Next Article in Journal
Optimal Pressure Sensor Deployment for Leak Identification in Water Distribution Networks
Next Article in Special Issue
A Dual Load-Modulated Doherty Power Amplifier Design Method for Improving Power Back-Off Efficiency
Previous Article in Journal
Health Status Recognition Method for Rotating Machinery Based on Multi-Scale Hybrid Features and Improved Convolutional Neural Networks
Previous Article in Special Issue
Surface-Mount Zero-Ohm Jumper Resistor Characterization in High-Speed Controlled Impedance Transmission Lines
 
 
Article
Peer-Review Record

Reinforcement Learning-Aided Channel Estimator in Time-Varying MIMO Systems

Sensors 2023, 23(12), 5689; https://doi.org/10.3390/s23125689
by Tae-Kyoung Kim 1 and Moonsik Min 2,*
Reviewer 1:
Reviewer 2: Anonymous
Reviewer 3:
Sensors 2023, 23(12), 5689; https://doi.org/10.3390/s23125689
Submission received: 17 April 2023 / Revised: 8 June 2023 / Accepted: 16 June 2023 / Published: 18 June 2023
(This article belongs to the Special Issue MIMO Technologies in Sensors and Wireless Communication Applications)

Round 1

Reviewer 1 Report

This paper proposed a reinforcement learning-aided channel estimator for time-varying MIMO systems, where the basic concept is to select the detected data symbol for channel estimation. The reviewer has the following comments:

1. The MAP rule is used for data detection, which achieves good performance but also incurs very high computational complexity. The MAP rule is not often used in practice, how about the performance achieved by other detection algorithms.

2. In practice, pilot signals should be inserted periodically, while in this work, there is only one pilot block, and complex algorithms are used for channel tracking. The performance of such a tracking scheme will degrade significantly when n increases. This part requires further study.

3. Why not use deep reinforcement learning techniques to solve the considered problem?

None

Author Response

Please see attached file.

Author Response File: Author Response.pdf

Reviewer 2 Report

the proposed topic and methodology are interesting even if only slightly innovative. The following suggest aimed at improve the quality of the work should be taken into account by the authors.

1) the proposed methodology make use of an optimization algorithm, could you compare the obtained results with other state of the art optimizers?

2) you presented only numerical assessment, I understand that an experimental assessment could be complicate. Could you insert some suggestions relates to how implement an experimental assessments?

3) please slightly improve the reference section.

The quality of english language is acceptable, there are only minor typos and grammar errors.

Author Response

Please see attached file.

Author Response File: Author Response.pdf

Reviewer 3 Report


Comments for author File: Comments.pdf


Author Response

Please see attached file.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

No further comments.

None

Reviewer 3 Report

The revised manuscript is fine. The reviewer has no other questions.

Back to TopTop