436-444, 2015.
[Day 02] 什麼是tinyML? - iT邦幫忙, ”https://ithelp.ithome.com.tw/m/articles/10264226”.
Lin, Henry W., Max Tegmark, and David Rolnick., "Why does deep and cheap learning work so well?," vol. 168, no. 6, pp. 1223-1247, 2017.
Papageorgiou, Constantine P., Michael Oren, and Tomaso Poggio., "A general framework for object detection," Sixth International Conference on Computer Vision, pp. 555-562, 1998.
【機器學習】傳統目標檢測算法總結 - CSDN, ”https://blog.csdn.net/qq_32742009/article/details/81388228”.
He, K., Zhang, X., Ren, S., & Sun, J., "Spatial pyramid pooling in deep convolutional networks for visual recognition," vol. 37, no. 9, pp. 1904-1916, 2015.
Girshick, Ross., "Fast r-cnn," Proceedings of the IEEE international conference on computer vision, pp. 1440-1448, 2015.
基於深度學習的目標檢測技術演進, “https://www.cnblogs.com/skyfsm/p/6806246.html”
Ren, S., He, K., Girshick, R., & Sun, J., "Faster r-cnn: Towards real-time object detection with region proposal networks," Advances in neural information processing systems, vol. 28, 2015.
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A., "You only look once: Unified, real-time object detection," Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 779-788, 2016.
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C. Y., & Berg, A. C., "Ssd: Single shot multibox detector," Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14, pp. 21-37, 2016.
Redmon, J., & Farhadi, A., "YOLO9000: better, faster, stronger," Proceedings of the IEEE conference on computer vision and pattern recognition., pp. 7263-7271, 2017.
Redmon, J., & Farhadi, A., "Yolov3: An incremental improvement," arXiv preprint arXiv:1804.02767, 2018.
Bochkovskiy, Alexey, Chien-Yao Wang, and Hong-Yuan Mark Liao., "Yolov4: Optimal speed and accuracy of object detection," arXiv preprint arXiv:2004.10934, 2020.
Li, Chuyi, et al., "YOLOv6: A single-stage object detection framework for industrial applications," arXiv preprint arXiv:2209.02976, 2022.
LI, Chuyi, et al, "YOLOv6 v3. 0: A Full-Scale Reloading," arXiv preprint arXiv:2301.05586, 2023.
WANG, Chien-Yao; BOCHKOVSKIY, Alexey; LIAO, Hong-Yuan Mark., "YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors," arXiv preprint arXiv:2207.02696, 2022.
鄭建彥, 建立自己的YOLO辨識模型 – 以柑橘辨識為例, “https://blog.cavedu.com/2019/07/25/yolo-identification-model/”, 2019
比較 GeForce 顯示卡 - NVIDIA, “https://www.nvidia.com/zh-tw/geforce/graphics-cards/compare/?section=compare-20”
Intel® Core™ i7-9700 處理器, “https://www.intel.com.tw/content/www/tw/zh/products/sku/191792/intel-core-i79700-processor-12m-cache-up-to-4-70-ghz/specifications.html”
CUDA Toolkit - NVIDIA, “https://developer.nvidia.com/cuda-toolkit”
Confusion matrix - wikipedia, “https://en.wikipedia.org/wiki/Confusion_matrix”
Rezatofighi, Hamid, et al., "Generalized intersection over union: A metric and a loss for bounding box regression," Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 658-666, 2019.