YOLOv8-RCAA: A Lightweight and High-Performance Network for Tea Leaf Disease Detection
Round 1
Reviewer 1 Report
Comments and Suggestions for Authors
This study proposes a lightweight network named YOLOv8-RCAA based on YOLOv8 to detect tea diseases. It has certain novelty, the structure is reasonable, the experiment and results are sufficient, deep discussion should be made to better support the conclusion and object.
All of the four contributions of this study listed in Line 112-124 are followed by references which means they are all verified by other studies?
Add more detailed information about how to collect the images, such as tools used, shooting height, shooting rules if any, leaf scale or canopy scale?
The object of this study is to find a lightweight deep convolutional neural networks on agricultural devices with limited resources. So I think authors should give some kind of scenarios or platforms the algorithm going to deploy with. And the image acquisition method should match the potential applicaiton cases.
Chinese characters should be avoided in Figure 3/8.
Rotate the second image in first row in Figure 9.
In section 3, authors should add discussions with other studies, the limitation and future work of this study.
The title of section 4 should change to conclusion. Discussions should move to section 3.
Author Response
Please see the attachment.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
Comments and Suggestions for Authors
A novel lightweight network named YOLOv8-RCAA (YOLOv8-RepVGG-CBAM-Anchorfree-ATSS), is proposed and implemented with an objective to locate and detect tea diseases with high accuracy, performance and, deployment.
The reviewer observations about the article are
Section 1 Introduction
The inclusion of several improvements from [25], [26],[27] and [28] in the architecture does it had any other trade off shall have been explained.
The novelty of the architecture in the above context has to be well explained.
Section 2 Materials and Methods
There is a typographical mistake in Line No. 134.
As according to this reviewer could any augmentation technique involving diverse background have improved efficiency should be analysed.
Section 3 Results
The results are investigated and the discussion is elaborate.
Conclusion
The conclusion section elucidates the research article in a nice manner.
Comments on the Quality of English Language
The flow of the article has to be fine and interesting to the readers.
The grammar is good.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 3 Report
Comments and Suggestions for Authors
How the proposed work is different than "https://www.nature.com/articles/s41598-023-33270-4"? Analytical analysis for the study is also required here.
What is the significance of using YOLOv8-RCAA for tea disease detection? There are other possibilities as well. Article seems incomplete in terms of author names, affiliation etc.
A lot of techniques are putted together like YOLOv8-RepVGG-CBAM-Anchorfree-ATSS. I guess the complexity of computation may get increased here. Step by step procedure for this study should also be mentioned here. It will help greatly for upcoming researchers.
Is this study applicable to every part of China or some specific parts only? and why? This will help to gain access that what are those conditions that will help to apply this study on other countries as well having same ecological conditions.
Some basic and recent study is also missing like a) Contemporary and futuristic intelligent technologies for rice leaf disease detection b) Resource-efficient federated learning over IoAT for rice leaf disease classification
Do all the factors affecting Tea are considered here? Is there any assumptions made for this study, then mention those as well. Authors are also requested to provide Dataset authenticity proof.
Comments on the Quality of English Language
Some editing of english is required here.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Round 2
Reviewer 2 Report
Comments and Suggestions for Authors
1. The Figure 6 may be checked again for consistency.
Author Response
Comments 1: The Figure 6 may be checked again for consistency.
Response 1: Thank you for your constructive advice. Based on your suggestions, we have
modified Figures 6 and 7 by changing Mc to Mc(F) and Ms to Ms(F’) to ensure consistency
with Equations 6 and 8. Additionally, we have corrected the minor error in Equation 8.
Author Response File: Author Response.pdf
