Cardiovascular diseases (CVD) are the most chronic and dangerous diseases in worldwide. The early prediction of CVD can help to prevent deaths due to these diseases, using bio-medical signal analysis. In this field, the ECG signal plays an important role due to its significant nature of providing the health-related information. However, the signal acquisition process is a crucial step where signals get corrupted due to electrode movement, muscle movement and other types of interference which can degrade the performance of the signal analysis. Several approaches have been introduced but achieving the desired performance robustly is still considered as a challenging task. This paper presents a novel approach for ECG signal filtering by combining a combination of the extended Kalman filter, wavelet transform and an adaptive thresholding approach called as Linearized Kalman Filter aided Wavelet transform with Adaptive Thresholding (LKFWAT). In this process, the initial states of the signal are observed using a Kalman filter, later; a linearization scheme is presented to represent the signal in the linear form. Finally, an adaptive threshold method is applied to reduce the noise during signal construction. It will show the significant improvement in next level process of disease classification. A comparative experimental analysis is carried out which shows that the proposed approach achieves improved performance when compared with the state-of-art ECG denoising techniques.
Selective Feature Coding for Cardiac Arrhythmia Detection through ECG Signal Analysis
