A Study on Iterative Decoding With LLR Modulator Using Neural Network in SMR System

Nishikawa, Madoka; Nakamura, Yūichi; Osawa, Hisashi; Okamoto, Yoshihiro; Kanai, Y.

doi:10.1109/tmag.2019.2891711

Cited by 11 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because the estimated TMR by the MLP-based TMR estimator helps the MLP-based data detector to detect the received signal, the proposed scheme exhibits a better bit error ratio (BER) performance than a conventional partial response maximum likelihood (PRML) detector. For a shingled magnetic recording system, a log-likelihood ratio (LLR) modulator based on an NN was developed to improve the reliability of the decoder output and recalculate the LLR value [11]. The LLR modulator, which was designed to be used in conjunction with a low-density parity check code, improves iterative decoding performance.…”

Section: Introductionmentioning

confidence: 99%

Soft-Output Detector Using Multi-Layer Perceptron for Bit-Patterned Media Recording

Jeong

Lee

2022

Applied Sciences

View full text Add to dashboard Cite

As conventional data storage systems are faced with critical problems such as the superparamagnetic limit, bit-patterned media recording (BPMR) has received significant attention as a promising next-generation magnetic data storage system. However, the reduced spacing between islands at increased areal density causes severe intersymbol and intertrack interference, which degrade BPMR system performance. In this study, we introduce a soft-output detector using multi-layer perceptron to predict reliable information. A received signal is equalized and detected by the MLP detector. The MLP detector provides a well-estimated value by using the binary-cross entropy function as a loss function and the identity function as an activation function for the output layer of the MLP detector. This study investigates the received probability distributions out of the detectors and compares the performance of various versions against a conventional detector. Compared with the conventional detection, the proposed MLP detectors provide a small variance and better BER performance than the conventional detection. Simulations of MLP designs show an advantage over conventional detection. Moreover, the proposed MLP detectors with the demodulator exhibit better BER performance than the conventional detector with the demodulator.

show abstract

Section: Introductionmentioning

confidence: 99%

Soft-Output Detector Using Multi-Layer Perceptron for Bit-Patterned Media Recording

Jeong

Lee

2022

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Several works have attained deep learning sufficient for feasible encoding and decoding channels-for example, a multilayer perceptron (MLP) compared to an equalizer filter, Viterbi detectors, and decoders [9]- [11]. Moreover, many convolution neural network (CNNs) contrivances have also improved iterative decoding systems with parity checks of log-likelihood ratio (LLR) modulators [6], [12]- [15], lowering BER. DNN decoders have used the sequential feedforward of recurrent neural networks (RNNs) for turbo decoders [16] and LDPCbased long-short term memory (LSTM) to minimize the complexity of neuron parameters and noises [17], rapidly reducing computational time [18].…”

Section: Introductionmentioning

confidence: 99%

Long-Short Term Memory-Based Application on Adaptive Cross-Platform Decoder for Bit Patterned Magnetic Recording

2020

View full text Add to dashboard Cite

Dynamic bit encoding and decoding of the magnetic recording process remain a challenge in that the process is restrained by the balance between reading and writing performance of the decoder's bit error rate (BER). Sequential neural networks offer data streamflow for processes to reproduce recoded bits from signal distribution, overcoming the limitation of codeword mapping designed for each specific bitpatterned magnetic recording (BPMR) channel. Here, we implement the vanilla long short-term memory (LSTM) for adaptive modulation decoders in various BPMR channel designs within a single network, which benefits multi-channel decoder calibration tools with the same standardization. Signal information from media readback, a two-dimensional (2D) equalizer, 2D Viterbi, and a 2D soft-output Viterbi algorithm (SOVA) detector is arranged as a tensor that enables sequence-to-sequence bit prediction even with a highly complex data arrangement. Our adaptive model can predict recorded bits from readback with accuracies of approximately 97% for rate 4/5 decoding and 75% for crossing platforms, using a recently proposed singlereader/two-track reading (SRTR) system at an areal density of 4 Tb/in 2 in a signal-to-noise ratio range of 1 to 8 dB. We conducted a BER simulation with the relevant results from conventional decoders and the LSTM model. Ultimately, our approach may demonstrate the limitation of supervised learning designed for BPMR systems and reveal a sequence data focus on LSTM that paves the way for sequential-type, unsupervised, mechanism-based, next-generation magnetic recordings.INDEX TERMS Long-short term memory (LSTM), supervised learning, deep learning, bit-patterned media recording (BPMR), channel decoding

show abstract

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

2021

View full text Add to dashboard Cite

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.

show abstract

A Study on Iterative Decoding With LLR Modulator Using Neural Network in SMR System

Cited by 11 publications

References 9 publications

Soft-Output Detector Using Multi-Layer Perceptron for Bit-Patterned Media Recording

Soft-Output Detector Using Multi-Layer Perceptron for Bit-Patterned Media Recording

Long-Short Term Memory-Based Application on Adaptive Cross-Platform Decoder for Bit Patterned Magnetic Recording

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

Contact Info

Product

Resources

About