Noise Removal-based Thresholding framework for Arrhythmia classification

Abstract

Electrocardiogram (ECG) signal analyses can enhance human life in various ways, from detecting and treating heart illness to controlling the lives of cardiac-diseased people. ECG analysis has become crucial in medical studies for accurately detecting cardiovascular diseases (CVDs). Cardiac Arrhythmia is one of the major life-threatening diseases. Analyzing ECG signals is the easiest way to detect Arrhythmia. Different noises often corrupt the ECG signals, like power line interference, electromyographic (EMG) noise, and electrode motion artifact noise. Such noises make it difficult to identify the various peaks in the ECG signal for arrhythmia classification. To overcome such problems, Noise Removal-based Thresholding (NRT) framework has been introduced to remove noises from ECG signals and accurately classify Arrhythmia. Discrete Wavelet transform reduces noise from ECG signals in the pre-processing stage. The noise-removed signal is segmented by K-means clustering for R-peak detection by finding all local maximum points from the signal. The signal features are extracted by Burg’s method to obtain good frequency resolution and quick integration for short-time signals in the form of a cumulative distribution function. All features collected from R-peak are fed to the Iterative Convolutional Neural Network (ICNN) and classified the arrhythmia types based on the alignment of a few variables to work well with the Euclidean distance metric. The NRT framework is evaluated based on the data obtained from the MIT-BIH Arrhythmia dataset and achieves the Accuracy of 99.45 %, Positive Prediction of 98.92%, F1-Score of 98.95%, SNR of 35 dB, MSE of 0.001, RMSE of 0.002