Denoising of Heart Sounds Using Transform Domain Adaptive Line Enhancer

Heart sound analysis plays a crucial role in diagnosing cardiovascular diseases. However, accurate interpretation is often hindered by the presence of various types of noise in recorded heart sounds. This paper presents a novel approach for denoising heart sounds by utilizing a transform domain adaptive line enhancer (TDALE). The proposed method combines the Hadamard Transform with the Normalized Least Mean Squares (NLMS) algorithm to create an adaptive filter. Experimental evaluation was conducted on a dataset of recorded heart sounds contaminated with different types of noise. The results demonstrate that the TDALE-based approach effectively reduces noise while preserving the diagnostic information contained within the heart sounds. Comparative analysis with existing denoising techniques showcases the superiority of the proposed method in terms of denoising performance and preservation of important cardiac features.