基於FaceNet和邊緣運算實現人臉辨識的智慧取藥系統

以作者查詢圖書館館藏

、以作者查詢臺灣博碩士

、以作者查詢全國書目

、勘誤回報

、線上人數：99

、訪客IP：13.59.153.178

姓名

楊昊汶(Hao-Wen Yang) 查詢紙本館藏

畢業系所

通訊工程學系

論文名稱

基於FaceNet和邊緣運算實現人臉辨識的智慧取藥系統
(To Realize Facial Recognition Smart Medicine Collection System Based on FaceNet and Edge Computing)

相關論文

★ UHF頻段RFID彈藥管理系統之設計、實作與評估	★ 移動物偵測與追蹤之IP Camera系統
★ SDN自適應性自動化網路安全之研究	★ Wi-Fi Direct Service 應用於IoT
★ 射頻前端電路應用於載波聚合長期演進技術	★ 3C無線充電裝置運用在車載系統所產生之EMI輻射
★ 基於LoRa技術的物聯網前端防盜警示感測裝置實作與評估	★ DOCSIS 3.1 效能研究與下行通道干擾阻隔之設計
★ 藍芽無線光學投影翻譯筆	★ 手持裝置應用於MIMO ( 8x8 ) Wi-Fi系統之設計
★ 基於無伺服器運算之智慧農業雲端系統設計與研究	★ 嵌入式系統實現電梯物聯網
★ 在802.11 Ad-Hoc網路中基於速率考量之路由協定設計	★ 合作博弈與灰色模糊方法改善無線網路之性能
★ 採用拍賣策略之動態分散式方法於減少叢集小型基地台間干擾之研究	★ 在LTE-A下聚合未授權頻譜及動態分配資源以優化系統效能

檔案

[Endnote RIS 格式]

[Bibtex 格式]

[相關文章]

[文章引用]

[完整記錄]

[館藏目錄]

至系統瀏覽論文 (2026-7-10以後開放)

摘要(中)

台灣已是高齡社會，並且國發會推估將在 2025 年邁入超高齡社會，對醫療的需求勢必日益增加。然而，近年醫院卻面臨著護理師和藥師短缺的問題，除了高壓工作環境、高工時和低薪資，還有須輪流值夜班及處理大量病患的調劑工作等問題，使得醫院藥師離職率居高不下。人手不足的情況導致許多醫院的領藥窗口總是大排長龍，候藥時間的增加，也對病人的就醫體驗造成負面影響。
本論文提出一個基於邊緣運算（Edge Computing）的智慧取藥系統，
旨在能與傳統健保卡領藥的方式「並行」運作，提供一個替代的領藥途徑，進而有效減少候藥時的人流壓力和等待時間，提高藥品領取的效率。該系統採用當前最新一代的樹莓派 5（Raspberry Pi 5）作為邊緣裝置，結合YOLOv5和FaceNet實現人臉辨識的即時身分驗證，確保病人正確領出自己的藥品。透過邊緣運算的理念，人臉偵測與辨識的過程都完全在邊緣端的樹莓派完成，無須再把數據傳輸到雲端伺服器處理，從而加快數據處理速度。最後，將模型和相關資料儲存於AWS雲端服務中，並透過創建LINE Bot讓病人可以進行雙重認證，進一步提升系統安全性。此研究也期盼未來能在無人藥局的實現上，提供新穎的應用概念。

摘要(英)

Taiwan is already an aged society, and the National Development Council (NDC) estimates that it will become a super-aged society by 2025, which will increase the demand for healthcare. However, in recent years, hospitals have faced a shortage of registered professional nurses and pharmacists. In addition to the high-pressure work environment, high working hours and low pay, the high turnover rate of hospital pharmacists is due to the need to work night shifts and to handle a large number of patients′ dispensing duties. The shortage of manpower has led to long queues at the medicine collection windows of many hospitals, and the increase in waiting time for medicine collection has also had a negative impact on the patients′ experience. This thesis proposes an edge computing-based intelligent medicine collection system, which aims to operate ‘side-by-side’ with the traditional National Health Insurance (NHI) card to provide an alternative way to collect medicines, thus effectively reducing the pressure and waiting time of medicine collection and improving the efficiency of medicine adoption. The system utilizes the latest generation Raspberry Pi 5 as an edge device, and combines YOLOv5s and FaceNet to achieve real-time face recognition authentication, ensuring that patients receive their medication correctly. With the concept of edge computing, the process of face detection and recognition is done entirely on the Raspberry Pi at the edge, eliminating the need to transfer the data to a cloud server for processing, thus speeding up the data processing. Finally, the model and related data are stored in the AWS cloud service, and a LINE Bot is created to allow double authentication of the patient, further enhancing the security of the system. This thesis is also expected to provide novel application concepts for the realization of human-less pharmacy in the future.

關鍵字(中)

★ 醫療物聯網
★ 邊緣運算
★ 人臉偵測
★ 人臉辨識
★ FaceNet

關鍵字(英)

★ Internet of Medical Things
★ Edge Computing
★ Face Detection
★ Face Recognition
★ FaceNet

論文目次

中文摘要 i
英文摘要 ii
誌謝 iv
目錄 v
圖目錄 viii
表目錄 xi
第一章序論 1
1-1 前言 1
1-2 研究動機 2
1-3 研究目的 4
1-4 論文架構 5
第二章相關研究背景 6
2-1 邊緣運算 6
2-1-1 邊緣裝置—樹莓派 8
2-1-2 Raspberry Pi Camera Module相機模組 10
2-2 物件偵測 12
2-2-1 卷積神經網路CNN 14
2-2-2 YOLO 15
2-3 FaceNet 人臉辨識 18
2-3-1 三元組損失（Triplet Loss） 19
2-4 機器學習 20
2-4-1 資料強化 21
2-4-2 增量式學習 22
2-5 LINE 23
2-5-1 LINE Bot 23
2-6 AWS 雲端服務 24
2-6-1 AWS IAM 24
2-6-2 Amazon S3 24
第三章系統架構與流程 25
3-1 系統架構 25
3-2 伺服器端 26
3-2-1 收集人臉圖像 27
3-2-2 人臉偵測模型訓練 28
3-2-3 資料強化 31
3-2-4 人臉辨識模型訓練 33
3-2-5 建立人臉特徵資料庫及部屬模型 35
3-2-6 效能評估 37
3-3 邊緣端 39
3-3-1 辨識預測 40
3-3-2 系統硬體設計 42
3-3-3 系統運作及LINE Bot通知 45
第四章模擬與分析 47
4-1 人臉偵測模型訓練結果與分析 47
4-1-1 原始模型與增量式學習訓練結果分析 47
4-1-2 不同人臉偵測模型之效能比較 49
4-2 人臉辨識模型訓練結果與分析 51
4-2-1 模型訓練結果分析 51
4-2-2 模型效能評估 53
第五章結論與未來展望 56
參考文獻 58

參考文獻

[1] A. Haydari and Y. Yılmaz, "Deep Reinforcement Learning for Intelligent Transportation Systems: A Survey", IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 1, pp. 11-32, Jan. 2022.
[2] H. Kathiriya, A. Pandya, V. Dubay and A. Bavarva, "State of Art: Energy Efficient Protocols for Self-Powered Wireless Sensor Network in IIoT to Support Industry 4.0", 2020 8th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO), Noida, India, pp. 1311-1314, 2020.
[3] L. Sun, X. Jiang, H. Ren and Y. Guo, "Edge-Cloud Computing and Artificial Intelligence in Internet of Medical Things: Architecture, Technology and Application", IEEE Access, vol. 8, pp. 101079-101092, 2020.
[4] C. E. M. Gomes, V. F. Lucena, F. Yazdi and P. Göhner, "Extending an intelligent medicine cabinet through the use of consumer electronic devices in order to increase the medication adherence", 2015 IEEE 5th International Conference on Consumer Electronics - Berlin (ICCE-Berlin), Berlin, Germany, pp. 98-102, 2015.
[5] R. Garg, I. Bhatt, K. Eashwer and S. K. Jindal, "Experimental Design and Implementation of RFID based Clinical Medicine Dispenser", 2022 1st International Conference on the Paradigm Shifts in Communication, Embedded Systems, Machine Learning and Signal Processing (PCEMS), Nagpur, India, pp. 33-36, 2022.
[6] P. J. Sun, "Privacy Protection and Data Security in Cloud Computing: A Survey, Challenges, and Solutions", IEEE Access, vol. 7, pp. 147420-147452, 2019.
[7] W. Yu et al., "A Survey on the Edge Computing for the Internet of Things", IEEE Access, vol. 6, pp. 6900-6919, 2018.
[8] J. Pan and J. McElhannon, "Future Edge Cloud and Edge Computing for Internet of Things Applications", IEEE Internet of Things Journal, vol. 5, no. 1, pp. 439-449, Feb. 2018.
[9] M. Abrar, U. Ajmal, Z. M. Almohaimeed, X. Gui, R. Akram and R. Masroor, "Energy Efficient UAV-Enabled Mobile Edge Computing for IoT Devices: A Review", IEEE Access, vol. 9, pp. 127779-127798, 2021.
[10] N. Valov and I. Valova, "Raspberry Pi as a Tool to Combine Different Courses Part of University Education", 2019 18th International Conference on Information Technology Based Higher Education and Training (ITHET), pp. 1-5, Magdeburg, Germany, 2019.
[11] 網路資料on line resources：HACKATRONIC：Raspberry Pi 5 Pinout, specifications, Pricing A Complete Guide。取自https://www.hackatronic.com/raspberry-pi-5-pinout-specifications-pricing-a-complete-guide/
[12] 網路資料on line resources：Raspberry Pi：Camera。取自https://www.raspberrypi.com/documentation/accessories/camera.html
[13] Z. -Q. Zhao, P. Zheng, S. -T. Xu and X. Wu, "Object Detection With Deep Learning: A Review", IEEE Transactions on Neural Networks and Learning Systems, vol. 30, no. 11, pp. 3212-3232, Nov. 2019.
[14] Ki-Yeong Park, Sun-Young Hwang, "An improved Haar-like feature for efficient object detection", Pattern Recognition Letters, vol. 42, pp. 148-153, 2014.
[15] 網路資料on line resources：Cinnamon AI Taiwan：深度學習：CNN原理。取自https://cinnamonaitaiwan.medium.com/%E6%B7%B1%E5%BA%A6%E5%AD%B8%E7%BF%92-cnn%E5%8E%9F%E7%90%86-keras%E5%AF%A6%E7%8F%BE-432fd9ea4935
[16] J. Redmon, S. Divvala, R. Girshick and A. Farhadi, "You Only Look Once: Unified, Real-Time Object Detection", 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, pp. 779-788, 2016.
[17] L. Jiao et al., "A Survey of Deep Learning-Based Object Detection", IEEE Access, vol. 7, pp. 128837-128868, 2019.
[18] R. Bao and Z. Yang, "CNN-Based Regional People Counting Algorithm Exploiting Multi-Scale Range-Time Maps With an IR-UWB Radar", IEEE Sensors Journal, vol. 21, no. 12, pp. 13704-13713, 15 June15, 2021.
[19] L. Yan, Z. Chen, X. Wu, X. Yuan, J. Zhu and J. Li, "Object Detection Method Based On Improved SSD Algorithm For Smart Grid", 2021 IEEE 5th Conference on Energy Internet and Energy System Integration (EI2), Taiyuan, China, pp. 3020-3024, 2021.
[20] A. Bochkovskiy, C. Y. Wang and H. Y. Liao, "YOLOv4: Optimal Speed and Accuracy of Object Detection", ArXiv, https://doi.org/10.48550/arXiv.2004.10934, 2020.
[21] 網路資料on line resources：ultralytics：YOLOv5。取自https://github.com/ultralytics/yolov5
[22] F. Schroff, D. Kalenichenko and J. Philbin, "FaceNet: A unified embedding for face recognition and clustering", 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, pp. 815-823, 2015.
[23] I. William, D. R. Ignatius Moses Setiadi, E. H. Rachmawanto, H. A. Santoso and C. A. Sari, "Face Recognition using FaceNet (Survey, Performance Test, and Comparison)", 2019 Fourth International Conference on Informatics and Computing (ICIC), Semarang, Indonesia, pp. 1-6 , 2019.
[24] A. Singh and R. Kumar, "Heart Disease Prediction Using Machine Learning Algorithms", 2020 International Conference on Electrical and Electronics Engineering (ICE3), Gorakhpur, India, pp. 452-457, 2020.
[25] T. R. N and R. Gupta, "A Survey on Machine Learning Approaches and Its Techniques:", 2020 IEEE International Students′ Conference on Electrical,Electronics and Computer Science (SCEECS), Bhopal, India, pp. 1-6, 2020.
[26] A. Mikołajczyk and M. Grochowski, "Data augmentation for improving deep learning in image classification problem", 2018 International Interdisciplinary PhD Workshop (IIPhDW), Świnouście, Poland, pp. 117-122, 2018.
[27] C. Khosla and B. S. Saini, "Enhancing Performance of Deep Learning Models with different Data Augmentation Techniques: A Survey", 2020 International Conference on Intelligent Engineering and Management (ICIEM), London, UK, pp. 79-85, 2020.
[28] M. Masana, X. Liu, B. Twardowski, M. Menta, A. D. Bagdanov and J. van de Weijer, "Class-Incremental Learning: Survey and Performance Evaluation on Image Classification", IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 5, pp. 5513-5533, 1 May 2023.
[29] Q. Yang, Y. Gu and D. Wu, "Survey of incremental learning", 2019 Chinese Control And Decision Conference (CCDC), Nanchang, China, pp. 399-404, 2019.
[30] 網路資料on line resources：LINE。取自https://zh.wikipedia.org/zh-tw/LINE
[31] 網路資料on line resources：LINE Engineering：開發LINE聊天機器人不可不知的十件事。取自
https://engineering.linecorp.com/zh-hant/blog/line-device-10/
[32] 網路資料on line resources：AWS IAM。取自https://docs.aws.amazon.com/zh_tw/IAM/latest/UserGuide/introduction.html
[33] 網路資料on line resources：Amazon S3。取自https://docs.aws.amazon.com/zh_tw/AmazonS3/latest/userguide/Welcome.html
[34] S. Yang, P. Luo, C. C. Loy and X. Tang, "WIDER FACE: A Face Detection Benchmark", 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, pp. 5525-5533, 2016.
[35] G. B. Huang, M. Mattar, T. L. Berg and E. Learned-Miller, "Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments", University of Massachusetts: Amherst, Technical Report 07-49, 2007.
[36] Kıvrak, O., & Gürbüz, M. Z., "Performance Comparison of YOLOv3,YOLOv4 and YOLOv5 algorithms : A Case Study for Poultry Recognition", Avrupa Bilim Ve Teknoloji Dergisi(38), pp. 392-397, 2022.
[37] Zhang, Z.; Huang, J.; Hei, G.; Wang, W., "YOLO-IR-Free: An Improved Algorithm for Real-Time Detection of Vehicles in Infrared Images", Sensors 2023, 23, 8723. https://doi.org/10.3390/s23218723
[38] A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, H. Adam, "MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications", arXiv, arXiv:1704.04861v1, 2017.
[39] A. Arias-Duart, E. Mariotti, D. Garcia-Gasulla and J. M. Alonso-Moral, "A Confusion Matrix for Evaluating Feature Attribution Methods", 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Vancouver, BC, Canada, pp. 3709-3714, 2023.
[40] K. Zhang, Z. Zhang, Z. Li and Y. Qiao, "Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks", IEEE Signal Processing Letters, vol. 23, no. 10, pp. 1499-1503, Oct. 2016.

指導教授

吳中實(Jung-Shyr Wu)

審核日期

2024-7-15

推文