Next Article in Journal
Malicious Contract Detection for Blockchain Network Using Lightweight Deep Learning Implemented through Explainable AI
Next Article in Special Issue
A Novel DME-YOLO Structure in a High-Frequency Transformer Improves the Accuracy and Speed of Detection
Previous Article in Journal
Real-Time Embedded Vision System for Online Monitoring and Sorting of Citrus Fruits
Previous Article in Special Issue
Traffic Sign Recognition Based on Bayesian Angular Margin Loss for an Autonomous Vehicle
 
 
Article
Peer-Review Record

DSW-YOLOv8n: A New Underwater Target Detection Algorithm Based on Improved YOLOv8n

Electronics 2023, 12(18), 3892; https://doi.org/10.3390/electronics12183892
by Qiang Liu 1, Wei Huang 1,2,*, Xiaoqiu Duan 1, Jianghao Wei 1, Tao Hu 1, Jie Yu 1 and Jiahuan Huang 1
Reviewer 1:
Reviewer 2:
Reviewer 3: Anonymous
Reviewer 4: Anonymous
Electronics 2023, 12(18), 3892; https://doi.org/10.3390/electronics12183892
Submission received: 22 August 2023 / Revised: 10 September 2023 / Accepted: 11 September 2023 / Published: 15 September 2023
(This article belongs to the Special Issue Advances and Applications of Computer Vision in Electronics)

Round 1

Reviewer 1 Report

The authors of the manuscript, titled "DSW-YOLOv8n: a new underwater target detection algorithm based on improved YOLOv8n," focused on informatics solutions to improve the ability to distinguish objects in photographs taken under challenging conditions. A proprietary algorithm based on modified "YOLOv8n" was chosen for this purpose. A description of the modification of the algorithm with its analysis is presented. 

Comparative studies showing the indicative effects of the modification were performed. The tests were performed based on own images of objects inside of the water and on a set of images, "Pascal VOC," intended for training and checking intelligent algorithms for image analysis. In the cases, comparing the modified to the source algorithm favored the modified.

The items in the references closely relate to the scientific problem under study. The choice of underwater images to study and evaluate the effectiveness of the proposed improvements also indicates the usefulness of the practical use of the algorithm.

As for negative comments;

The authors discussed and compared the effects of their solution - complemented "YOLOv8n" to the use of older algorithms for this purpose in Chapter "4. Analysis and discussion of experimental." Discussion of results was done, citing only one item from the references, which may indicate an overly general review of the content of the cited literature items prepared at the beginning of the manuscript. I recommend supplementing this chapter with other cited items and, on this occasion, a more in-depth discussion of the results, based not only on numerical indicators but also on the objective difficulty of identifying the selected objects analyzed.

Author Response

Dear reviewer: thank you for your careful review and constructive suggestions regarding our manuscript. We have revised the manuscript in accordance with the comments and marked all the amends on our revised manuscript. Modified parts use red font. Thank you very much and best wishes.

Please find an attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

The submitted manuscript needs careful revision. For the details see the attached file.

Comments for author File: Comments.pdf

The quality of English language is acceptable. Some corrections are suggested in the attached file, too.

Author Response

Dear reviewer: thank you for your careful review and constructive suggestions regarding our manuscript. We have revised the manuscript in accordance with the comments and marked all the amends on our revised manuscript. Modified parts use red font. Thank you very much and best wishes

Please find an attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

Below, some remarks have been made to improve the paper entitled: "DSW-YOLOv8n: A new underwater target detection algorithm based on improved YOLOv8n". The paper is very interesting; however, the authors must improve it, addressing all the remarks. 

1) Introduction: Further references regarding the subject must be added, highlighting the most relevant ones and making some comparisons.

2)  Check the format of the equations, font size, etc.

3) Experiments: How many samples were used for the URPC and Publicity Dataset?. The above is not clear. A table with each category and the number of samples obtained must be included.

4) Please explain well the data processing algorithm used.

5) What is the meaning of the SGD Acronym?

6) Fix the sentence of 4.2 session: Comparison of ablation experiments. The authors should check and verify the manuscript's spelling and English punctuation marks. There are many errors. 

7) The order or name of Figure 7 is not correct.

8) Explain better the Figure 7 about the detection results of the method.

What is the accuracy of this model to detect the different images? 

The english language must be improved. Moderate editing required

Author Response

Dear reviewer: thank you for your careful review and constructive suggestions regarding our manuscript. We have revised the manuscript in accordance with the comments and marked all the amends on our revised manuscript. Modified parts use red font. Thank you very much and best wishes.

Please find an attachment.

Author Response File: Author Response.pdf

Reviewer 4 Report

The proportion of non-peer reviewed cited sources is too high. Try and replace them with peer reviewed WoS and Scopus journal articles. ‘environment monitoring, and Marine resources survey’ – why initial letter capitalization? ‘Some researchers have considered using artificial light sources to compensate for these challenges’, ‘Drawing inspiration from human perception processes, researchers have been exploring selective visual attention models.’ – mention some sources. The manuscript will benefit from further discussion of key concepts and methodological criteria in order to offer a better articulation between theory and data. There is a need of structuring the discussion to ensure that the methodological aspects are clearly presented. More development and depth of the methodology and analysis are needed.  The figures should be improved, unified as style, and thoroughly explained. ‘we used recall rate, average detection time’ – We. You should compare your results with others in terms of concrete data for better research integrative value. The chosen methodology seems, at points, to be narrower than what is needed to support the broader conclusions of the work. The analysis strikes me as requiring a bit more depth and to clearly state the contribution that it makes. Apart from compiling key studies, a critical approach to the literature is required. The conclusions should clarify the main contribution of the paper and the value added to the field. There is some discussion of the limitations of the study however these are not considered in terms of the implications on the study findings.
The relationship between multisensor fusion and dynamic routing technologies and virtual navigation and simulation modeling tools as regards underwater target detection has not been covered, and thus such sources can be cited:
Kovacova, M., Oláh, J., Popp, J., and Nica, E. (2022). “The Algorithmic Governance of Autonomous Driving Behaviors: Multi-Sensor Data Fusion, Spatial Computing Technologies, and Movement Tracking Tools,” Contemporary Readings in Law and Social Justice 14(2): 27–45. doi: 10.22381/CRLSJ14220222.
Zvarikova, K., Rowland, Z., and Nica, E. (2022). “ Multisensor Fusion and Dynamic Routing Technologies, Virtual Navigation and Simulation Modeling Tools, and Image Processing Computational and Visual Cognitive Algorithms across Web3-powered Metaverse Worlds,” Analysis and Metaphysics 21: 125–141. doi: 10.22381/am2120228.
Novak, A., Novak Sedlackova, A., Vochozka, M., and Popescu, G. H. (2022). “Big Data-driven Governance of Smart Sustainable Intelligent Transportation Systems: Autonomous Driving Behaviors, Predictive Modeling Techniques, and Sensing and Computing Technologies,” Contemporary Readings in Law and Social Justice 14(2): 100–117. doi: 10.22381/CRLSJ14220226.

Author Response

Dear reviewer: thank you for your careful review and constructive suggestions regarding our manuscript. We have revised the manuscript in accordance with the comments and marked all the amends on our revised manuscript. Modified parts use red font.You provided 3 references, reading these references, I learned to bring a lot, also very helpful to my article. The articles you provided are in the references 2,3, and 6 of my paper, and I cited them respectively. 

Thank you very much and best wishes.

Please find an attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 3 Report

I have received the corrections of the authors, so I believe that they have addressed all the remarks done previously. Therefore,  in my humble opinion, this paper might be published in this journal.

 I think the moderate editing of English language must be required

Author Response

Dear reviewer:

Thank you very much for your review again. The English language of the paper really needs to be improved in many areas. I have made careful revisions, marked the modified part with red font, and uploaded the revised version. I appreciate your guidance on my manuscript.

Gratitude and best wishes.

Reviewer 4 Report

This revised version can be published.

Author Response

Dear reviewer:

Thank you very much for your guidance and comments on my manuscript. I look forward to more suggestions and guidance in the future.

Gratitude and best wishes.

Back to TopTop