臺灣博碩士論文加值系統

根據從衛生福利部網站刊登的統計數據得知，心臟疾病在近幾年仍然是導致我國人民死亡的其中一項主要原因，並且因其而死亡的人數依舊是逐年增長，對此我們需要有所應對。本研究提出一種針對心電圖辨識的輕量型的卷積神經網路模型，並實現在微控制器上的應用，可在現實應用中協助迅速且精確地進行心臟疾病的辨識，有望在改善心臟疾病預防和監測方面發揮重要作用。
在本論文之研究中，我們設計並建構了一個基於深度可分離卷積技術的高效輕量型卷積神經網路模型，用以實現在資源有限的微控制器上進行心臟疾病辨識。該模型在測試過程中以參數量為5206與運算量為179630得情況下達到98.49%的準確率，並且能順利至以微控制器為核心的嵌入式系統上運作，耗能僅為 2.4mJ，雖然準確度無法達到完美100%準確，但同時具有低複雜度、低耗能與高效能，使其適合在資源受限的環境中應用。

According to statistical data published on the website of the Ministry of Health and Welfare, heart disease continues to be one of the leading causes of death in our country in recent years. The number of deaths due to heart disease is increasing year by year. In response to this, it is necessary to take measures. This study proposes a lightweight convolutional neural network model for electrocardiogram (ECG) recognition. The model is designed to be implemented on microcontrollers, enabling rapid and accurate identification of heart disease in real-world applications. It is expected to play a crucial role in improving the prevention and monitoring of heart diseases.
In this research, we have designed and constructed an efficient lightweight convolutional neural network model based on depthwise separable convolution techniques. This model is intended for heart disease recognition on microcontrollers with limited resources. During testing, the model achieved an accuracy of 98.49% with 5206 parameters and 179630 computations. It can successfully operate on embedded systems with microcontrollers as the core, consuming only 2.4mJ of energy. While the accuracy may not reach a perfect 100%, the model boasts low complexity, low energy consumption, and high efficiency, making it suitable for application in resource-constrained environments.

摘要...i
Abstract...ii
誌謝...iii
目錄...iv
表目錄...v
圖目錄...vi
第一章 緒論...1
1.1 前言...1
1.2 研究背景...3
1.2.1 心電圖概論...3
1.2.2 MIT-BIH數據庫介紹...5
1.2.3 卷積神經網路介紹...10
第二章 文獻探討...14
2.1 一般ECG研究...14
2.2 穿戴式ECG研究...18
第三章 研究方法...29
3.1 系統軟體及硬體介紹...30
3.2 數據集資料建構...31
3.3 深度可分離卷積...33
3.4 神經網路模型的建構與比較...35
第四章 系統成果與比較...38
4.1 系統實驗方法...38
4.2 系統成果...39
4.3 成果比較...42
第五章 結論...43
參考文獻...44
Extended Abstract...47

[1]邱艶芬，2014，簡易心電圖讀本，臺灣：華杏出版股份有限公司，5月。
[2]Y. Lecun, L. Bottou, Y. Bengio and P. Haffner, "Gradient-based learning applied to document recognition," Proceedings of the IEEE., vol. 86, no. 11, pp. 2278-2324, Nov. 1998.
[3]X. Zhai and C. Tin, "Automated ECG Classification Using Dual Heartbeat Coupling Based on Convolutional Neural Network," IEEE Access., vol. 6, pp. 27465-27472, May. 2018.
[4]M. Salem, S. Taheri and J. Yuan, "ECG Arrhythmia Classification Using Transfer Learning from 2- Dimensional Deep CNN Features," 2018 IEEE Biomedical Circuits and Systems Conference (BioCAS), Cleveland, OH, USA, pp. 1-4, Oct. 2018.
[5]w. zhu, X. Chen, Y. Wang and L. Wang, "Arrhythmia Recognition and Classification Using ECG Morphology and Segment Feature Analysis," IEEE/ACM Transactions on Computational Biology and Bioinformatics, vol. 16, no. 1, pp. 131-138, Jan. 2019.
[6]B. Hou, J. Yang, P. Wang and R. Yan, "LSTM-Based Auto-Encoder Model for ECG Arrhythmias Classification," IEEE Transactions on Instrumentation and Measurement, vol. 69, no. 4, pp. 1232-1240, Apr. 2020.
[7]J. Huang, B. Chen, B. Yao and W. He, "ECG Arrhythmia Classification Using STFT-Based Spectrogram and Convolutional Neural Network," IEEE Access, vol. 7, pp. 92871-92880, Jul. 2019.
[8]S. Y. ŞEN and N. ÖZKURT, "ECG Arrhythmia Classification By Using Convolutional Neural Network And Spectrogram," 2019 Innovations in Intelligent Systems and Applications Conference (ASYU), Izmir, Turkey, pp. 1-6, Oct. 2019.
[9]U. Satija, B. Ramkumar and M. S. Manikandan, "A New Automated Signal Quality-Aware ECG Beat Classification Method for Unsupervised ECG Diagnosis Environments," IEEE Sensors Journal, vol. 19, no. 1, pp. 277-286, Jan. 2019.
[10]H. Yang and Z. Wei, "Arrhythmia Recognition and Classification Using Combined Parametric and Visual Pattern Features of ECG Morphology," IEEE Access, vol. 8, pp. 47103-47117, Mar. 2020.
[11]W. Qi and H. Su, "A Cybertwin Based Multimodal Network for ECG Patterns Monitoring Using Deep Learning," IEEE Transactions on Industrial Informatics, vol. 18, no. 10, pp. 6663-6670, Oct. 2022.
[12]T. Pokaprakarn, R. R. Kitzmiller, R. Moorman, D. E. Lake, A. K. Krishnamurthy and M. R. Kosorok, "Sequence to Sequence ECG Cardiac Rhythm Classification Using Convolutional Recurrent Neural Networks," IEEE Journal of Biomedical and Health Informatics, vol. 26, no. 2, pp. 572-580, Feb. 2022.
[13]N. Wang, J. Zhou, G. Dai, J. Huang and Y. Xie, "Energy-Efficient Intelligent ECG Monitoring for Wearable Devices," IEEE Transactions on Biomedical Circuits and Systems, vol. 13, no. 5, pp. 1112-1121, Oct. 2019.
[14]S. Saadatnejad, M. Oveisi and M. Hashemi, "LSTM-Based ECG Classification for Continuous Monitoring on Personal Wearable Devices," IEEE Journal of Biomedical and Health Informatics, vol. 24, no. 2, pp. 515-523, Feb. 2020.
[15]A. Rana and K. K. Kim, "A Lightweight DNN for ECG Image Classification," 2020 International SoC Design Conference (ISOCC), Yeosu, Korea (South), pp. 328-329, 2020.
[16]S. Kim, S. Chon, J. -K. Kim, J. Kim, Y. Gil and S. Jung, "Lightweight Convolutional Neural Network for Real-Time Arrhythmia Classification on Low-Power Wearable Electrocardiograph," 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Glasgow, Scotland, United Kingdom, pp. 1915-1918, 2022.
[17]B. Bengherbia, M. R. Aymene Berkani, Z. Achir, A. Tobbal, M. Rebiai and M. Maazouz, "Real-Time Smart System for ECG Monitoring Using a One-Dimensional Convolutional Neural Network," 2022 International Conference on Theoretical and Applied Computer Science and Engineering (ICTASCE), Ankara, Turkey, pp. 32-37, 2022.
[18]S. Ran ,X. Yang, M. Liu, C. Cheng, H. Zhu, Y. Yuan, "Homecare-Oriented ECG Diagnosis With Large-Scale Deep Neural Network for Continuous Monitoring on Embedded Devices," IEEE Transactions on Instrumentation and Measurement, vol. 71, pp. 1-13, no. 2503113, 2022.
[19]G. Sivapalan, K. K. Nundy, S. Dev, B. Cardiff and D. John, "ANNet: A Lightweight Neural Network for ECG Anomaly Detection in IoT Edge Sensors," IEEE Transactions on Biomedical Circuits and Systems, vol. 16, no. 1, pp. 24-35, Feb. 2022.
[20]Y. -L. Xie, X. -R. Lin and C. -W. Lin , "SEmbedNet: Hardware-Friendly CNN for Ectopic Beat Classification on STM32-Based Edge Device," 2022 IEEE International Conference on Recent Advances in Systems Science and Engineering (RASSE), Tainan, Taiwan, pp. 1-6, 2022.
[21]F. Jiang, Y. Li, C. Sun and C. Wang, "Lightweight Neural Networks for Automatic Classification of ECG Signals," 2022 14th International Conference on Wireless Communications and Signal Processing (WCSP), Nanjing, China, pp. 527-532, 2022.
[22]J. Xiao, J. Liu, H. Yang, Q. Liu, N. Wang, Z. Zhu, "ULECGNet: An Ultra-Lightweight End-to-End ECG Classification Neural Network," IEEE Journal of Biomedical and Health Informatics, vol. 26, no. 1, pp. 206-217, Jan. 2022.
[23]Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam, “MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications, ” arXiv preprintarXiv:1704.04861, Apr 2017.
[24]François Chollet, “Xception: Deep Learning with Depthwise Separable Convolutions,” arXiv preprint arXiv:1610.02357, Oct 2016.