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

NCU Institutional Repository > 資訊電機學院 > 通訊工程研究所 > 博碩士論文 > Item 987654321/95309

請使用永久網址來引用或連結此文件: http://ir.lib.ncu.edu.tw/handle/987654321/95309

題名:	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
作者:	楊昊汶;Yang, Hao-Wen
貢獻者:	通訊工程學系
關鍵詞:	醫療物聯網;邊緣運算;人臉偵測;人臉辨識;FaceNet;Internet of Medical Things;Edge Computing;Face Detection;Face Recognition;FaceNet
日期:	2024-07-15
上傳時間:	2024-10-09 16:38:44 (UTC+8)
出版者:	國立中央大學
摘要:	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。;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.
顯示於類別:	[通訊工程研究所] 博碩士論文

文件中的檔案:

檔案	描述	大小	格式	瀏覽次數
index.html		0Kb	HTML	21	檢視/開啟

在NCUIR中所有的資料項目都受到原著作權保護.

社群 sharing

資料載入中.....