基於深度學習的低解析度熱感應器在被照護者床旁偵測系統的模型訓練與實現

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：56

、訪客IP：3.138.34.93

姓名

劉漢武(HAN-WU LIU) 查詢紙本館藏

畢業系所

生醫科學與工程學系

論文名稱

基於深度學習的低解析度熱感應器在被照護者床旁偵測系統的模型訓練與實現
(Model Training and Implementation of a Low- Resolution Thermal Sensor-Based Bedside Detection System for Caregivers Using Deep Learning)

相關論文

★ 非接觸式生理感測訊號分析研究	★ 以磁振造影探究有病灶及無病灶神經疾病的自動偵測方法之開發
★ 複雜系統跨頻率耦合方法	★ 不同麻醉深度之相位-振幅耦合量測及強度比較
★ 基於小波轉換之單一導程心電圖重構12導程心電圖與分類	★ 發展非侵入式即時交感神經活性指標之量測系統
★ 以靜息態功能性磁振造影探討頸動脈支架手術對於頸動脈狹窄病患大腦功能之影響	★ 運用加速度計實現具多項生理功能量測之即時監控IOT平台
★ 功能性抗生物沾黏單層膜於冠狀動脈心血管疾病標誌物之檢測應用	★ 創新利用模擬呼吸竇性心律不整之多階熵評估乙型腎上腺素阻斷劑在心衰竭病人之治療成效
★ 發展高抗干擾非接觸式生理訊號監測系統	★ 應用特徵分群技術於非侵入式神經活性與行為活動訊號之生物指標萃取
★ 應用模擬電生理及人工智慧技術創造跨臨床心電圖資料庫之心肌缺血成像模型	★ 從同步鼾聲聲學分析和睡眠動態核磁共振成像進行靜態顱面測量和動態上呼吸道塌陷觀察，並探討其與阻塞性睡眠呼吸中止症嚴重程度的關聯。
★ 口內負壓睡眠裝置對於睡眠呼吸中止病人的轉譯研究- 針對解剖結構治療療效及策略探討	★ 體外加強反搏治療裝置開發

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 (2029-7-14以後開放)

摘要(中)

本研究是基於在考量被照護者隱私狀況，以較低成本的低解析度熱感應器，配合深度學習的方式，進而監控被照護者之床旁狀況，包括跌倒偵測、離床警示、翻身狀況及睡眠品質。本設計的研究中使用的低解析度熱感應器安裝於病房上方，輸出圖像raw data 後再轉成圖像，再搭配實際攝像機做標識(Labeling) 判斷，最後傳至類神經網路(CNN) 做模型學習。本論文使用自行架設之環境實錄進行模型訓練，經過整理後取得10144 張圖像。此資料集80% 用來訓練模型，20% 用來驗證模型，模型調整後可達87.92%以上的準確率(accuracy radio)。

摘要(英)

This study aims to monitor the bedside conditions of caregivers, including fall detection, bed exit alerts, turning over, and sleep quality, using low-resolution thermal sensors that are more cost-effective and consider caregiver privacy. The low-resolution thermal sensors used in this design are installed above the patient room, output image raw data, and then converted into images. They are then labeled and judged using an actual camera and finally transmitted to a deep neural network (DNN) for model training. This paper uses the data from the self-built environment for model training and obtains 10,144 images after整理. 80% of this dataset is used to train the model, and 20% is used to verify the model. After the model is adjusted, the accuracy ratio can reach over 87.92%..

關鍵字(中)

★ 深度學習
★ 長者照護
★ 電腦視覺
★ 低解析度熱感應器
★ 在床狀態偵測

關鍵字(英)

論文目次

摘要 i
Abstract ii
誌謝 iii
目錄 iv
圖目錄 vi
表目錄 viii
第一章、緒論 1
1-1. 研究背景與動機 1
1-2. 相關研究文獻 2
1-3. 研究目標 4
1-4. 研究貢獻 4
1-5. 論文架構 4
第二章、方法與環境說明 5
2-1. 硬體架構 5
2-2. 紅外線熱感測器 6
2-3. 測試環境 7
2-4. 基於CNN(Convolution Neural Network) 原理 9
2-5. TensorFlow 11
2-6. 混淆矩陣(Confusion Matrix) 12
第三章、研究內容與結果 15
3-1. 採集訓練及測試的資料 15
3-2. 資料預處理 17
3-3. 訓練及測試模型 24
3-4. 結果與討論 24
第四章、總結與未來展望 33
4-1. 總結 33
4-2. 未來展望 33
參考資料 34
附錄一 36
附錄二 38
附錄三 40
附錄四 45
附錄五 46
附錄六 48

參考文獻

[1] P. Gerland, "What′s Beneath the Future: World Population Prospects," in Semaine Data-SHS, 2023.
[2] 賴. C.-Y. L. 楊聖睿(Sheng-Rui Yang), 許津萍(Chin-Ping Hsu),曾秀學(Hsiu-Hsueh Tseng),鄭舒倖(Shu-Hsing Cheng),鄭泰如(Tai-Ju Cheng), "Skin Change at Life′s End (SCALE): Kennedy Terminal Ulcers (KTU)," 醫學與健康期刊, vol. 9, no. 2, pp. 91-96, 2020.
[3] F. Lai, J. Kandukuri, B. Yuan, Z. Zhang, and M. Jin, "Thermal image enhancement through the deconvolution methods for low-cost infrared cameras," Quantitative infrared thermography journal, vol. 15, no. 2, pp. 223-239, 2018.
[4] L. M. Ng and R. Simmons, "Infrared spectroscopy," Analytical chemistry, vol. 71, no. 12, pp. 343-350, 1999.
[5] X. Yu and X. Lin, "FALL DETECTION USING LOW-RESOLUTION THERMAL SENSOR," 2019.
[6] Z. Zhang, E. Klassen, and A. Srivastava, "Gaussian blurring-invariant comparison of signals and images," IEEE Transactions on Image Processing, vol. 22, no. 8, pp. 3145-3157, 2013.
[7] M.-H. Lin, "Fall Detection Using Low Resolution Thermopile Array Sensor and Deep Learning," National Cheng Kung University, 2021.
[8] C. E. Fabián Riquelme, Tomás Rodenas, Jean-Gabriel Minonzio and Carla Taramasco. (2019, Oct 21) eHomeSeniors Dataset: An Infrared Thermal Sensor Dataset for Automatic Fall Detection Research. Sensors. 16.
[9] Y.-C. T. Sheng-Yang Chiu, Jen-Jee Chen, "Low-Resolution Thermal Sensor-Guided Image Synthesis," in IEEE Xplore, Taiwan, C. o. A. I. Pervasive AI Research Labs, National Yang Ming Chiao Tung University, Ed., 2023.
[10] P. Foltýnek, M. Babiuch, and P. Šuránek, "Measurement and data processing from Internet of Things modules by dual-core application using ESP32 board," Measurement and Control, vol. 52, no. 7-8, pp. 970-984, 2019.
[11] R. Salikhov, V. K. Abdrakhmanov, and T. Yumalin, "Experience of using bluetooth low energy to develop a sensor data exchange system based on the nrf52832 microcontroller," in 2021 International Ural Conference on Electrical Power Engineering (UralCon), 2021: IEEE, pp. 229-233.
[12] MLX90640 32x24 IR Array Datasheet: Melexis INC., 2019.
[13] B. Mishra and A. Kertesz, "The use of MQTT in M2M and IoT systems: A survey," Ieee Access, vol. 8, pp. 201071-201086, 2020.
[14] G. Spasov, V. Tsvetkov, and G. Petrova, "Using IR array MLX90640 to build an IoT solution for ALL and security smart systems," in 2019 IEEE XXVIII International Scientific Conference Electronics (ET), 2019: IEEE, pp. 1-4.
[15] V. J. Neha Sharma, Anju Mishra, "An Analysis Of Convolutional Neural Networks For Image Classification," Procedia Computer Science, no. 132, pp. 377-384, 2018.
[16] J. W.Kalat, Biological psychology (13e). Cengage Learning, 2019.
[17] V. Verdhan, Computer Vision Using Deep Learning: Neural Network Architectures with Python and Keras. Limerick, Ireland: Apress, 2021.
[18] R. Zaheer and H. Shaziya, "A study of the optimization algorithms in deep learning," in 2019 third international conference on inventive systems and control (ICISC), 2019: IEEE, pp. 536-539.
[19] A. Gulli and S. Pal, Deep learning with Keras. Packt Publishing Ltd, 2017.
[20] N. K. Manaswi and N. K. Manaswi, "Understanding and working with Keras," Deep learning with applications using Python: Chatbots and face, object, and speech recognition with TensorFlow and Keras, pp. 31-43, 2018.
[21] K. M. Ting. (2018) “Confusion matrix,” Encyclopedia of Machine Learning and Data Mining, Springer.
[22] M. Heydarian, T. E. Doyle, and R. Samavi, "MLCM: Multi-label confusion matrix," IEEE Access, vol. 10, pp. 19083-19095, 2022.
[23] L. Jian-Wei, Z. Hui-Dan, L. Xiong-Lin, and X. Jun, "Research progress on batch normalization of deep learning and its related algorithms," Acta Automatica Sinica, vol. 46, no. 6, pp. 1090-1120, 2020.
[24] M. Mahsereci, L. Balles, C. Lassner, and P. Hennig, "Early stopping without a validation set," arXiv preprint arXiv:1703.09580, 2017.

指導教授

羅孟宗

審核日期

2024-7-16

推文