Performance Improvement of PRML Channel with Jitter-like Media Noise

Abstract

An application of the neural network equalization to the PRML channel with jitter-like media noise is studied. First, a model of the read/write channel with jitter-like media noise and a neural network equalizer are described. Then, the bit-error rate of the 16/17(0, 6/6)coded EPR4ML and E^2PR4ML systems using a neural network equalizer is evaluated by computer simulation and the performance is compared with that of the conventional systems using a transversal filter. The results show that the neural network equalization can reduce the influenece of jiter-like media noise on the performance.