EXPLORE PUBLICATIONS BY COUNTRIES

ECG, Wavelet Transform, Principle Component Analysis, Arrhythmia Detection.

The detection of abnormal cardiac rhythms, automatic discrimination from rhythmic heart activity, became a thrust area in clinical research. Arrhythmia detection is possible by analyzing the electrocardiogram (ECG) signal features. The presence of interference signals, like power line interference (PLI), Electromyogram (EMG) and baseline drift interferences, could cause serious problems during the recording of ECG signals. Many a time, they pose problem in modern control and signal processing applications by being narrow in-band interference near the frequencies carrying crucial information. This paper presents an approach for ECG signal enhancement by combining the attractive properties of principal component analysis (PCA) and wavelets, resulting in multi-scale PCA. In Multi-Scale Principal Component Analysis (MSPCA), the PCA’s ability to decorrelate the variables by extracting a linear relationship and wavelet analysis are utilized. MSPCA method effectively processed the noisy ECG signal and enhanced signal features are used for clear identification of arrhythmias. In MSPCA, the principal components of the wavelet coefficients of the ECG data at each scale are computed first and are then combined at relevant scales. Statistical measures computed in terms of root mean square deviation (RMSD), root mean square error (RMSE), root mean square variation (RMSV) and improvement in signal to noise ratio (SNRI) revealed that the Daubechies based MSPCA outperformed the basic wavelet based processing for ECG signal enhancement. With enhanced signal features obtained after MSPCA processing, the detectable measures, QRS duration and R-R interval are evaluated. By using the rule base technique, projecting the detectable measures on a two dimensional area, various arrhythmias are detected depending upon the beat falling into particular place of the two dimensional area.