What are you looking for ?
Infinidat
Articles_top

R&D: Neural Network Equalization for Asynchronous Multitrack Detection in TDMR

Proposed equalization strategy on realistic 2D magnetic-recording channel, and find that proposed equalizer outperforms conventional linear equalizer, by a 37% reduction in bit-error rate and 33% gain in areal density.

IEEE Xplore has published, in 2022 IEEE 33rd Magnetic Recording Conference (TMRC) proceedings, an article written by Elnaz Banan Sadeghian, Department of Electrical and Computer Engineering, Stevens Institute of Technology, Hoboken, NJ, USA.

Abstract: The advent of multiple readers in magnetic recording opens the possibility of replacing the current industry’s single-track detection with the more promising multitrack detection architectures. We have proposed a first solution, a generalized partial-response maximum-likelihood (GPRML) architecture, that extends the conventional PRML paradigm to jointly detect multiple asynchronous tracks. In this paper, we propose to replace the conventional communication-theoretic multiple-input multiple-output equalizer in the GPRML architecture with a neural network equalizer for better adaption to the nonlinearity of the underlying channel. We evaluate the proposed equalization strategy on a realistic two-dimensional magnetic-recording channel, and find that the proposed equalizer outperforms the conventional linear equalizer, by a 37% reduction in the bit-error rate and a 33% gain in the areal density.

Articles_bottom
AIC
ATTO
OPEN-E