R&D: Optimization of 2D Generalized Partial Response Target Using Multi-Layer Perceptron for Bit-Patterned Media Recording Systems

AIP Advances has published an article written by Thien An Nguyen and Jaejin Lee, Department of Information Communication Convergence Technology, Soongsil University, Seoul 06978, South Korea.

Abstract: “In magnetic storage systems, the read signal that is the output of the magnetic recording channel is passed through the equalizer to convert it into the desired partial response (PR) target signal. However, mapping between the output of the recording channel and the PR target signal is a non-linear problem. Therefore, many multilayer perceptron (MLP) equalizers have been proposed. In this paper, we propose an optimization scheme of two-dimensional generalized PR target using MLP for improving the detection performance of the bit-patterned magnetic recording (BPMR) systems. The simulation results show that the proposed scheme outperforms the previous methods.“