A Hybrid Cracked Tiers Detection System Based on Adaptive Correlation Features Selection and Deep Belief Neural Networks
, Ali Hakem Alsaeedi 1, Riyadh Rahef Nuiaa 2, Zaid Abdi Alkareem Alyasseri 3,4,5,*, Nor Samsiah Sani 6,*, Suha Mohammed Hadi 7, Husam Jasim Mohammed 8, Bashaer Abbuod Musawi 9 and Maifuza Mohd Amin 6Round 1
Reviewer 1 Report
The manuscript has work of high scientific value which has shown that the proposed model/method is superior to the existing methods.
There is need to do spell check as there exist a few errors.
Abbreviations in figure captions should be in full - i.e figure 4, 5, 6, 7, 8, 9
Abbreviations in table captions should be in full - i.e table 1, 2
Author Response
Thank you for your comments.
Author Response File: 
Author Response.docx
Reviewer 2 Report
This article presents a hybrid cracked tire detection system based on adaptive correlation feature selection and deep belief neural networks and consists of three main areas: feature extraction, feature selection, and predictor. The system was tested using real images of cracked and normal tires.
In my opinion, the article will be better appreciated by the readers if the following points will be improved:
- Rewrite the abstract (not more than 250 words) to have the following information: motivation, problem statement, approach and obtained results;
- Do not use or specify abbreviations in the abstract;
- In a paper is not recommended to be used first plural person (we ). Rewrite entire paper in an impersonal mode;
- Usually in an article is not used future tense (will);
- Reorganise the paper according to the sections requested by the publisher: Introduction, Materials and Methods, Results, Discussions and Conclusions;
- To illustrate the flow of the proposed ACFS, is better to use a block diagram;
- You compare your work with other research in terms of accuracy. Explain why the works comparable;
- Extend the Conclusion section and emphasize the novelty of your research.
Author Response
Thank you for your comments.
Author Response File: Author Response.docx
Round 2
Reviewer 2 Report
It was not easy to see what are the modifications in the paper. They are not highlighted.
