Classification of FHSS Signals in a Multi-Signal Environment by Artificial Neural Network

Abstract

Frequency-hopping spread spectrum (FHSS) spreads the signal over a wide bandwidth where the carrier frequencies change rapidly according to a pseudorandom number making signal classification difficult. Classification becomes more complex with the presence of additive white Gaussian noise (AWGN) and interference due to background signals. In this paper, an artificial neural network (ANN) based classification system is proposed for FHSS signals in the presence of AWGN and background signal. The probability of correct classification (PCC) of the FHSS signals is performed by the linear discriminant (LD) and ANN. Based on the signal-to-noise ratio (SNR) range at 0.9 PCC, the performance of the LD and ANN respectively is 5.1 dB and 2.5 dB in the presence of AWGN only whereas their performance is 14 dB and 2.3 dB when the background signal is present. Resultantly, the ANN-based system outperformed the LD method by 2.6 to 11.7 dB of SNR.