GRU-Based Deep Learning Framework for Real-Time, Accurate, and Scalable UAV Trajectory Prediction
Round 1
Reviewer 1 Report
Comments and Suggestions for AuthorsDear Authors,
Please find my review in the attached file.
Kind regards,
Comments for author File: 
Comments.pdf
Author Response
Dear Reviewer,
Thank you for your thorough review.
We've made the changes you suggested and are submitting them as attachments.
Author Response File: Author Response.pdf
Reviewer 2 Report
Comments and Suggestions for AuthorsThis paper analyzes the methods already known in the literature.
The paper can be improved if the methods used are presented (even if they are known). Pseudocodes (and/or formulas used) should be added for each algorithm used.
The paper talks about reliability... what kind of reliability?
Were all the tests done on simulators? Why not on a real UAV?
Author Response
Dear Reviewer,
We sincerely appreciate your thoughtful and constructive feedback on our manuscript. Your valuable comments have helped us refine the clarity and completeness of our research. In response to your suggestions, we have made the following clarifications and improvements.
We hope this clarification fully addresses your concerns. Please let us know if there are any additional suggestions to further improve the manuscript. Thank you once again for your time and thoughtful review.
Best regards,
Seungwon Yoon
Author Response File: Author Response.pdf
Reviewer 3 Report
Comments and Suggestions for AuthorsThis paper deals with the topic of real-time trajectory prediction for drones, which is obviously of interested for the journal. The paper is globally well-written and its structure is adapted. The introduction does provide a sufficient background as well as enough references to present the tackled problem and the methodology used.
The results presented are convincing and clear, showing a strong improvement on the capacity to predict the drones trajectory using GRU-based DL. In my opinion, the paper can be considered for publication as soon as these (minor) points are tackled :
- Tables 2, 3 and 4 present the RMSE and MAE for the model : a relative value (for example wrt. the total variation of latitude duriong the flight) would be more informative.
- In section 4.1, the advantage of your model against the FlightBERT++ model is presented in terms of accuracy. I believe the computational burden should also be discussed for both models.
- Table 7 shows a RMSE for latitude and longitude several orders of magnitude greater than the total variation of lat/lon during the flight (which is not consistent with figure 6 showing quite a good agreement for the trajectories). Is there some kind of error in the values presented ?
- Sections 4.3 and 4.4 and 5. are quite redundant (sections 4.3 and 4.4 even begin with the same sentence). The paper would gain to see some parts fused together and have a more concise presentation. Also in these sections you might also want to avoid using too much superlatives to describe the results / contributions.
Also, here are some typos spotted during my reading :
- formula (2) "+F" should be a subscript
- line 340 : "he resulting ..." -> "The resulting"
Author Response
Dear Reviewer,
We sincerely appreciate your thoughtful and constructive feedback on our manuscript. Your insightful comments have been instrumental in refining the clarity, accuracy, and overall presentation of our work. We are grateful for the time and effort you dedicated to evaluating our research.
In response to your valuable suggestions, we have carefully revised the manuscript and addressed each of your comments as follows.
We truly appreciate your valuable feedback, which has significantly contributed to improving the quality of our manuscript. We hope that our revisions adequately address your concerns, and we welcome any further suggestions for refinement.
We appreciate your feedback and are confident that these revisions have strengthened the clarity and impact of our manuscript.
Best regards,
Seungwon Yoon
Author Response File: Author Response.pdf
