Rueangnetr, Natthakan

Preferred name

Alternative Name

Rueangnetr, N.

Main Affiliation

Integrated Innovative Technology

natthakan.ru@kmitl.ac.th

Now showing 1 - 6 of 6

Some of the metrics are blocked by your
consent settings
Enhancing Log-Likelihood Ratios with Mutual Information on Three-Reader One-Track Detection in Staggered BPMR Systems
(2025-03-01)
Rueangnetr, Natthakan
;
Koonkarnkhai, Santi
;
Kovintavewat, Piya
;
Greaves, Simon John
;
Warisarn, Chanon
Because so much information is currently being shared online, there has been a sharp rise in the need for data storage devices over the past ten years. The main storage option is the hard disk drive (HDD), which is less expensive than some other types of data storage. Physical constraints, such as the superparamagnetic limit, are difficult to overcome using existing HDD technology. Consequently, bit-patterned magnetic recording (BPMR) has emerged as a potential solution, offering higher areal densities whilst maintaining thermal stability. Nevertheless, BPMR poses new challenges, such as inter-symbol interference and inter-track interference. Consequently, a number of approaches, such as staggered island layouts and array-reader magnetic recording, have been proposed to overcome these issues. However, this article proposes a three-reader one-track detection method to enhance data retrieval in a staggered BPMR system. Leveraging three-track reading for one-track detection, we obtain three readback signals that function as mutual data sequences. This substantially enhances the detection process in one-dimensional partial-response maximum-likelihood channels. Next, using these mutual data sequences, four novel techniques are presented to enhance bit-error rate (BER) performance and detection accuracy: hard-information flipping, maximum soft-information finding, bit-summation detection, and multilayer perceptron (MLP). This study shows that these proposed techniques can provide better BER performance compared with conventional methods and that the MLP is the most effective technique in enhancing system performance.
Some of the metrics are blocked by your
consent settings
Three-Track Detection Using a Multi-Layer Perceptron for Dual-Layer Bit-Patterned Magnetic Recording Systems
(2025-01-01)
Koonkarnkhai, Santi
;
Plotchu, Siriphon
;
Martnok, Warunee
;
Rueangnetr, Natthakan
;
Kilaso, Sathapath
This paper proposes a multi-layer perceptron (MLP)-based three-track detection method for dual-layer bit-patterned magnetic recording systems. Three architectures are explored: one MLP for three tracks, two MLPs for upper and lower layers, and three individual MLPs per track. Simulation results show that all MLP-based methods outperform conventional partial response maximum likelihood detection, especially under high areal density and complex interference. Among them, the two-MLP system achieves the best bit-error rate performance by effectively separating detection tasks across layers.
Some of the metrics are blocked by your
consent settings
Soft Information Adjustor for Four-Head/Two-Track (4H/2T) Bit-Patterned Magnetic Recording
(2022-01-01)
Rueangnetr, Natthakan
;
Warisarn, Chanon
;
Koonkarnkhai, Santi
;
Kovintavewat, Piya
To mitigate the two-dimensional (2D) interference and track misregistration (TMR) effect, we have previously proposed a TMR correction method combined with the soft-information adjustor (SIA) technique. In practice, the SIA technique uses the advantage of a 2D soft-output Viterbi algorithm (SOVA) detector to improve the reliability of the log-likelihood ratio (LLR) before deciding the estimated user bits. To further improve its performance, this paper proposes a novel SIA scheme by exploiting the advantage of the 2D SOYA detector to improve the LLR reliability of the estimated data bits for the considered upper- and lower-track in four-head/two-track (4H/2T) bit-patterned magnetic recording system. The simulation results indicate that the proposed system can deliver a better BER performance over the conventional SIA system, in particular when the system experiences media noise.
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
3/5 Decoder and LLR Estimator-based Multilayer Perceptron for SRTR Bit-Patterned Media Recording
(2022-01-01)
Rueangnetr, Natthakan
;
Warisarn, Chanon
;
Koonkamkhai, Santi
;
Kovintavewat, Piya
To increase the data storage capacity of the hard disk drives for storing huge digital information that grows rapidly, one of the alternative technologies, bit-patterned media recording (BPMR), can support an areal density (AD) of up to 4 Terabits per square inch (Tb/in2). To increase AD; however, due to inter-track interference (ITI) and inter-symbol interference (ISI), which degrade system performance, when we must reduce the distance between bit-islands. In this work, we propose the rate-3/5 decoder and the log-likelihood ratio (LLR) estimator which performs together with the rate-3/5 constraint code based on the multilayer perceptron (MLP) under a single reader/two-track reading (SRTR) BPMR system. The results of our simulations show that, with the same 3 Tb/in2 user density (UD), when compared to both conventional uncoded and coded systems with and/or without media noise, the proposed system can achieve a lower signal to noise ratio (SNR) while maintaining the same bit error rate performance.
Some of the metrics are blocked by your
consent settings
Deep Neural Networks based Soft-Information Improvement for Two-head/Two-Track Bit-Patterned Magnetic Recording
(2022-01-01)
Khametong, Anawin
;
Rueangnetr, Natthakan
;
Warisarn, Chanon
;
Koonkarnkhai, Santi
;
Kovintavewat, Piya
To increase an areal density (AD) of an ultra-high density bit-patterned magnetic recording (BPMR) system, we have previously proposed a track misregistration (TMR) correction method combined with the soft information adjustor (SIA) to cope with the effects of TMR and two-dimensional (2D) interference. However, we found that soft information or log-likelihood ratio (LLR) can be improved to earn better bit-error-rate (BER) performances. In this work; therefore, we propose to use two types of deep neural networks (DNNs), i.e., multi-layer perceptron (MLP) and long short-Term memory (LSTM) network with identical parameter magnitude to improve overall system performance. Here, both DNNs are operated with an earlier SIA on a two-head/two-Track (2H2T) BPMR system. Numerical results show that our proposed methods can deliver better BER performance over the earlier SIA system at all TMR levels with and without position jitter noises at the AD of 3.0 Terabit per square inch.

Rueangnetr, Natthakan

Filters

Settings

Sort By

Results per page