Research on Optimization Method of VR Task Scenario Resources Driven by User Cognitive Needs
Round 1
Reviewer 1 Report
As far as I understand, the authors try to inform designers of VR task scenarios about design decisions based on a model that predicts the cognitive load of users. To this end, convolutional neural networks (CNN) are used in a mixed model of manual qualitative judgements and automatic prediction.
This paper is hard to read due to serious language flaws and a sloppy writing. Especially the abstract and introduction are full of redundancies, unexplained abbreviations and cumbersome sentences. Articles are frequently missing when needed, words after citations such as "Li Y [6] et al." are continued in uppercase, etc.
The theoretical frameworks are not explained in detail and the figures are insufficiently annotated and described for an easy understanding of the contents.
It is unclear how the features and properties in the different layers of the process are identified and selected. The application of machine learning in the process of determining design decisions seems to be the innovation presented by the authors. However, the qualitative analysis of the correlation of design features to cognitive load appears to be a manual task and the cornerstone of the approach. Designers are used to these kind of decisions by their training anyway.
Thus, the whole approach can be taken into doubt since the authors do not succeed to adequately report and prove the benefits over traditional design processes. It is unclear how the model is further trained, improved and is actual useable in design practice.
Hence, I argue that major revisions are needed to clearly present and justify this research.
Author Response
Dear Professor，
Thank you for your valuable comments. All of these comments have contributed a lot to improve the quality of our article. According to your comments, we have made extensive modifications to our manuscript and supplemented extra data to make our results convincing. Detailed corrections are set out in the annex. If there are any other modifications we could make, we would like very much to modify them and we really appreciate your help.
Yours sincerely,
Qianwen Fu
Author Response File: 
Author Response.docx
Reviewer 2 Report
The paper focuses on VR feature optimization and was able to outline which design feature affects each criterion levels the most in a case scenario. I found it very interesting and potentially impactful for VR system construction and design.
Before publication, I would recommend addressing some points.
Since the paper aims to be understood by a multidisciplinary readership (for instance cognitive psychologist could benefit from your research), I would recommend explaining in a more general manner some key points of the paper.
For instance, on which basis the VR system' ontology knowledge has been represented? Why those features (e.g., immersion, Fluency, Sense of pleasure) have been selected instead of others? Where are derived from?
The importance degree index should be specified further. Does it reflect the overall importance across criterion levels or within each level?
Some other minor points.
In the first part of the introduction and elsewhere in the paper, punctuation is "strange". It seems that commas are used instead of dots. Please check this issue.
QFD acronym should be explained to the readers the first time you used it.
Author Response
Dear Professor，
Thank you for your valuable comments. All of these comments have contributed a lot to improve the quality of our article. According to your comments, we have made extensive modifications to our manuscript and supplemented extra data to make our results convincing. Detailed corrections are set out in the annex. If there are any other modifications we could make, we would like very much to modify them and we really appreciate your help.
Yours sincerely,
Qianwen Fu
Author Response File: Author Response.docx
Round 2
Reviewer 1 Report
My criticism has been addressed extensively. The quality of the paper is now much higher and I recommend its publication.
Reviewer 2 Report
Dear authors,
I find the paper greatly improved both in quality and in clarity and thus I think it can be accepted and published in the present form.
Best Regards
