簡易檢索 / 詳目顯示

回結果列表
研究生： 黃明志
Huang, Ming-Chih
論文名稱： 使用光體積變化描記圖偵測飢餓狀態
Using Photoplethysmography for Hunger Detection
指導教授： 侯廷偉
Hou, Ting-Wei
學位類別： 碩士
Master
系所名稱： 工學院 - 工程科學系碩士在職專班
Department of Engineering Science (on the job class)
論文出版年： 2020
畢業學年度： 108
語文別： 中文
論文頁數： 45
中文關鍵詞： 飢餓 、光體積變化描記圖 、心脈 、人工智慧
外文關鍵詞： Hungry, Photoplethysmography, Heart pulse, AI
相關次數： 點閱：219  下載：0 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 本研究試圖提出一套方法，使用光體積變化描記圖元件之穿戴式硬體，以非侵入式的量測方式，搭配資料分析及人工智慧，判斷佩戴此裝置的使用者，處於飯前或飯後的狀態。

    本研究第一階段先取得十位使用者在飯前與飯後的量測資料。第二階段則提出二種演算法，用以分析飯前與飯後訊號的特性，並加以判斷狀態。第一種演算法使用資料分析方法進行比較，第二種演算法使用人工智慧學習，並提出一種創新的資料疊置圖形模式，將資料疊置後的圖形，導入人工智慧學習。第三階段則使用本研究所述的裝置，經過十位受測者實驗，在使用第一種一般資料方法進行辨識時，辨識率最低達59.32%，在使用第二種演算法，輔以人工智慧訓練後，辨識率可達90.83% 以上。

    This research proposes an approach, using wearable non-invasive hardware with photoplethysmography (PPG) component, combined with data analysis and artificial intelligence, to determine whether the user is in a pre-meal (hungry) or post-meal state.

    In the first stage of this research, ten volunteers’ pre-meal and post-meal signals were recorded using the device. In the second stage, two algorithms are proposed to analyze the signals to determine their states. The first algorithm uses data analysis methods, and the second algorithm uses artificial intelligence. An innovative overlay method is proposed. This method cuts and overlaps a fixed period of signal waveforms. The first data analysis method has a recognition rate as low as 59.32%. The second method, using artificial intelligence for identification, has a recognition rate of more than 90.83%.

    摘要............................I Extended Abstract...............II 致謝............................X 目錄............................XI 表目錄..........................XIII 圖目錄..........................XIV 第一章 緒論.....................1 1.1 研究動機....................1 1.2 研究目的....................2 1.3 章節提要....................3 第二章 相關研究與文獻探討.......4 2.1 量測方式的選用..............4 2.2 相關應用的探討..............8 2.3 裝置規格的探討..............9 第三章 裝置實作與方法設計.......11 3.1 硬體平台....................11 3.1.1 平台架構..................11 3.1.2 感測器模組................11 3.1.3 微控制器模組..............13 3.1.4 裝置製作..................13 3.2 軟體平台....................15 3.2.1 雜訊濾除..................15 3.2.2 資料擷取..................16 3.2.3 格式設計..................17 3.3 人工智慧....................19 第四章 實驗與結果...............20 4.1 實驗人員與測試條件..........20 4.2 一般資料判斷法..............21 4.2.1 頻率判斷法................21 4.2.2 波幅判斷法................24 4.2.3 一般資料判斷法小結........26 4.3 人工智慧判斷法..............27 4.3.1 訓練平台及參數............27 4.3.2 單脈波與雙脈波............28 4.3.3 單人與多人................30 4.3.4 疊置圖檔產生方法..........32 4.3.5 單層圖檔與多層圖檔........33 4.3.6 人工智慧辨識結果..........35 4.4 實驗結果討論................36 4.4.1 人工智慧辨識率不佳........36 4.4.2 實驗過程遭遇的問題........38 第五章 結論與未來展望...........40 5.1 結論........................40 5.2 未來展望....................41 參考文獻........................42 附錄一、多層疊置單雙脈波辨識率比較表....44

    [1] Z. Zhang, "Photoplethysmography-Based Heart Rate Monitoring in Physical Activities via Joint Sparse Spectrum Reconstruction," IEEE Transactions on Biomedical Engineering, vol. 62, no. 8, pp. 1902-1910, Aug. 2015.
    [2] S. C. Huang, P. H. Hung, C. H. Hong, H. M. Wang, "A New Image Blood Pressure Sensor Based on PPG, RRT, BPTT, and Harmonic Balancing," IEEE Sensors Journal, vol. 14, no. 10, pp. 3685-3692, Oct. 2014.
    [3] C. T. Chu, H. K. Chiang, J. J. Hung, "Dynamic Heart Rate Monitors Algorithm for Reflection Green Light Wearable Device," in Signal Processing, Computer Networks and Telecommunications, pp.438-445, Okinawa, Japan, 2015.
    [4] E. Abe, H. Chigira, K. Fujiwarai, T. Yamakawa, M. Kano, "Heart Rate Monitoring by A Pulse Sensor Embedded Game Controller," in Asia-Pacific Signal and Information Processing Association, pp.1266-1269, Hong Kong, 2015.
    [5] M. I. Friedman, E. M. Stricker, "The Physiological Psychology of Hunger : A Physiological Perspective," Psychological Review, vol. 83, no. 6, pp. 409-431, 1976.
    [6] S. Nicolaidis, P. Even, "Physiological determinant of hunger, satiation, and satiety," The American Journal of Clinical Nutrition, vol. 42, pp. 1083-1092, 1985.
    [7] J. Allen, "Photoplethysmography and its application in clinical physiological measurement," Physiological Measurement, vol. 28, pp. 1-39, 2007.
    [8] J. W. Kang, Y. S. Park, H. Chang, W. Lee, S. P. Singh, W. Choi, L. H. Galindo, R. R. Dasari, S. H. Nam, J. Park, P. T. C. So, "Direct observation of glucose fingerprint using in vivo Raman spectroscopy," Science Advances, vol. 6, no. 4, eaay5206, 4 Jan. 2020.
    [9] C. Y. Li, Y. C. Chen, W. J. Chen, P. Huang, H. H. Chu, "Sensor -Embedded Teeth for Oral Activity Recognition," in International Symposium on Wearable Computers, pp.41-44, Zurich, Switzerland, 2013.
    [10] A. Choi, H. Shin, "Photoplethysmography sampling frequency: pilot assessment of how low can we go to analyze pulse rate variability with reliability?," Physiological Measurement, vol. 38, no. 3, pp. 586-600, 2017. (DOI: 10.1088/1361-6579/aa5efa)
    [11] S. Mahdiani, V. Jeyhani, M. Peltokangas, A. Vehkaoja, "Is 50 Hz high enough ECG sampling frequency for accurate HRV analysis?," 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 5948-5951, 2015.
    [12] D. Fujita, A. Suzuki, "Evaluation of the Possible Use of PPG Waveform Features Measured at Low Sampling Rate," IEEE Access, vol. 7, pp. 58361-58367, May 2019.
    [13] Wikipedia, "Heart rate," [Online]. Available: https://en.wikipedia.org/wiki/Heart_rate. [Accessed : Feb. 15 2020].
    [14] J. Murphy, Y. Gitman, "PulseSensor Open Hardware Project," [Online]. Available: https://pulsesensor.com/pages/open-hardware. [Accessed : Feb. 28 2020].
    [15] Broadcom, "APDS-9005," [Online]. Available: https://docs.broadcom.com/doc/AV02-0080EN. [Accessed : Feb. 28 2020].
    [16] J. Murphy, Y. Gitman, "PulseSensor Datasheet," [Online]. Available: https://cdn.shopify.com/s/files/1/0100/6632/files/Pulse_Sensor_Data_Sheet.pdf. [Accessed : Feb. 28 2020].
    [17] Arduino, "Arduino Nano," [Online]. Available: https://store.arduino.cc/usa/arduino-nano. [Accessed : Feb. 15 2020].
    [18] Microchip, "ATmega328p," [Online]. Available: http://ww1.microchip.com/downloads/en/DeviceDoc/Atmel-7810-Automotive-Microcontrollers-ATmega328P_Datasheet.pdf. [Accessed : Feb. 15 2020].
    [19] FTDIchip, "FT232R," [Online]. Available: https://www.ftdichip.com/Support/Documents/DataSheets/ICs/DS_FT232R.pdf. [Accessed : Mar. 7 2020].
    [20] 陳坤明, "電子元件的雜訊從何而來, 國家奈米元件實驗室," 2016. [Online]. Available: http://www.ndl.org.tw/docs/publication/23_4/pdf/E3.pdf. [Accessed : Jan. 23 2020].
    [21] Wikipedia, "RS-232," [Online]. Available: https://zh.wikipedia.org/wiki/RS-232. [Accessed : Feb. 22 2020].
    [22] TensorFlow, "Convolutional Neural Network (CNN)," [Online]. Available: https://www.tensorflow.org/tutorials/images/cnn. [Accessed : Mar. 5 2020].
    [23] C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, Z. Wojna, "Rethinking the Inception Architecture for Computer Vision," [Online]. Available: https://arxiv.org/abs/1512.00567. [Accessed : May. 9 2020].
    [24] Microchip, "MCP6001," [Online]. Available: http://ww1.microchip.com/downloads/en/DeviceDoc/MCP6001-1R-1U-2-4-1-MHz-Low-Power-Op-Amp-DS20001733L.pdf. [Accessed : Mar. 1 2020].

    無法下載圖示 校內：2025-08-08公開
    校外：不公開
    電子論文尚未授權公開，紙本請查館藏目錄
    QR CODE