Presentation | 2004/7/1 Simplification and Performance Improvements of Neural Network Equalizer for Perpendicular Magnetic Recording Hisashi OSAWA, Takayuki SUDO, Toshimasa SIMIZU, Yoshihiro OKAMOTO, Yasuaki NAKAMURA, Hiroaki MURAOKA, Yoshihisa NAKAMURA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | An important issue in perpendicular magnetic recording is the performance degradation of PRML system due to the influence of the data dependent noise such as jitter-like medium noise. In this report, the neural network equalization is studied to mitigate the influence of jitte-like medium noise. A method of simplification of neural network using a hybrid genetic algorithm(GA) is proposed. Then, the bit error rate performance for PR2ML system with a simplified neural network equalizer is obtained and compared with those of conventional neural network and transversal filter equalizers. The results show that the SNR improvements of PR2ML systems with simplified neural network equalizer over PR2ML system with conventional neural network and transversal filter equalizers are about 0.8 and 1.0 dB, respectively. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | perpendicular magnetic recording / PRML system / neural network equalizer / genetic algorithm / hybrid GA |
Paper # | MR2004-3 |
Date of Issue |
Conference Information | |
Committee | MR |
---|---|
Conference Date | 2004/7/1(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Magnetic Recording (MR) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Simplification and Performance Improvements of Neural Network Equalizer for Perpendicular Magnetic Recording |
Sub Title (in English) | |
Keyword(1) | perpendicular magnetic recording |
Keyword(2) | PRML system |
Keyword(3) | neural network equalizer |
Keyword(4) | genetic algorithm |
Keyword(5) | hybrid GA |
1st Author's Name | Hisashi OSAWA |
1st Author's Affiliation | Faculty of Engineering, Ehime University() |
2nd Author's Name | Takayuki SUDO |
2nd Author's Affiliation | Faculty of Engineering, Ehime University |
3rd Author's Name | Toshimasa SIMIZU |
3rd Author's Affiliation | FUJITSU TEN LIMITED |
4th Author's Name | Yoshihiro OKAMOTO |
4th Author's Affiliation | Faculty of Engineering, Ehime University |
5th Author's Name | Yasuaki NAKAMURA |
5th Author's Affiliation | Faculty of Engineering, Ehime University |
6th Author's Name | Hiroaki MURAOKA |
6th Author's Affiliation | RIEC, Tohoku University |
7th Author's Name | Yoshihisa NAKAMURA |
7th Author's Affiliation | RIEC, Tohoku University |
Date | 2004/7/1 |
Paper # | MR2004-3 |
Volume (vol) | vol.104 |
Number (no) | 166 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |