Repair Method and Muéganos Structure Applied to the Nesting Problem in Finite Materials
Round 1
Reviewer 1 Report
This paper introduces a novel repair method aimed at resolving pixel overlaps between items obtained through random generated solutions from metaheuristics. The proposed procedure systematically examines each item and performs four moves (up, down, left, and right) whenever it encounters overlapping pixels until no more overlaps remain. Additionally, a new structure called "muéganos" is defined, facilitating the nesting of elements in a more compact and waste-minimizing manner. This research is very interesting, and I have the following suggestions:- The contributions and core innovations of this work are not very clear. It is recommended to summarize them in the introduction section.
- There is a lack of a systematic introduction to related works, which makes it unclear about the essential differences between this method and existing methods. It is suggested to add a section on related works.
- There is no performance comparison with existing classic or SOTA works, and it is unclear what the positioning of this paper's work is.
Author Response
Response to Reviewer 1 Comments
Comment 1. “The contributions and core innovations of this work are not very clear. It is recommended to summarize them in the introduction section”.
Response 1: At the end of Introduction section, a summary of the contributions and innovations of this work was made.
Comment 2. “There is a lack of a systematic introduction to related works, which makes it unclear about the essential differences between this method and existing methods. It is suggested to add a section on related works”.
Response 2: Related Work section was added to the introduction.
Comment 3. “There is no performance comparison with existing classic or SOTA works, and it is unclear what the positioning of this paper's work is”.
Response 3: Some comparisons were conducted with findings presented in prior research. The Experimental Results section incorporates both images and statistical outcomes derived from the proposed methodology.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
This paper mainly proposes a repair method to avoid the overlaps of pixels between items. Meanwhile, a new structure called muéganos is defined as an auxiliary method applied to the repair method. The whole paper is clearly organized and the data results are clearly presented. The detailed comments are as below:
1. In abstract: How successfully is the proposed repair method, the comparison between nesting without and with muéganos has been mentioned but the result of the repair method hasn’t been detailed in the abstract.
2. In introduction, some paragraphs are related work which should be summarized.
3. In methodology, I think the method will be more user-friendly if there is a general flow-chart about the repair method in the beginning of this part.
4. In experimental results, some other repair methods should be added as a comparison.
5. Some machine learning methods are missing. [1] Graph-based few-shot learning with transformed feature propagation and optimal class allocation[2] U2D2Net: Unsupervised Unified Image Dehazing and Denoising Network for Single Hazy Image Enhancement
NAN
Author Response
Response to Reviewer 2 Comments
Comment 1: “In abstract: How successfully is the proposed repair method, the comparison between nesting without and with muéganos has been mentioned but the result of the repair method hasn’t been detailed in the abstract”.
Response 1: In the abstract section, the results obtained from comparisons with other methods were included, demonstrating how the proposed method enhances the solutions.
Comment 2: “In introduction, some paragraphs are related work which should be summarized”.
Response 2: A review of the Introduction section was carried out and a summary was made in some paragraphs. A Related Work section was added inside the Introduction.
Comment 3: “In methodology, I think the method will be more user-friendly if there is a general flow-chart about the repair method in the beginning of this part”.
Response 3: In “Methodology” section, a flow-chart was added, where the entire repair procedure is specified.
Comment 4: “In experimental results, some other repair methods should be added as a comparison”.
Response 4: Some comparisons were conducted with findings presented in prior research. The Experimental Results section incorporates both images and statistical outcomes derived from the proposed methodology.
Comment 5: “Some machine learning methods are missing. [1] Graph-based few-shot learning with transformed feature propagation and optimal class allocation[2] U2D2Net: Unsupervised Unified Image Dehazing and Denoising Network for Single Hazy Image Enhancement”.
Response 5: Machine learning methods were added in the Related Work section, according to your suggestions.
Reviewer 3 Report
The paper presents a combinatorial optimization problem of nesting items within finite materials, which is crucial in various manufacturing industries like metallurgy, paper, textiles, footwear, and glass. The objective is to optimize material usage and minimize waste using Computer Vision, Computational Intelligence, and Digital Image Processing techniques. The study explores heuristic and metaheuristic methods, including Greedy algorithms, Simulated Annealing, Particle Swarm Optimization, and Genetic Algorithms, to solve the complex nesting problem. The proposed repair method targets overcoming overlaps in solutions obtained from metaheuristics. It also introduces the concept of "muéganos," a structure to compact items and reduce waste. Experimental results show that the proposed method, especially with muéganos, improves wastage and solution quality compared to previous methods.
Strengths:
- Incorporates a wide range of heuristic and metaheuristic techniques for solution approximation.
- Introduces the novel concept of "muéganos" to improve compaction and reduce waste.
- Experimental results demonstrate the effectiveness of the proposed approach, showing significant waste reduction.
Area of Improvement:
- The paper could benefit from more detailed explanations of the methodologies, algorithms, and experimental setups.
- It would be helpful to provide more context about the datasets or materials used in the experiments.
- The paper could discuss the limitations of the proposed method, potential challenges, and scenarios where it might not perform as effectively.
- It is not clear how well this solution can be applied to real problems.
- Please add what to infer from table and figures in captions so that it is easier to understand.
Author Response
Response to Reviewer 3 Comments
Comment 1: “The paper could benefit from more detailed explanations of the methodologies, algorithms, and experimental setups”.
Response 1: In Methodology section, a flow-chart was added, where the entire repair procedure is specified.
Comment 2: “It would be helpful to provide more context about the datasets or materials used in the experiment”.
Response 2: Details of the materials used were included in the Experimental Results section.
Comment 3: “The paper could discuss the limitations of the proposed method, potential challenges, and scenarios where it might not perform as effectively”.
Response 3: In the Discussion section, we address the prospect of future efforts to address the limitations of the proposed approach. An illustrative example of this is the maintenance of a pattern count for the performance of specific production tasks, depending on the industry to which this method is applied. Furthermore, to speed up the execution time, it would be desirable to integrate the use of threads to improve the speed of procedures during real-time execution. It should be noted that our method is applicable to various industries using nesting problems.
Comment 4: “It is not clear how well this solution can be applied to real problems”.
Response 4: The application of the proposed method to real-world problems is mentioned in the Discussion and Future Work section.
Comment 5: “Please add what to infer from table and figures in captions so that it is easier to understand”.
Response 5: The captions of the figures and tables were revised to be more specific and easier to understand.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
I don't have any more comments.
Author Response
Response to Reviewer 1 Comments
No comments
Author Response File: Author Response.pdf
Reviewer 2 Report
The author answer most of my concerns. Maybe few data is also important in this field.[1]Graph-based few-shot learning with transformed feature propagation and optimal class allocation
NAN
Author Response
Response to Reviewer 2 Comments
Comment 1: “The author answer most of my concerns. Maybe few data is also important in this field.[1]Graph-based few-shot learning with transformed feature propagation and optimal class allocation.”
Response 1: Machine learning method was added in the Related Work section, according to your suggestion.
Author Response File: Author Response.pdf
Reviewer 3 Report
The captions of the figures and tables can still benefit from a detailed explanation what to infer from results presented.
Author Response
Response to Reviewer 3 Comments
Comment 1: “The captions of the figures and tables can still benefit from a detailed explanation what to infer from results presented”.
Response 1: A detailed explanation of the results presented in the caption of the figures and tables was added.
Author Response File: Author Response.pdf
