João H. V. M. Melo, Renato Candido, Magno T. M. Silva Detecção de sopro cardíaco utilizando uma rede neural convolucional. Simpósio Brasileiro de Telecomunicações – SBrT’2026, 2026, Salvador, Anais do SBrT 2026, 2026, pp. 1–3. [pdf] (in portuguese)

Abstract

This work presents an automatic heart murmur detection system based on phonocardiogram signals using machine learning techniques. The proposed approach combines acoustic feature extraction with a convolutional neural network to classify normal and murmur heart sounds. The results indicate that the proposed methodology is a promising approach for computer-aided cardiac screening applications.

Keywords

Machine learning, heart murmur classification, convolutional neural network, phonocardiogram, mel-frequency cepstral coefficients.

Downloads

• PDF