当前位置: X-MOL 学术IEEE T. Magn. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Deep Neural Network a Posteriori Probability Detector for Two-dimensional Magnetic Recording
IEEE Transactions on Magnetics ( IF 2.1 ) Pub Date : 2020-06-01 , DOI: 10.1109/tmag.2020.2985636
Jinlu Shen , Ahmed Aboutaleb , Krishnamoorthy Sivakumar , Benjamin J. Belzer , Kheong Sann Chan , Ashish James

In two-dimensional magnetic recording (TDMR) channels, intersymbol interference (within and between tracks) and pattern-dependent media noise are impediments to reaching higher areal density. We propose a novel deep neural network (DNN)-based a posteriori probability (APP) detection system with parallel multi-track detection for TDMR channels. The proposed DNN-based APP detector replaces the trellis-based Bahl–Cocke–Jelinek–Raviv (BCJR) or Viterbi algorithm and pattern-dependent noise prediction (PDNP) in a typical TDMR scenario, in which it directly outputs log-likelihood ratios of the coded bits and iteratively exchanges them with a subsequent channel decoder to minimize bit error rate (BER). We investigate three DNN architectures—fully connected DNN, convolutional neural network (CNN), and long short-term memory (LSTM) network. The DNN’s complexity is limited by employing linear partial response (PR) equalizer pre-processing. The best performing DNN architecture, CNN, is selected for iterative decoding with a channel decoder. Simulation results on a grain-flipping-probability (GFP) media model show that all three DNN architectures yield significant BER reductions over a recently proposed 2D-PDNP system and a previously proposed local area influence probabilistic (LAIP)-BCJR system. On a GFP model with 18 nm track pitch and 11.4 Teragrains/in2, the CNN detection system achieves an information areal density of 3.08 Terabits/in2, i.e., a 21.72% density gain over a standard BCJR-based 1D-PDNP; the CNN-based system also has $3\times $ the throughput of 1D-PDNP, yet requires only 1/10th the computer run time.

中文翻译:

用于二维磁记录的后验概率检测器的深度神经网络

在二维磁记录 (TDMR) 通道中,符号间干扰(磁道内和磁道之间)和依赖模式的媒体噪声是达到更高面密度的障碍。我们提出了一种新的基于深度神经网络 (DNN) 的后验概率 (APP) 检测系统,该系统具有 TDMR 通道的并行多轨检测。所提出的基于 DNN 的 APP 检测器在典型的 TDMR 场景中取代了基于网格的 Bahl-Cocke-Jelinek-Raviv (BCJR) 或 Viterbi 算法和模式相关噪声预测 (PDNP),其中它直接输出对数似然比编码位并与随后的信道解码器迭代地交换它们以最小化误码率 (BER)。我们研究了三种 DNN 架构——全连接 DNN、卷积神经网络 (CNN) 和长短期记忆 (LSTM) 网络。DNN 的复杂性受到采用线性部分响应 (PR) 均衡器预处理的限制。性能最佳的 DNN 架构 CNN 被选择用于使用通道解码器进行迭代解码。颗粒翻转概率 (GFP) 媒体模型的仿真结果表明,与最近提出的 2D-PDNP 系统和先前提出的局部区域影响概率 (LAIP)-BCJR 系统相比,所有三种 DNN 架构都显着降低了 BER。在具有 18 nm 轨道间距和 11.4 Teragrains/in2 的 GFP 模型上,CNN 检测系统实现了 3.08 Terabits/in2 的信息面密度,即比基于标准 BCJR 的 1D-PDNP 的密度增益提高了 21.72%;基于 CNN 的系统的吞吐量是 1D-PDNP 的 3 倍,但只需要计算机运行时间的 1/10。
更新日期:2020-06-01
down
wechat
bug