Neural network applications for jamming state information generator

Abstract

A known jamming state information (JSI) scheme for a coded frequency-hopped M-ary frequency-shift-keying (FH/MFSK) system under partial-band noise jamming, plus additive white Gaussian noise, utilizes the maximum a posteriori (MAP) rule based on the total energy received in the M-tone signaling bands. It is assumed that the knowledge of partial-band noise jamming fraction is available to the JSI generator. Because this scheme reduces the M-dimensional information into one dimension, i.e., the total energy, the generated JSI may not be the best. In this paper, a neural network approach to the JSI generation is presented. The efficiency of the new JSI generator with known partial-band noise jamming fraction is compared with the MAP generator. The neural network scheme is then generalized to increase its robustness by allowing for an unknown partial-band noise jamming fraction. The neural network JSI generator with or even without knowledge of jamming fraction offers significantly better performance for a coded FH/MFSK communication system than the MAP JSI generator for high code rate.