N-STGAT: Spatio-Temporal Graph Neural Network Based Network Intrusion Detection for Near-Earth Remote Sensing

Round 1

Reviewer 1 Report

1.     The abstract is not coherent. It would be good if authors can write a sentence describing numerical results and improvement over other methods.

2.     Authors should pattern the motivation behind using this method to explain in the introduction.

3.     Authors should provide the comments of the cited papers after introducing each relevant work. Authors also should provide more sufficient critical literature review to indicate the drawbacks of existed approaches.

4.    Pattern the motivation behind using this method to explain in the introduction. Why the existing schemes failed? Does no study try to address this aspect before? If yes, this has to be mentioned.

5.    There needs to be citation of recent papers on this topic and revise the literature section with slight Incorporation of recent ideas.

6.    There are some improvements required for the clarity of the diagrams drawn. More specifically the fig.1 needs to provide with good quality and high resolutions.

 

 

 The manuscript is written in poor language and is not technically sound. And the problem is not visible.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 2 Report

1. It is recommended that some experimental data samples be presented in the paper, so that readers can have a clearer understanding of the identified objects and the effectiveness of network intrusion detection.

2. There is limited introduction to the spatial temporary graph neural network model, and it is recommended to add a description of the model architecture. I did not read how GAT and LSTM are combined.

3. Please describe the missing aspects of the original dataset, which led to the expansion of the paper. At the same time, please provide a detailed description of the data expansion method to reflect the scientific and reasonable nature of the dataset expansion.

4. In the description of contribution in the paper, it is mentioned that improvements have been made to the spatial temporary graph neural network. Please provide a specific description of the improvement points.

The English description of the model structure needs to be added.

Modify editing of English language required

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Round 2

Reviewer 1 Report

1.     The abstract is not coherent. It would be good if authors can write a sentence describing numerical results and improvement over other methods.

2.     Authors should pattern the motivation behind using this method to explain in the introduction.

3.     Authors should provide the comments of the cited papers after introducing each relevant work. Authors also should provide more sufficient critical literature review to indicate the drawbacks of existed approaches.

4.    Pattern the motivation behind using this method to explain in the introduction. Why the existing schemes failed? Does no study try to address this aspect before? If yes, this has to be mentioned.

5.    There needs to be citation of recent papers on this topic and revise the literature section with slight Incorporation of recent ideas, for e.g.,, 

- Exploiting dynamic spatio-temporal correlations for citywide traffic flow prediction using attention based neural networks

 

- Exploiting dynamic spatio-temporal graph convolutional neural networks for citywide traffic flows prediction

 

6.    There are some improvements required for the clarity of the diagrams drawn. More specifically the fig.1 needs to provide with good quality and high resolutions.

7.    Parameters of network have been enhanced using training data "until the model obtains the maximum accuracy". If this accuracy is the training accuracy, maybe over-fitting has been performed. If this accuracy is the testing accuracy, the system is adjusted over the same subset that is evaluated. A validation subset could be used to optimize the system with different data than the testing data and without performing over-fitting. In addition, it would be interesting to know which range of each parameter has been analyzed."?

Need to improve the English.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 2 Report

The author has made revisions to the review comments. Please modify the expression of some English sentences.

Minor editing of English language required

Author Response

Please see the attachment.

Author Response File: Author Response.docx