Peer-Review Record
Serial Detection with Neural Network-Based Noise Prediction for Bit-Patterned Media Recording Systems
Appl. Sci. 2021, 11(10), 4387; https://doi.org/10.3390/app11104387
Reviewer 1:
Anonymous
Reviewer 2:
Anonymous
Appl. Sci. 2021, 11(10), 4387; https://doi.org/10.3390/app11104387
Submission received: 16 April 2021
/
Accepted: 4 May 2021
/
Published: 12 May 2021
(This article belongs to the Section Electrical, Electronics and Communications Engineering)
Round 1
Reviewer 1 Report
The authors present a neural network approach to improve readout performance in ultra-high density data storage using bitpattern media recording (BPMR). In this approach, a neural network is used for noise prediction in order to produce a soft output that can be more easily denoised. The paper is well written, the effectiveness of the method is well argued, and the conclusions are strongly supported. Just a minor concern:
P. 17 Line 379) The sentence "...when we just only use it alone" may be improved with "...when we just use it alone".
Reviewer 2 Report
The paper is well written and the logic is clear
