Detection and Classification of Baseline-Wander Noise in ECG Signals Using Discrete Wavelet Transform and Decision Tree Classifier

Abstract

An electrocardiogram (ECG) signal is usually contaminated with various noises, such as baseline-wander, power-line interference, and electromyogram (EMG) noise.Denoising must be performed to extract meaningful information from ECG signals for clinical detection of heart diseases. This work is focused on baseline-wander noise as it shares the same frequency spectrum as the ST segment of ECG signals. Hence, it is important to estimate the baseline-wander prior to its removal from ECG signals. This paper presents a method for classifying each segment of the ECG signal's baseline-wander as minimal, moderate or large. We use the C4.5 decision tree algorithm to model the classifier using the WEKA data-mining tool. We test the proposed method on ECG signals obtained from the MIT-BIH arrhythmia database (48 ECG recordings, each slightly longer than 30 min). We use 36 ECG recordings for training the classifier with the remaining 12 ECG recordings as the test data for classification. We partition each recording into 5 second, non-overlapping segments, which result in 361 segments for each record. The classification results show that the model classifier achieves an average sensitivity of 97.36 %, specificity of 99.50 %, and overall accuracy of 98.89 % in classifying the baseline-wander noise in ECG signals. The proposed method effectively addresses the question of identifying the minimal baselinewander segments. Moreover, the proposed framework may help in devising an algorithm for the selective filtering of moderate and large baseline-wander segments to achieve the best tradeoff between accuracy and computational cost.

Baseline Wander Correction of the Electrocardiogram Signals for Effective Preprocessing

“…Therefore, it is extremely important to assess the baseline deviation before it is removed from the ECG signal. A good estimate of baseline wander will prevent filtering of the ECG signal segments without a baseline, thereby ensuring the accuracy of the received signal [5]. The most commonly used method for removing baseline drift is a cubic spline algorithm that interpolates the baseline fit using selected data points on the original signal.…”

Deep Learning Framework with ECG Feature-Based Kernels for Heart Disease Classification

“…Difficulty lies in the fact that the ECG signals often have different types of noise, such as Baseline Wander (BW), Power Line Interference (PLI), and artifacts [3]- [5], which can affect the evaluation of diagnostic results. For this reason, many methods for improving the quality of the ECG signals have been proposed [6], [7].…”