Digital Modulation Classification Using Wavelet Transform and Artificial Neural Network

Abstract

Received signals contain a vast amount of uncertainty due to the unknown modulating signals, communication channel, and noise. Therefore the modulation classification problem has to be approached based on artificial neural networks . In this work a digital modulation classification method is presented, based on discrete wavelet transform (DWT) and artificial neural networks (ANN) to distinguish digital modulation, like quadrature amplitude (QAM), phase shift keying (PSK), and frequency shift keying (FSK) signals. Feature extraction is performed via the DWT detail coefficients of the digital signals using (db4) mother wavelet, because of the usefulness of wavelet in signal de-noising . The extracted features are presented to an ANN for pattern recognition. In this work Levenberg- Marquardt error back propagation algorithm is used since it appears to be the fastest method for training moderate-sized feed forward neural networks (up to several hundred weights).The performance of the classification scheme is investigated through simulations using matlab-7, high recognition rates are obtained of about (97%). However, there are probabilities of misclassification of about (3%).