Next Article in Journal
A Digital Twin-Based Heuristic Multi-Cooperation Scheduling Framework for Smart Manufacturing in IIoT Environment
Next Article in Special Issue
Non-Autoregressive Sparse Transformer Networks for Pedestrian Trajectory Prediction
Previous Article in Journal
Spontaneous Epileptic Recordings from hiPSC-Derived Cortical Neurons Cultured with a Human Epileptic Brain Biopsy on a Multi Electrode Array
Previous Article in Special Issue
Research on Blast Furnace Tuyere Image Anomaly Detection, Based on the Local Channel Attention Residual Mechanism
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Applied Sciences
Volume 13
Issue 3
10.3390/app13031435
Review Report
applsci-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
Article
Peer-Review Record

AAL-Net: A Lightweight Detection Method for Road Surface Defects Based on Attention and Data Augmentation

Appl. Sci. 2023, 13(3), 1435; https://doi.org/10.3390/app13031435
by Cheng Zhang †, Gang Li †, Zekai Zhang, Rui Shao, Min Li, Delong Han and Mingle Zhou *
Reviewer 1: Anonymous
Reviewer 2:
Michal Zabovsky
Appl. Sci. 2023, 13(3), 1435; https://doi.org/10.3390/app13031435
Submission received: 1 January 2023 / Revised: 16 January 2023 / Accepted: 17 January 2023 / Published: 21 January 2023
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)

Round 1

Reviewer 1 Report

The paper proposes a lightweight first-stage object detection network, AAL-Net, used for road surface defects. A lightweight feature extraction module (LF) and NAM attention module are used to ensure the accuracy and real-time of the pothole detection process. A data augmentation method is also employed to further improve the detection accuracy and robustness of the AAL-Net. The results indicate that this network has better performance than other existing networks. Overall, this paper is well organized, and relevant methods are comprehensively described. Some of my comments and suggestions are given below.

 

(1) The authors should pay more attention to the grammar check. For example, ‘parameter’ and ‘are’ (see lines 275 and 277) are inconsistent. In line 299, ‘performe’ should be replace by ‘performed’.

 

(2) Section 2.1 introduces some lightweight neural networks, such as ShuffleNet and MobileNet. The application of lightweight networks for defect detection in engineering areas should be introduced as well. Here are some examples: doi:10.3390/electronics8111354; doi: 10.1007/s00170-022-10335-8.

 

(3) Section 4.2.1 introduces the relevant experimental settings, such as batch size, learning rate, and optimizer. The authors should clarify why these parameters are used and whether different parameters have been tested and compared.

 

(4) In Figures 8, 9, 10, 12, the scales of y-axis should be added.

 

(5) The results of Section 4 indicate that AAL-Net is superior to other existing networks. It is recommended that the authors should conduct in-depth comparison and analysis to explain why AAL-Net has the best performance, or clarify the advantages of the proposed model over the existing ones. Otherwise, only descripting comparison results is not good enough. More discussion and analysis should be added.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Complete comments and suggestions are provided in the file attached.

Comments for author File: Comments.pdf

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Overall, the authors have managed to respond to the reviewer’s comments. This manuscript with high quality can be accepted for publication.

Back to TopTop