Detection and Correction of Abnormal IoT Data from Tea Plantations Based on Deep Learning
, Jinlei Feng 1, Wu Zhang 1,2,*, Bo Liu 1, Tao Wang 1, Chenlu Zhang 1, Shaoxiang Xu 1, Lifu Zhang 1, Guanpeng Zuo 1, Yixi Lv 1, Zhe Zheng 1, Yu Hong 1 and Xiuqi Wang 1Round 1
Reviewer 1 Report
• Capitalize the first letter of the following words in your title "correction," "abnormal," "data," "plantations," and "deep learning."
• In the introduction, the authors say, "However, due to the complex tea plantation production environment and other factors,…." Why does tea plantation production consider complex? Justify.
• In the introduction, I recommend that authors present their contributions as points (bullets) to be understood easily by the readers.
• How did the authors calculate the accuracy in Table 1?
• Cite this sentence "The convolution kernel of this layer is used to slide the window ….."
• You need to discuss figure 3 in more detail. For example, what is the output of the CNN model, and what is the input of the SVM model?. How are the two models integrated with each other?
• Move the dataset section to the methodology section because readers need to understand your input before you talk about the design.
• Figure 6 needs to be redesigned because it shows that the CNN-SVM and LSTM are working in parallel; however, I think in your case, CNN-SVM produced the results first, and then these results are inputted into the LSTM model. Is that what you mean?
• Retitle your conclusions to "Conclusions and Future Work."
Author Response
Please see the attachment.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
This paper discusses a novel architecture for abnormal data detection and correction
The presentation flow and content are good with appropriate tables and figures.
Justification for the use of SeLU activation function may be added.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 3 Report
This research presented a detection and correction model of abnormal IoT data from tea plantations using deep learning.
The paper is interesting and I have following major/minor corrections to improve quality.
1. The introduction section needs a few lines regarding the importance of cloud and SDN technologies. Also, it would be better to highlight the developed contributions at the end of the introduction section.
2. It needs some relevant discussion in the related work and revised cited references in terms of manuscript contents.
3. Experiments and results should be presented in separate sections.
4. I can see several grammar issues & long sentences, so double check please
5. Compare your results in the latest state of art for reference check following
Rehman, A., Saba, T., Kashif, M., Fati, S. M., Bahaj, S. A., & Chaudhry, H. (2022). A revisit of internet of things technologies for monitoring and control strategies in smart agriculture. Agronomy, 12(1), 127.
Khan, M. A., Akram, T., Sharif, M., Awais, M., Javed, K., Ali, H., & Saba, T. (2018). CCDF: Automatic system for segmentation and recognition of fruit crops diseases based on correlation coefficient and deep CNN features. Computers and electronics in agriculture, 155, 220-236.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
Thanks
