학술논문

A Study on Accelerating SP Decoding by Neural Network in SMR System
Document Type
Periodical
Source
IEEE Transactions on Magnetics IEEE Trans. Magn. Magnetics, IEEE Transactions on. 59(11):1-5 Nov, 2023
Subject
Fields, Waves and Electromagnetics
Decoding
Iterative decoding
Signal to noise ratio
Artificial neural networks
Target tracking
Shingled magnetic recording
Mathematical models
low-density parity-check (LDPC) code
neural network (NN)
shingled magnetic recording (SMR)
Language
ISSN
0018-9464
1941-0069
Abstract
We have previously studied low-density parity-check (LDPC) coding and iterative decoding in the shingled magnetic recording (SMR) system as a signal processing method to realize ultrahigh-density hard disk drives (HDD). In addition, we have proposed the application of the neural network (NN) to improve decoding performance and realize the automation of iterative decoding. In this study, we apply an NN to accelerate iterative decoding in the sum-product (SP) decoder. As the result, the SP decoder with the NN realized “no errors” at the fewest times of the iterative decoding compared to our previous studies.