Artificial-Neural-Network-Based Predicted Model for Seam Strength of Five-Pocket Denim Jeans: A Review

Round 1

Reviewer 1 Report

This paper is a review of the Artificial Neural Network used in different fields, but dominantly focused at the field of textiles. The chapter 2. Artificial Intelligence in Textile Industry in well written and relevant for the field. In comparison with other published material, this review is extensive and gives a good insight into this specific field of research. The description is precise, with a large number of relevant references included (especially the presentation of outcomes within the Table 1. The references are appropriate.

The quality of figures should be improved. The type and size of letters is not consistent, some letters are hard to read.

Also, if the figures are not developed by authors, the reference needs to be given in the figure caption.

The chapter 1.1. Artificial Intelligence in Different Fields of Life needs to be shortened and given without figures, as the focus of the paper is on textiles, not other fields.

Author Response

"Please see the attachment."

Author Response File: Author Response.pdf

Reviewer 2 Report

SUMMARY

The paper presents a review of AI method in the in the textile Industry. It covers a sufficient number of articles on the topic and provides insight into the challenges that can be addressed by AI. However, the review lacked a systematic and consolidated presentation

COMMENTS

1. Fig. 2 mixes AI methods (Genetic algorithms, ANN, ...) and its applications (robotics, NLP).

2. In Fig 2, the meaning of the arrows from the Machine learning to ANN, from ANN to Fuzzy Logic, etc. is not clear.

3. Only one specific case of metaheuristic optimization algorithms is described (Genetic algorithm) in Fig.2 and the text below.  

4.  The expert systems and NLP (lines 101-110 and 130-138) are not a technique but an application. For example, ANN and Fuzzy Logic can be used in an expert system.

5. Industrial applications are omitted in Figure 3 (power industry, machinery, mining).

6.  It is recommended to significantly shorten the text in lines 154-241. It is very superficial and not systemic. It is better to provide readers with links to open reviews on different applications of AI.

7. There are no signatures on Fig. 9, it is difficult to understand what the authors meant.

8.  Data in Tables 1 and 2 need to be systematized. The same things are labeled differently, such as "Multi-layered Perception (MLP) NN" and "Multi-layer perception neural network", "Image Processing Algorithms" and "Image Processing techniques", and so on.

9. Table 1 does not specify which AI techniques are used in image processing. A lot of AI approaches can be used in this field.

10. It is not clear why the MLP image is shown at the end of the article (Fig. 25).

11.     “In this study authors tried to present the future trends of research on AI based studies.” At the same time the description of the future trends is only 1 paragraph (lines 897-911) without references.

12. The synthesis of the submitted data has not been completed. There is no conclusion on the most promising methods as well as on the risks of AI application.

13. The review covers much more than the title of the article.

Author Response

"Please see the attachment."

Author Response File: Author Response.pdf

Reviewer 3 Report

This review focuses on the hot research topic on AI technology with specific perspective on textile industry, which is very interesting, comprehensive and informative. A great number of cutting-edge application examples are included in this article. There are a few suggestions proposed below for revision.

1. As the review focus on the ‘Predicted Model for Seam Strength Five Pocket Denim Jeans’, the background on AI tech out of this scope in the front section should be shortened.

2. The AI tech on textiles industry not limited to Five Pocket Denim Jeans, should be briefly mentioned to increase the integrity of this review.

3. There are too many subsectors included in the article. This makes each subsector short and sloppy, with only one citation used in each. It is recommended to pick up a few to describe in details.

4. The limitation of current AI tech on textiles’ making should also be mentioned.

Good.

Author Response

"Please see the attachment."

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

The paper has been improved according to the comments. I suggest to accept it for publishing.

Author Response

"Please see the attachment."

Author Response File: Author Response.pdf

Reviewer 2 Report

The authors considered most of the comments and significantly improved the article. Only two comments remain 

1. Only one specific case of metaheuristic optimization algorithms is described (Genetic algorithm). Metaheuristic optimization algorithms include genetic, swarm intelligence, simulated annealing, etc.

2. The Section 5 "Future Trends" contains a lot of general information such as "To begin building our AI-based model, we must first collect a representative and diversified dataset", "Selecting the right machine learning methods is essential", "The performance of the model is then assessed using the validation data and suitable regression assessment measures" and so on. In my opinio, more in-depth conclusions need to be drawn and justified by the information provided in the review.

Author Response

"Please see the attachment."

Author Response File: Author Response.pdf

Reviewer 3 Report

Accept in present form

Author Response

"Please see the attachment."

Author Response File: Author Response.pdf

Round 3

Reviewer 2 Report

It can be accepted now