DSpace-CRIS

Now showing 1 - 4 of 4

Some of the metrics are blocked by your
consent settings
Three-Track Detection Using a Multilayer Perceptron for Dual-Layer Bit-Patterned Magnetic Recording Systems
(2026-01-01)
Koonkarnkhai, Santi
;
Plotchu, Siriphon
;
Martnok, Warunee
;
Rueangnetr, Natthakan
;
Kilaso, Sathapath
This article proposes a multilayer perceptron (MLP)-based three-track detection method for dual-layer bit-patterned magnetic recording (BPMR) systems. Three different MLP architectures are explored and evaluated, namely: 1) a single MLP detecting all three tracks simultaneously; 2) three MLPs, each detecting one track independently; and 3) two MLPs dedicated to upper and lower recording layers. Simulation results show that the proposed MLP-based systems outperform the conventional partial-response maximum-likelihood (PRML) detection scheme, particularly under severe interferences and high areal density (AD). Among the proposed systems, the two-MLP architecture offers the optimal balance between detection accuracy and computational complexity, making it the most promising solution for future high-density magnetic recording systems.
Some of the metrics are blocked by your
consent settings
An MLP-Based ITI Suppression Method for Multi-Head Multi-Track Bit-Patterned Magnetic Recording
(2025-01-01)
Koonkarnkhai, Santi
;
Kovintavewat, Piya
;
Warisarn, Chanon
Inter-track interference (ITI) is a critical challenge in bit-patterned magnetic recording (BPMR) systems, particularly at high areal densities (ADs) where reduced bit period and track pitch lead to severe interference. This article introduces a novel multi-layer perceptron (MLP)-based ITI suppression method for the three-head three-track (3H3T) BPMR system. Our approach uses an MLP to estimate the main track data and uses iterative decoding to generate soft information, which will then be used to reconstruct and remove ITI for the adjacent tracks. At an AD of 3 Tb/in2 and a bit-error rate (BER) of 10<sup>-5</sup> , simulation results show that the proposed system achieves performance gains of 1 and 6.5 dB compared with the previously proposed 3H3T system and the conventional system with one-head one-track detection, respectively. In addition, our system demonstrates robust performance under challenging conditions, maintaining effectiveness with track mis-registration (TMR) up to 10% and media noise up to 5%. These results indicate that the proposed method can be considered as one of the promising solutions for ultrahigh-density BPMR systems.
Some of the metrics are blocked by your
consent settings
Deep Neural Network Detection With an ITI Subtraction for Non-Uniform Track-Width Two-Dimensional Magnetic Recording
(2024-04-01)
Buajong, Chaiwat
;
Lee, Jaejin
;
Warisarn, Chanon
Continuously expanding the magnetic recording density results in unavoidable interferences including intersymbol interference (ISI) and intertrack interference (ITI) that both critically degrade the system performance. Even with advanced signal processing tools, two-dimensional magnetic recording (TDMR) still struggles to provide satisfactory performance. Thus, this article proposes the deep neural network (DNN)-based detection deployed in conjunction with an equalizer for the TDMR system. The coding scheme uses a low-density parity-check (LDPC) code, enabling the information exchange or the turbo decoding. The retrieval of data occurs within a group of three adjacent tracks. We also explore two different track configurations: uniform and non-uniform tracks that involve doubling the width of the middle track among the three adjacent tracks. The utilization of the highly reliable signal obtained from the double-width track enables the application of ITI subtraction technique, enhancing the information exchange. This technique can mitigate the ITI effect by subtracting the target signal with the imitated ITI signal. In addition, we investigate two different DNN architectures including the multilayer perceptron (MLP) and convolutional neural network (CNN), along with two scenarios for the detections in different passes of turbo decoding. The simulation results conducted on the Voronoi media model, with realistic grains and non-magnetic grain boundaries, show that the proposed detection systems with the non-uniform track configuration offer a performance gain up to 5.3 dB over the system with the uniform track configuration. Moreover, iteration for the turbo decoding passes incrementally improves the system performance in the proposed systems with the non-uniform track while the systems with the uniform track no longer provide performance gain as the number of iterations goes on.
Some of the metrics are blocked by your
consent settings
Multilayer Perceptron-based Detector for a Coded Two-Dimensional Magnetic Recording
(2022-01-01)
Buajong, Chaiwat
;
Warisam, Chanon
Recently, magnetic recording technology is on the verge of reaching its recording density limit. Two-dimensional (2- D) magnetic recording (TDMR) becomes a candidate for next- generation magnetic recording because of its compatibility with the current technology and powerful 2-D signal processing tools. However, the degradation in signal quality due to 2-D interference is inevitable. In this paper, we introduce the multilayer perceptron (MLP)-based detector that can produce soft-output information in the form of a log-likelihood ratio (LLR). Such a detector can also execute turbo decoding by exchanging information with a low- density parity-check (LDPC) code. The simulation result shows that the proposed system outperforms the systems that use the conventional detector based on the Viterbi algorithm.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results