Soft-information flipper based on long-short term memory networks for ultra-high density magnetic recording

Abstract

Currently, researchers have been developing new ultra-high density magnetic recording technologies to meet the exponential growth of data storage demand. One of the main prospective technologies is bit-patterned media recording (BPMR) technology which is expected to upgrade the areal density (AD) up to 4.0 Terabit per square inch (Tb/in2). To achieve the expected high AD, the distance between each magnetic island in BPMR medium must; however, be reduced significantly, and it will enhance the two-dimensional (2-D) interference, namely inter-symbol interference (ISI) and inter-track interference (ITI). These two effects need to be probably handled to maintain overall system performance. Therefore, we propose a soft-information flipper based on long-short term memory (LSTM) networks combined with the rate-5/6 2-D modulation code in the coded three-track/three-head BPMR systems. In the proposed system, three soft-information sequences produced by the multiple 2-D soft-output Viterbi algorithms are employed as LSTM network inputs to generate the coded data sequences. During the supervised learning process, the known values of the coded data sequences are used as the targets at the output stage of LSTM network. The simulation results indicate that, at the same user density of 2.5 Tb/in2, the proposed system can provide bit-error-rate performance over both the soft-information flipping scheme based on a priori log-likelihood ratios summation and conventional uncoded systems. Moreover, the results also reveal that the proposed system is more robust to the media noise compared to other systems.