本論文提出一個基於偵測異常心跳的機器學習演算法及整體演算法的硬體設計。心電圖(Electrocardiogram, ECG)是於臨床中時常被用來檢測心血管疾病，例如心房早期收縮(APC,Atrial Premature Contraction)及心室早期收縮(PVC,Premature Ventricular Contraction)。透過心電圖的量測，可以得知心臟的狀態，並配合即時辨識演算法，辨識出異常心跳的種類。
本論文提出的偵測異常心跳的機器學習演算法包含了四個部分：特徵值擷取、特徵值標準化(normalize)、主成分分析(Principal Component Analysis)以及類神經網路，可將接收到的心電圖即時進行辯識並將結果輸出，並可長時間進行監控。
本論文的辨識演算法流程為心電圖訊號採集、心電圖訊號預處理、特徵值提取(Feature extraction)、特徵值標準化(normalize)、主成分分析(Principal Component Analysis)、類神經網路(Neural network)分類器，先將收集到的心電圖進行濾波後，經由特徵提取得到所需特徵值，再將特徵值標準化，接著用主成分分析降低特徵值數量，然後給予類神經網路特徵值進行分類，最終輸出辨識結果。訊號取樣頻率為400Hz，演算法採用每300點(約0.75秒)進行辨識。特徵萃取採用心跳間距、變異數、最小值位置以及最大值位置等數值作為特徵。由於每個個體間的心電圖略有差異，因此採用較合理方式分割訓練資料集以及測試資料集，並使用具學習能力的類神經網路架構進行分類，可使演算法更適用於不同個體，以提升精準度。
本論文將演算法於硬體與軟體上分別實現，在軟體的準確率可達95.45%，硬體準確率亦為95.45%，因此證實提出的架構確實能實現於硬體並進行心電圖的即時辨識。

This paper presents a real-time identification system for electrocardiogram (ECG) classification with the neural network (NN) classifier. The identification flow of the proposed system is described as following step by step: 1. Collecting ECG lead II signal. 2. Filtering original signals by wavelet transform. 3. Calculating twenty feature values and normalizing these features. 4. Using principal component analysis (PCA) to reduce feature number. 5. Classifying the normal beat, premature atrial complex (PAC) and premature ventricular contraction (PVC) by classifier. The accuracy of the proposed method are evaluated using different normal and abnormal ECG signals taken from the standard MIT-BIH arrhythmia database. The proposed system is verified on software design. The software part is designed by python and tested by Matlab, and the hardware is implemented by the chip fabricated with TSMC 0.18um CMOS technology. All machine learning process, including preprocessing, feature extraction, and classifier, is implemented by a chip. The train data and test data are independent from each other. In other words, the person included in train data set never appears in test data set. The accuracy of the proposed system is about 95.45% by the verification on the software. It reveals the proposed architecture is effective for ECG classification.

參考文獻
[1] World Health Organization, “The top 10 causes of death” May 2018 [online]. Available:https://www.who.int/news-room/fact-sheets/detail/the-top-10-causes-of-death , Accessed on Sep. 1, 2019.
[2] Ministry of health and welfare, “107年死因統計結果分析” June 2018 [online]. Available: https://dep.mohw.gov.tw/DOS/cp-4472-48034-113.html , Accessed on Sep. 1, 2019].
[3] A. Haar, “Zur Theorie der orthogonalen Funktionensysteme,” Mathematische Annalen, vol. 69, pp. 331-371, 1910.
[4] A. Gonz, I. A. lez, M. cana, X. Otazu, O. Fors, and A. Seco, “Comparison between Mallat's and the `a trous' discrete wavelet transform based algorithms for the fusion of multispectral and panchromatic images,” Int. J. of Remote Sensing, vol. 26, pp. 595-614, 2005.
[5] H. Li, D. Yuan, X. Ma, “Genetic algorithm for the optimization of features and neural networks in ECG signals classification” Sci. Rep-Uk, 7 (2017), p. 41011.
[6] P. N. Whatmough, S. K. Lee, D. Brooks, G.-Y. Wei, "DNN engine: A 28-nm timing-error tolerant sparse deep neural network processor for IoT applications", IEEE J. Solid State Circuits, vol. 53, no. 9, pp. 2722-2731, Sep. 2018.
[7] C. C. Lin and C. M. Yang, "Heartbeat Classification Using Normalized RR Intervals and Wavelet Features," 2014 International Symposium on Computer, Consumer and Control, Taichung, 2014, pp. 650-653.
[8] T. Yingthawornsuk, "Classification of ECG Signals Using Modified Hjorth Descriptors," 2018 14th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS), Las Palmas de Gran Canaria, Spain, 2018, pp. 345-350.
[9] M. Kallas, C. Francis, L. Kanaan, D. Merheb, P. Honeine and H. Amoud, "Multi-class SVM classification combined with kernel PCA feature extraction of ECG signals," 2012 19th International Conference on Telecommunications (ICT), Jounieh, 2012, pp. 1-5.
[10] S. Faziludeen and P. V. Sabiq, "ECG beat classification using wavelets and SVM," 2013 IEEE Conference on Information & Communication Technologies, Thuckalay, Tamil Nadu, India, 2013, pp. 815-818. .