Edge Machine Learning for the Automated Decision and Visual Computing of the Robots, IoT Embedded Devices or UAV-Drones

Round 1

Reviewer 1 Report

The authors proposed an edge computing-based ML technology and the challenges of its implementation into various proof-of-concept solutions. I have the following concerns. 

 

1. A check on grammatical errors is required.

2. Recent AI-assisted edge computing research are missing. Some are mentioned as follows.

-> "FBI: A Federated Learning-Based Blockchain-Embedded Data Accumulation Scheme Using Drones for Internet of Things," in IEEE Wireless Communications Letters, vol. 11, no. 5, pp. 972-976, May 2022, doi: 10.1109/LWC.2022.3151873. 

-> "AI-enabled Secure Microservices in Edge Computing: Opportunities and Challenges," in IEEE Transactions on Services Computing, doi: 10.1109/TSC.2022.3155447.

3. Authors need to revise the abstract. The abstract needs to be a summary of the overall idea instead of a section summary.

4. Highlight your novelty. 

5. Add a table for section 2 containing the limitation of existing works. 

6. Technical depth is missing.

7. Instead of giving row code, try to provide as a pseudocode with more details.

8. Performance graph is missing. Also, a comparison with existing works is required. 

9. Concluding remarks are missing.

10. A complexity analysis is required.

11. A discussion on convergence is also required. 

Author Response

Please see the attached PDF.

Author Response File: Author Response.pdf

Reviewer 2 Report

The authors discussed edge machine learning (ML) technology and the difficulties of incorporating it into several proof-of-concept solutions they had constructed.  Here are my observations:

1. The paper has a weak structure. Paragraphs in introductions, for instance, are uneven.

2-The introduction section contains a number of problems. Missing are the hierarchy, gap, purpose, and method. 

3- There are insufficient references in the introduction section. In the introductory part, the authors could talk about the importance of deep learning techniques and their greater use outside of the field. The authors can use these significant sources in the introductory section.

https://www.sciencedirect.com/science/article/abs/pii/S2210670722004061

https://www.mdpi.com/1424-8220/22/8/3072

https://link.springer.com/article/10.1007/s00521-022-07104-9

4-Formulas borrowed from other works must be properly referenced.

5-The suggested approach must be explained in detail by the authors.

6- Findings are insufficient. The results must be explained by the authors. additional tables and figures should be included. What is the drawback of your work? It must be brought up.

7-Several figures' quality is totally inappropriate.  recreate them.

8-Separate sections for discussion and conclusions are required.

Author Response

Please see the attached PDF.

Author Response File: Author Response.pdf

Reviewer 3 Report

Edge Machine Learning for the Automated Decision and Visual Computing of the Robots, IoT Embedded Devices or UAV-Drones

1. Starting from the Introduction section, no referencing in the entire section except in third paragraph last line [1] [2] [3]. Authors are suggested to revisit this section.

2. Related work section start with reference [3] then all of sudden reference number [29] [30] etc comes. this section requires major changes with key points of various mechanisms discussed.

3. For the figure 2, the authors trained the neural network in 100 epochs in the ML cloud, need justification in details.

4. Figure 3 should be re designed with more clarity.

5. Authors are suggested to prepare flow chart for algorithm discussed in fig 4.

6. Prepare the flow chart for Visual Computing of the UAV/Drone PoC Development.

7. OpenPose architecture need more clarity.

8. Authors are suggested to perform the complexity analysis of the complete mechanism.

Author Response

Please see the attached PDF.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

I have no further concerns. 

Reviewer 2 Report

It can be accepted.

Reviewer 3 Report

Edge Machine Learning for the Automated Decision and Visual Computing of the Robots, IoT Embedded Devices or UAVDrones

The manuscript in its current state may be accepted for the publication