醫療科技的進步為早期的疾病偵測提供了更多元的方法,但生理訊號
的複雜性和對專業領域的依賴性也讓實際偵測上碰到許多困難。為了找出一個自動化且能正確判斷心律不整的方式,本篇論文提出了一個結合
Hilbert-Huang Transform 以及 Convolutional Neural Networks 的心電圖判別架構。透過 Hilbert-Huang Transform 來處理複雜且非平穩的生理訊號並轉換出 Hilbert Spectrum,再使用 Hilbert Spectrum 以訓練 Convolutional Neural Networks Model 來學習其特徵並判別心律不整的類別。最後透過實驗結果以驗證透過機器學習取代傳統由專家判別特徵的可行性及效率,同時分析所提出架構的準確度並加以探討。

In this thesis, a novel approach to arrhythmia-based signal classification is introduced. The objective is to properly identify three classes of patients exhibiting normal sinus rhythm, atrial fibrillation, and other rhythm. The proposed method apply Hilbert-Huang transform on raw signal to generate noise-free reconstruction of the original containing temporal variations as input for classification mechanism to learn representative features. The features are directly learned by a computer vision technique known as Convolutional Neural Network, thus replacing traditional methods of relying on experts to handcraft features. To summarize, this thesis contains two major processes: utilize a nonlinear and non-stationary signal processing technique to produce input, and to feed reconstructed signal containing representative features to CNN for multi-classification task. The experimental results indicate the effectiveness of this method, removing the need of human involvement in the process of feature selection. Through analyses and stimulations, the effectiveness of the proposed ECG-classification method is evaluated.

References

[1] H. Assodiky, I. Syarif, and T. Badriyah. Arrhythmia classification using long short-term memory with adapative learning rate. EMITTER International Journal of Engineering Technology, 2018.

[2] V. Fuster. Acc/aha/esc 2006 guidelines for the management of patients with atrial fibrillation: a report of the american college of cardiology/american heart association task force on pratice guidelines and the european society of cariology committee for practice guidelines (writing commitee to revise the 2001 guidelines for the management of patients with atrial fibrillation): developed in collaboration with
the european heart rhythm association and the heart rhythm society. Circulation - AHA/ASA Journals, 114(7):e257–354, 2006.

[3] N. E. Huang, Z. Shen, S. R. Long, M. C. Wu, H. J. Shin, Q. Zheng, N.C. Yen, C. C. Tung, and H. H. Liu. The empirical mode decomposition and the hilbert spectrum for nonlinear and non-stationary time series analysis. Proceedings of The Royal Society A Mathematical Physical
and Engineering Sciences, 1998.

[4] A. Isin and S. Ozadlili. Cardiac arrhythmia detection using deep learning. In 9th International Conference on Theory and Application of Soft Computing, Computing with Words and Perception, 2017.

[5] Y. LeCun, P. Haffner, and L. B. andYoshua Benegio. Object recognition with gradient-based learning. Shape, Contour and Grouping in Computer Vision, 1998.

[6] M.-Y. Li. A mobile application of analyzing heart rate variability and
detecting arrhythmia with wearable device in smart phones. Master’s thesis, National Central University, 2015.

[7] MonikaRani, Ekta, and R. Devi. Arrhythmia discrimination using support vector machine. In International Conference on Signal Processing, Computing and Control, 2017.

[8] PhysioNet. Af classification from a short single lead ecg recording: the physionet/computing in cardiology challenge 2017.

[9] B. Pourbabaee, M. J. Roshtkhari, and K. Khorasani. Feature leaning with deep convolutional neural netowrks for screening patients with paroxysmal atrial fibrillation. In International Joint Conference on Neural Networks, 2016.

[10] P. Rajpurkar, A. Y. Hannun, M. Haghpanahi, C. Bourn, and A. Y. Ng. Cardiologist-level arrhythmia detection with convolutional neural netowrks. Stanford Machine Learning Group, 2017.

[11] P. Shimpi, S. Shah, M. Shroff, and Godbole. A machine learning approach for the classification of cardiac arrhythmia. In International Conference on Computing Methogologies and Communication, 2017.

[12] X. Zhou, X. Zhu, K. Nakamura, and M. Noro. Atrial fibrillation detection using convolutional neural networks. In International Conference on Awareness Science and Technology, 2018.