A Survey: Network Feature Measurement Based on Machine Learning
Round 1
Reviewer 1 Report
The authors of this paper undertook a comprehensive examination of the utilization of machine learning algorithms in the assessment of network features. However, it is imperative that certain aspects be clarified in order to fully grasp the insights and implications of their findings.
1) In the reviewer's understanding, FNN and RNN are branches of DNN. It begs the question, why have the authors separated them? Perhaps it would be more appropriate to include them under the DNN section, or if not, what distinguishes DNN in subsection 2.1.4 from FNN in 2.1.6?
2) In section 2.2, LSTM and CNN are generally classified as supervised learning. The reviewer is left to ponder the rationale behind their inclusion in the unsupervised section. Please elucidate how these models were trained without the use of labeled datasets.
3) In section 2.2.2, reference [16] pertains to reinforcement learning. The reviewer cannot identify any utilization of the CNN model in the paper. Please elucidate the application of the CNN model.
Author Response
Please see the attachment.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
The authors have written a survey article network feature measurement based on machine learning algorithms.
· The authors need to provide details of existing survey articles and need for proposing the proposed survey article. There are sufficint number of survey article published. Check the following articles
o Getman, A. I., and M. K. Ikonnikova. "A Survey of Network Traffic Classification Methods Using Machine Learning." Programming and Computer Software 48, no. 7 (2022): 413-423.
o Wang, Danshi, Chunyu Zhang, Wenbin Chen, Hui Yang, Min Zhang, and Alan Pak Tao Lau. "A review of machine learning-based failure management in optical networks." Science China Information Sciences 65, no. 11 (2022): 1-19.
o Murshed, MG Sarwar, Christopher Murphy, Daqing Hou, Nazar Khan, Ganesh Ananthanarayanan, and Faraz Hussain. "Machine learning at the network edge: A survey." ACM Computing Surveys (CSUR) 54, no. 8 (2021): 1-37.
o Ayassi, Reda, Ahmed Triki, Noel Crespi, Roberto Minerva, and Maxime Laye. "Survey on the use of machine learning for quality of transmission estimation in optical transport networks." Journal of Lightwave Technology 40, no. 17 (2022): 5803-5815.
· The article lacks a theme. For example, what kind f networks are you considering? Bandwidth is essential in all networks such MANETs, Wireless Sensor Networks, Mesh networks, IoT, edge networks, etc.
· The number of articles referred for writing a survey article is not sufficient.
The article is well-written, but it lacks a theme. Please revise the article according to the above point.
Author Response
Please see the attachment
Author Response File: Author Response.pdf
Reviewer 3 Report
1. The abstract needs to be modified as per the study
2. Survey reports should give a comparative study on each section of the report
3. conclusion should be on the same Baisis
Author Response
Please see the attachment
Author Response File: Author Response.pdf
Reviewer 4 Report
The author addressed a review article on network feature measurement using machine learning techniques. Based on my review aspects, I have some questions and comments to revise the paper.
1. What are the challenges in network feature measurements?
2. Any constraints need to considered before feature selection? If any specify it.
3. Highlight the research questions of your review paper and provide the answer for the same. This will help the readers to understand the novelty in a clear way.
4. References are mistached with some contents. Recheck the references.
5. English and typo corrections are required.
Author Response
Please see the attachment
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
I think the authors have well-modified the paper and it can be published after checking for some spelling errors.
