Direct demodulator for amplitude modulated signals using artificial neural network

Abstract

This article, presents an Artificial Neural Network (ANN) based high speed demodulator, capable of demodulating amplitude modulated signals. The ANN is developed using Multilayer Perceptron (MLP) based Neural Network. We also introduce a pre-processing method for faster training of the ANN and a method training ANN using random modulating signal. Test results are presented for modulating signals such as triangular wave and square wave. We show that, the unique preprocessing technique introduced in this article enables us to achieve faster training of the ANN.