An Integrated YOLOv5 and Hierarchical Human-Weight-First Path Planning Approach for Efficient UAV Searching Systems
, Chin-En Yen 2, Hao-Fu Chang 1, Yi-Wei Chen 1, Ming-Tsung Hsu 1, Wen-Fu Wang 1, Da-Yi Yang 1 and Yu-Hsuan Hsieh 1Round 1
Reviewer 1 Report
Comments and Suggestions for AuthorsThe following suggestions should be carefully revised.
1. The summary and description of related work in the field are insufficient. Since deep learning methods have achieved remarkable results in the field of signal/image processing. The following related work of deep learning must be cited and discussed, including A memetic algorithm based on two_Arch2 for multi-depot heterogeneous-vehicle capacitated arc routing problem. Swarm and evolutionary computation, 63, 100864, 2021. New time-differenced carrier phase approach to GNSS/INS integration. GPS Solutions, 26(4), 122, 2022. Robust tube-based model predictive control with Koopman operators. Automatica, 137, 110114, 2022. Distributed bearing-based formation maneuver control of fixed-wing UAVs by finite-time orientation estimation. Aerospace Science and Technology, 136, 108241, 2023. Spectrum interference-based two-level data augmentation method in deep learning for automatic modulation classification, Neural Computing & Applications, vol. 33, pp. 7723-7745, 2020.
2. The reasons for using YoloV5 should be explained, since there has been developed to YoloV8.
3. Some other deep learning structures for detection should be comapred.
4. What is the basis for setting simulation parameters in Table 1.
5. The results in Figures 13 and 14 show obvious vibrations, and the reasons should be analyzed.
6. More experiments and ablation tests should be supplemented.
Comments on the Quality of English LanguageMinor editing of English language required.
Author Response
Please see the attachment.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
Comments and Suggestions for AuthorsAn Integrated YOLOv5 and Hierarchical Human-Weight-First Path Planning Approach for Efficient UAV Searching Systems
1. The abstract is not correlated with the title of the paper. The abstract of the manuscript should be revised as the new contributions and the explanation are not clear.
2. The authors claimed that the proposed method uses an integrated YOLOv5 for Efficient UAV Searching Systems, but I haven't seen detailed information about how they improved the existing YOLOv5 approach. They should clearly write in the abstract that they used the already improved YOLOv5 method or they improved the traditional YOLOv5 architecture by themselves while developing the Efficient UAV Searching Systems method?
3. More information is required about the method followed in the so-called subjective evaluation. I mean about the procedure and environment (the information provided to the subjects.
4. Achieved results caused by overfitting? Please discuss in the experiment section.
5. The authors didn’t mention any limitations of the proposed method, they should.
6. The conclusion part needs to be written with the major findings of this article. And future research direction on how to fix that challenge.
Summury: Generalizability is hard to measure, and some readers may object to that part of the conclusion, especially given the relatively small test set size. Perhaps randomly chosen several thousand images from an unbiased dataset with millions of images may convince more people, but that's almost impractical. Authors may wish to soften that claim.
Comments on the Quality of English LanguageMinor editing of English language required
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
Comments and Suggestions for AuthorsAccept.
Author Response
Thank you for your comments and kindly helps.
