A comparative analysis of LMS and NLMS algorithms for adaptive filtration of compressed ECG signal

This paper presents an adaptive filtration approach for electrocardiographic (ECG) signal processing. In this paper Adaptive filter is used to eliminate the noise in electrocardiographic (ECG) signal. For adaptive filtering approach, Least Mean Square (LMS) and Normalised Least Mean Square (NLMS) algorithms are used. NLMS algorithm is well suited for this application because it optimizes the speed of convergence. A comparative analysis of both algorithms is done in this paper. In addition, since ECG signals typically are very large and need to be stored for analysis and retrieval at a future time, incorporation of Walsh Hadamard transforms (WHT) provide compression and thus require less storage space for the implementation of algorithms and they also provide rapid signal reconstruction.