Artificial Intelligence-Enabled Exploratory Cyber-Physical Safety Analyzer Framework for Civilian Urban Air Mobility

Round 1

Reviewer 1 Report

The manuscript presents a Framework to detect attacks on a Civilian Urban Air Mobility scenario. The manuscript is well organized, but some parts of the presentation should be improved:

lines 168-170: In which sense "the UAM become protect 169 from the steal or lost".

lines 236-238: A better description of figure 3 should be provided. It needs to be clarified how the transverse/roll changes and vertical/yaw changes are referred to in Fig.3. How has the correlation been proven to be not spurious?

lines 241-245: lines 241-245: Why has a validation set not been considered?

lines 251-254: Where are the details about the mentioned models?

Please consider rechecking the manuscript: there are some typos (especially regarding past participles)

Author Response

Dear Reviewer,
We would like to thank the reviewer for the constructive comments, which have helped us to improve the technical contents and presentation quality significantly. We appreciate very much the reviewer’s time and efforts. Furthermore, we have taken into consideration all comments and suggestions in the revised manuscript. We have also described in the response letter how we have addressed all comments and the changes that we have made. 

Best Regards,
The authors of manuscript applsci-209782 

Author Response File: Author Response.pdf

Reviewer 2 Report

The manuscripts present a comparison of several Machine learning algorithms for predicting malicious activity for unmanned air mobility devices. The introduction section is very well written and adequately identifies the literature gaps. The novelty of the proposed algorithms and methodology may need some more additions to improve the quality of work. In addition to the suggested changes in the manuscript, the following points must be considered before publication:

1. Please avoid the word developed machine learning algorithms because the manuscript applies the existing algorithms. A basic description of the 6 degrees of freedom by yaw, pitch and roll may also be described using a figure.

2.  The methodology may be further explained in detail as follows, Please introduce the methodology using a block diagram in the figure clarifying the variables the algorithms the evaluation criteria and reference to switching/radio status etc for bringing clarity in the interpretation of the results.

3. Particularly the dataset used and the variables recorded in the given dataset may be introduced with descriptions of the variables and their significance. This will help in the understanding of figure 3.

4. There must be a section that discusses, in brief, the hyperparameters of the algorithms used and which hyperparameters were used for the case study and why? 

5. The clarity is lost in the case study with no information about the number of input variables, the names of the input variables and the discussion of their selection in light of significance in light of point 3 above. whether all were used during prediction or some were selected. Whether the selection of variables was based on the pearson correlation coefficient only or some other methods such as PCA. If only person correlation, why?

6. Without a description of the data, figures 12 and 13 cannot be understood. Switching states radio states require description while introducing the methodology.

7.  In the discussion section, the manuscript must compare the results with previous literature and establish the novelty of the manuscript explicitly. Please mention the significance of the novelty and results. The shortcoming of the methodology and the way forward for more research. A discussion section must have all such information to conclude a manuscript of such standard.

8. The novelty derived in the discussion must also be mentioned in the conclusion section.

A PDF is also attached with minor corrections

Comments for author File: Comments.pdf

Author Response

Dear Reviewer,
We would like to thank the reviewer for the constructive comments, which have helped us to improve the technical contents and presentation quality significantly. We appreciate very much the reviewer’s time and efforts. Furthermore, we have taken into consideration all comments and suggestions in the revised manuscript. We have also described in the response letter how we have addressed all comments and the changes that we have made. 

Best Regards,
The authors of manuscript applsci-209782 

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

All the queries have been addressed properly.