Resumo

RAIRAN ANTOLINES, José Danilo. Reconstruction of periodic signals using neural networks. Tecnura [online]. 2014, vol.18, n.39, pp.34-46. ISSN 0123-921X.

Abstract In this paper, we reconstruct a periodic signal by using two neural networks. The first network is trained to approximate the period of a signal, and the second network estimates the corresponding coefficients of the signal's Fourier expansion. The reconstruction strategy consists in minimizing the mean-square error via backpropagation algorithms over a single neuron with a sine transfer function. Additionally, this paper presents mathematical proof about the quality of the approximation as well as a first modification of the algorithm, which requires less data to reach the same estimation; thus making the algorithm suitable for real-time implementations.

Palavras-chave : backpropagation; frequency measurement; Fourier series; harmonic analysis.

        · resumo em Espanhol     · texto em Inglês     · Inglês ( pdf )