A Study on Accelerating SP decoding by Neural Network in SMR System
A Study on Accelerating SP decoding by Neural Network in SMR System
复制标题
SMR系统中神经网络加速SP解码的研究
DOI：
10.1109/intermagshortpapers58606.2023.10228247
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Y. Okamoto
中科院分区：
文献类型：
--
作者：
Madoka Nishikawa;Y. Nakamura;Y. Kanai;Y. Okamoto
我们之前研究了叠瓦式磁记录（SMR）系统中的低密度奇偶校验（LDPC）编码和迭代解码作为实现超高密度硬盘驱动器（HDD）的信号处理方法。此外，我们提出应用神经网络来提高解码性能并实现迭代解码的自动化。在本研究中，我们应用神经网络来加速和积（SP）解码器中的迭代解码。结果，与我们之前的研究相比，带有神经网络的 SP 解码器以最少的迭代解码次数实现了“无错误”。
We have previously studied low-density parity-check (LDPC) coding and iterative decoding in shingled magnetic recording (SMR) system as a signal processing method to realize ultra-high-density hard disk drive (HDD). In addition, we have proposed the application of the neural network to improve decoding performance and realize the automation of iterative decoding. In this study, we apply a neural network to accelerate iterative decoding in the sum-product (SP) decoder. As the result, the SP decoder with the neural network realized "no errors" at the fewest times of the iterative decoding compared to our previous studies.
通过阵列头读取和 2D 均衡抑制 ITI
影响因子：
1.6
作者：
Y. Nakamura;R. Suzuto;H. Osawa;Y. Okamoto;Y. Kanai;H. Muraoka
通讯作者：
H. Muraoka