Review Reports

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

Please check my comments
- In related work, you can talk about machine learning methods, such as Deep Learning in the DL-HEED protocol, which aims to pre-select candidate nodes for the BA module, thereby reducing the search space and computational latency.

-As noted in the discussion, the hybrid structure increases computational overhead. For resource-constrained sensor nodes, the energy spent on the optimisation process itself must be carefully balanced against the savings in communication.

- While the comparison with ACO is valuable, ACO is a relatively older baseline. Comparing BA-ABC against more recent hybrid algorithms (like the ones in your other manuscripts, e.g., QBWO or AGDO) would provide a more contemporary performance benchmark.

- The simulations involve up to 100 nodes. In large-scale IoT deployments (thousands of nodes), the "scout bee" phase and the global search might become bottlenecks.

- The paper uses several weighting factors (). The process for determining these weights is not well documented, which can affect the reproducibility and optimality of the results across different scenarios.

- Please Add a section analysing the computational energy consumption of the BA-ABC algorithm itself

- Beyond energy, include end-to-end latency results. Rapid local convergence (BA) should theoretically reduce the time taken to establish routes.

- How often is the BA-ABC algorithm triggered? Is it per round, or is there a threshold-based trigger (e.g., when a CH's energy drops below 20%) to save on computational overhead?

- In the comparison with ACO, did you find that the "loudness" and "pulse rate" updates in BA provided a faster response to node failures than ACO's pheromone evaporation?

- How sensitive is the network lifetime to changes in the weighting factors?  Is there an automated way to tune these based on the current network state?

- Section 3 can be improved, as the hybridisation of BA and ABC follows a trend in WSN optimisation where multiple objectives are balanced, similar to the EMO-PEGASIS protocol, which is  A Dual-Phase Machine Learning Protocol for Energy Delay Optimisation in WSNs.

 

 

 

 

Author Response

Dear Reviewer,

We sincerely thank you for your valuable and constructive comments. We have carefully revised the manuscript to address all your concerns. The revised version includes substantial improvements in the related work, methodology, experimental analysis, and performance evaluation. All modifications have been clearly incorporated into the manuscript. Below, we provide a detailed point-by-point response.

 

Comment 1:

In related work, include machine learning methods such as Deep Learning (e.g., DL-HEED).

Response:

Thank you for this insightful suggestion. We have expanded the Related Work section to include recent machine learning and deep learning-assisted clustering approaches. We discussed DL-based and reinforcement learning-enhanced optimisation techniques that reduce the search space and computational latency.

Revision Location:

Section 2, Page 3

Explanation:

Recent studies (e.g., Sayed Ali et al., 2023; Wang et al., 2024) demonstrate that integrating learning-based techniques significantly improves clustering efficiency and reduces unnecessary computations. Including these approaches strengthens the scientific context and aligns the manuscript with current research trends.

 

Comment 2:

A hybrid structure increases computational overhead.

Response:

We agree with this observation. A detailed computational complexity and energy trade-off analysis has been added.

Revision Location:

Section 5, Page 12

Explanation:

The revision clarifies that although the BA-ABC hybrid structure introduces additional computational cost, communication energy remains the dominant factor in WSNs. The proposed algorithm significantly reduces communication overhead, which outweighs the added processing cost, resulting in improved overall energy efficiency.

 

Comment 3:

Compare with more recent algorithms beyond ACO.

Response:

We have extended the experimental evaluation to include comparisons with both classical and recent optimisation techniques.

Revision Location:

Section 6, Table 3, Page 14

Explanation:

The manuscript now includes comparisons with modern approaches such as ABC-Q learning and quantum-based routing. The results demonstrate that the proposed BA-ABC algorithm consistently outperforms these methods in terms of energy consumption, latency, and network lifetime.

 

Comment 4:

Scalability concerns (limited to 100 nodes).

Response:

We have added a dedicated discussion on scalability for large-scale IoT deployments.

Revision Location:

Section 6, Page 16

Explanation:

The revision explains the potential bottlenecks in the scout bee phase and global search. It also highlights how adaptive clustering and BA-based local convergence reduce search space and maintain scalability in larger networks.

 

Comment 5:

Weighting factors are not well documented.

Response:

We have clarified the weighting factor selection process and introduced sensitivity analysis.

Revision Location:

Section 4, Pages 9-10

Explanation:

The manuscript now explains the normalisation and adaptive tuning of weights. A sensitivity analysis demonstrates their impact on network performance, improving reproducibility and robustness.

 

Comment 6:

Add computational energy consumption analysis.

Response:

A new subsection analysing computational energy consumption has been added.

Revision Location:

Section 5, Page 12

Explanation:

The analysis shows that computational energy is significantly lower than communication energy and is offset by the reduction in transmission energy achieved through optimised routing.

 

Comment 7:

Include end-to-end latency results.

Response:

We have incorporated a quantitative latency analysis supported by statistical validation.

Revision Location:

Section 6, Table 2, Page 14

Explanation:

The results demonstrate that BA-ABC achieves lower latency compared to ACO due to faster convergence enabled by the BA component.

 

Comment 8:

Clarify how often the BA-ABC algorithm is triggered.

Response:

We have clearly defined the triggering mechanism.

Revision Location:

Section 6, Page 13

Explanation:

The algorithm operates using a hybrid strategy combining periodic execution and threshold-based triggering (e.g., when CH energy falls below 20%). This reduces unnecessary computation while maintaining adaptability.

 

Comment 9:

Compare BA dynamics with ACO pheromone updates.

Response:

We have expanded the discussion comparing BA and ACO dynamic behaviour.

Revision Location:

Section 6, Page 16

Explanation:

The revision shows that BA adapts faster through dynamic loudness and pulse rate adjustments, while ACO relies on slower pheromone updates, leading to improved responsiveness in BA-ABC.

 

Comment 10:

Sensitivity of weighting factors.

Response:

A detailed sensitivity analysis has been included.

Revision Location:

Section 5, Page 12

Explanation:

The analysis demonstrates how different weight configurations affect energy consumption and network lifetime, and introduces adaptive tuning based on network conditions.

 

Comment 11:

Section 3 needs improvement.

Response:

Section 3 has been substantially revised and expanded.

Revision Location:

Section 3, Pages 5-7

Explanation:

The section now clearly presents the hybrid BA-ABC framework within a multi-objective optimisation context, aligning it with modern WSN optimisation trends such as EMO-based protocols.

 

Final Statement

All reviewer comments have been carefully addressed. The revised manuscript now includes:

1. Enhanced related work with recent references
2. Improved methodological clarity and algorithm description
3. Extended experimental evaluation with benchmark comparisons
4. Statistical validation of results
5. Additional performance metrics (latency and scalability)

We believe that these revisions significantly strengthen the manuscript and fully address the reviewer’s concerns.

Thank you again for your valuable feedback.

 

Reviewer 2 Report

Comments and Suggestions for Authors

The manuscript could benefit from several improvements, as outlined below:

1. The experimental setup could be described in a more comprehensive and structured manner to enhance clarity and reproducibility.

2. The experimental results should be more explicitly connected to the related work presented by the authors.

3. The authors are encouraged to further highlight the advantages of the proposed model, while also discussing its possible limitations and challenges.

4. Additional relevant references could be included to strengthen the literature review and improve the overall quality of the manuscript.

Comments on the Quality of English Language

-

Author Response

We sincerely thank the reviewer for the valuable comments and constructive feedback. We have carefully revised the manuscript to address all concerns. The revisions have significantly improved the clarity, structure, and scientific quality of the paper. Detailed responses are provided below.

 

Comment 1

The English could be improved to more clearly express the research.

Response:

We appreciate this comment. The manuscript has been carefully revised to improve language clarity, sentence structure, and readability throughout all sections. Redundant expressions and overly long sentences have been simplified, particularly in Sections 4, 5, and 6. These improvements enhance the overall flow and presentation of the manuscript.

 

Comment 2

The introduction could be improved.

Response:

Thank you for this suggestion. The Introduction has been refined to improve clarity and conciseness while maintaining strong background coverage. Repetitive statements have been removed, and the research gap has been more explicitly highlighted. Additionally, recent references have been strengthened to better position the proposed work within current research trends. These revisions can be found in Section 1 of the revised manuscript.

 

Comment 3

The research design must be improved.

Response:

We appreciate this important comment. The research design has been improved by clearly structuring the hybrid BA-ABC framework and explicitly defining the optimization objectives. The mathematical formulation and parameter definitions have been clarified, and the relationship between clustering and routing optimization has been more systematically presented. These improvements enhance the overall coherence and rigor of the methodology (Section 4).

 

Comment 4

The methods must be improved.

Response:

Thank you for this observation. The methodology section has been revised to improve clarity and reproducibility. Specifically:

1. All variables and parameters are now clearly defined
2. The algorithm steps are presented in a more structured and formal manner
3. The fitness function and weighting strategy are explicitly explained
4. Additional explanations for computational complexity and triggering mechanisms have been included

These revisions are detailed in Sections 4 and 5.

 

Comment 5

The results must be improved.

Response:

We appreciate this suggestion. The results section has been significantly improved by:

1. Providing clearer explanations of simulation outcomes
2. Reducing repetition in figure descriptions
3. Strengthening the connection between results and related work
4. Adding statistical validation and benchmark comparisons

New tables and discussions have been included to improve clarity and reliability of results (Section 6).

 

Comment 6

The conclusions could be improved.

Response:

Thank you for this comment. The conclusion section has been revised to provide a more balanced discussion. In addition to highlighting the advantages of the proposed BA-ABC algorithm, we have explicitly included its limitations, particularly regarding computational complexity in large-scale deployments. Future research directions have also been expanded.

 

Comment 7

Figures and tables could be improved.

Response:

We appreciate this feedback. Figures and tables have been refined by improving clarity and presentation. Figure descriptions have been shortened and made more precise, and captions have been revised to better reflect the content. These changes improve readability and presentation quality throughout the manuscript.

 

Comment 8

The experimental setup could be described more clearly.

Response:

Thank you for this valuable suggestion. The experimental setup has been restructured and described more comprehensively. All simulation parameters, assumptions, and evaluation metrics are now clearly presented in a dedicated and organized manner (Section 6, Table 1). This improves reproducibility and transparency.

 

Comment 9

The results should be better connected to related work.

Response:

We agree with this comment. The revised manuscript now explicitly compares the proposed BA-ABC algorithm with both classical and recent optimization methods, including ACO, PSO, and modern hybrid approaches. These comparisons are discussed in detail in Section 6, strengthening the connection between the proposed work and existing literature.

 

Comment 10

Highlight advantages and limitations.

Response:

Thank you for this important suggestion. The manuscript has been revised to clearly highlight both strengths and limitations. While the proposed BA-ABC algorithm demonstrates superior energy efficiency, reduced latency, and improved network lifetime, we have also discussed the trade-off in terms of computational complexity. This balanced discussion is now included in Sections 5 and 6.

 

Comment 11

Add more relevant references.

Response:

We appreciate this suggestion. Additional recent and relevant references (2022–2025) have been incorporated into the Introduction and Related Work sections. These references strengthen the literature review and better position the proposed work within current research developments.

 

Final Statement

We sincerely thank the reviewer for the insightful comments, which have significantly improved the quality, clarity, and contribution of the manuscript. We believe that the revised version addresses all concerns and meets the publication standards.

 

Reviewer 3 Report

Comments and Suggestions for Authors

The paper is suitable for the journal's field. The introduction briefly reviews some relatively recent works in the field. Section 2 presents the algorithm considered. Section 4 reviews the claimed contributions. Section 5 presents the application of the algorithm in sensor networks. Section 6 presents issues related to simulation and the graphical results obtained. The paper has a brief conclusion. To improve the manuscript, it is recommended to introduce a comparative analysis of the application of the method and the results obtained from the paper with similar issues from works in the field. And based on these details, the authors should analyze the quality of their results based on quality criteria applicable to the application addressed.

Author Response

Dear Reviewer,

We sincerely thank the reviewer for the constructive and insightful comments, which have significantly improved the quality and clarity of the manuscript. All comments have been carefully addressed, and corresponding revisions have been incorporated into the manuscript. The detailed responses are provided below.

 

Comment 1:
Does the introduction provide sufficient background and include all relevant references?
Reviewer’s evaluation: Must be improved

Response:
We appreciate the reviewer’s valuable suggestion. The Introduction section has been substantially revised to improve clarity, strengthen the research gap, and incorporate recent and relevant references (2021-2025). Specifically, redundant explanations were removed, and the research gap was explicitly clarified to emphasize the need for a unified and computationally efficient hybrid optimization framework.

Revision location: Section 1 (Introduction), final two paragraphs.

 

Comment 2:
Is the research design appropriate?
Reviewer’s evaluation: Must be improved

Response:
Thank you for this important comment. The research design has been improved by clearly formulating the proposed BA-ABC algorithm as a multi-objective optimization model. All variables and parameters are now explicitly defined, and the integration of clustering and routing into a unified framework has been clarified.

Revision location: Section 4 (Research Contributions and Objectives), fitness function and model formulation paragraphs.

 

Comment 3:
Are the methods adequately described?
Reviewer’s evaluation: Must be improved

Response:
We have enhanced the methodological clarity by standardizing equation descriptions, explicitly defining variables, and improving the algorithm presentation. In addition, computational complexity analysis has been added to ensure reproducibility and clarity.

Revision location: Section 4 and Section 5 (Algorithm description and complexity analysis).

 

Comment 4:
Are the results clearly presented?
Reviewer’s evaluation: Must be improved

Response:
The Results section has been significantly strengthened by adding detailed analytical explanations, reducing repetition, and linking findings to recent literature. Additionally, explanations of performance improvements have been clarified based on the hybrid optimization mechanism.

Revision location: Section 6 (Simulation Setup and Results).

 

Comment 5:
Are the conclusions supported by the results?
Reviewer’s evaluation: Must be improved

Response:
The Conclusion section has been revised to ensure alignment with the presented results. A balanced discussion has been added, including limitations of the proposed method and directions for future work, improving the scientific rigor of the conclusions.

Revision location: Conclusion section.

 

Comment 6:
Are all figures and tables clear and well-presented?
Reviewer’s evaluation: Must be improved

Response:
Figure descriptions have been refined to improve clarity and reduce redundancy. Captions have been simplified and made more concise to enhance readability.

Revision location: Section 6 (Figures 2-6).

 

Main Comment:
Introduce a comparative analysis and evaluate the quality of results based on appropriate criteria

Response:
We thank the reviewer for this important suggestion. A comprehensive comparative and statistical analysis have been added to strengthen the evaluation of the proposed method. Specifically:

1. A benchmark comparison with classical and recent algorithms (ACO, PSO, ABC-Q Learning, Quantum-based routing) has been included (Table 3).
2. Statistical validation using mean, standard deviation, variance, and confidence intervals has been incorporated (Table 4).
3. Latency performance analysis has been added (Table 2).
4. Standard evaluation metrics (energy consumption, network lifetime, latency, and remaining energy) have been explicitly defined.

These additions provide a rigorous and quantitative evaluation framework and demonstrate the superiority and reliability of the proposed BA-ABC algorithm.

Revision location: Section 6 (Simulation Setup and Results), Tables 2-4.

 

We believe that these revisions have fully addressed the reviewer’s comments and significantly improved the manuscript. We sincerely thank the reviewer again for the valuable feedback.

 

Round 2

Reviewer 2 Report

Comments and Suggestions for Authors

Please ensure that you have successfully addressed all the following comments: 

• The experimental setup could be described in a more comprehensive and structured manner to enhance clarity and reproducibility.

• The experimental results should be more explicitly connected to the related work presented by the authors.

• The authors are encouraged to further highlight the advantages of the proposed model, while also discussing its possible limitations and challenges.

• Additional relevant references could be included to strengthen the literature review and improve the overall quality of the manuscript.

 

Comments on the Quality of English Language

-

Author Response

Reviewer Comment:
The English could be improved to more clearly express the research.

Response:
We sincerely thank the reviewer for this valuable comment. The manuscript has been carefully revised to improve the clarity, readability, and overall quality of the English language. Specifically, we have refined sentence structures, corrected grammatical inconsistencies, reduced redundancy, and improved the academic tone throughout the paper. In addition, several long and complex sentences have been simplified to enhance clarity and ensure better readability for an international audience. These revisions have been applied across all sections of the manuscript.

 

Reviewer Comment:
The introduction could be improved by including more relevant references.

Response:
We appreciate the reviewer’s insightful suggestion. The Introduction section has been significantly strengthened by incorporating additional recent and high-quality references (2021-2026) related to hybrid optimisation, AI-driven routing, and energy-efficient WSN frameworks. These additions improve the contextual background and better position the proposed BA-ABC algorithm within the current state of the art. The updated references can be found in Section 1 (Introduction).

 

Reviewer Comment:
The research design could be improved.

Response:
Thank you for this constructive comment. The research design has been further clarified by explicitly defining the multi-objective optimisation framework, including the formulation of the fitness function, parameter definitions, and algorithm workflow. Additional explanations have been added in Sections 4 and 5 to clearly describe the hybrid integration of the Bat Algorithm (BA) and Artificial Bee Colony (ABC), as well as their respective roles in local and global optimisation.

 

Reviewer Comment:
The methods are not adequately described.

Response:
We appreciate this observation. The methodology section has been substantially expanded to improve clarity and reproducibility. Specifically, we have:

1. Provided a detailed step-by-step algorithm description
2. Defined all parameters and variables in Table 1
3. Clarified the optimisation process, including clustering, routing, and fitness evaluation
4. Included mathematical formulations and explanations for each stage of the algorithm

These improvements are presented in Sections 4 and 5.

 

Reviewer Comment:
The results are not clearly presented.

Response:
We thank the reviewer for this important comment. The Results section has been improved by:

1. Enhancing figure descriptions with clearer explanations
2. Adding structured tables (Tables 3-6) for quantitative comparison
3. Including statistical validation (mean, variance, confidence intervals, and t-test analysis)
4. Improving the logical flow between figures and discussion

These revisions ensure that the results are presented in a clear, structured, and scientifically rigorous manner (Section 6).

 

Reviewer Comment:
The conclusions are not sufficiently supported by the results.

Response:
We appreciate this feedback. The Conclusion section has been revised to explicitly link the key findings with the presented results. Quantitative improvements (e.g., energy reduction, latency improvement, and network lifetime extension) are now clearly summarised and directly supported by the simulation outcomes and statistical analysis.

 

Reviewer Comment:
Figures and tables could be improved.

Response:
Thank you for this suggestion. All figures and tables have been carefully reviewed and improved. Specifically:

1. Figure captions have been expanded for clarity
2. Tables have been reformatted for better readability
3. Additional explanatory text has been added to improve interpretation
4. Cross-references between figures, tables, and text have been clarified

 

General Comments

Reviewer Comment:
The experimental setup could be more comprehensive and structured.

Response:
We have enhanced the experimental setup by clearly describing simulation parameters, hardware configuration, number of runs, and reproducibility conditions. Additional details are now provided in Section 6 to ensure clarity and repeatability.

 

Reviewer Comment:
The results should be better connected to related work.

Response:
Thank you for this valuable suggestion. A more explicit comparison with recent studies has been added, including hybrid, AI-based, and quantum-inspired optimisation methods. The discussion now clearly highlights how the proposed BA-ABC algorithm compares with and improves upon existing approaches (Section 6).

 

Reviewer Comment:
Highlight advantages and discuss limitations.

Response:
We appreciate this important comment. The manuscript has been revised to clearly emphasise the advantages of the proposed model, including:

1. Improved energy efficiency
2. Faster convergence
3. Reduced computational overhead

Additionally, a dedicated discussion of limitations has been added in the Conclusion section, addressing computational complexity, parameter sensitivity, and real-world deployment challenges.

 

Reviewer Comment:
Additional references should be included.

Response:
We thank the reviewer for this suggestion. Several recent and relevant references (2021-2026) have been added throughout the manuscript, particularly in the Introduction and Related Work sections, to strengthen the academic foundation and improve the overall quality of the paper.

 

We sincerely thank the reviewer for their constructive and insightful comments. All suggestions have been carefully addressed, and the manuscript has been substantially improved in terms of clarity, structure, technical depth, and scientific rigour.

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors The authors acknowledged the comments and made changes to the paper.

Author Response

Thank you very much for your guidance.