Heart sound analysis using neural and statistical classifiers: a comparison

Abstract

The results of a classical pattern recognition approach to heart sound analysis are compared with those of a trained neural network classifier. Noise not correlated with the specific heart operation is reduced by use of adaptive digital online filtering. The results, indicating the advantages of learning neural classifiers, are regarded as being transferable to other applications.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>