A Study on Neural Network Detector in SMR System

We have previously proposed the waveform equalization using a two-dimensional finite impulse response (TD-FIR) filter and the inter-track interference (ITI) canceller as a signal processing method for shingled magnetic recording (SMR) system. In this study, we propose a neural network detector (NND) to automate the iterative decoding in the future and evaluate the performance of the NND in SMR system. The result shows that our proposed NND shows almost the same performances as a combined system with TD-FIR filter and soft-output Viterbi algorithm (SOVA) detector with signal-dependent noise predictor.