All reviews of published articles are made public. This includes manuscript files, peer review comments, author rebuttals and revised materials. Note: This was optional for articles submitted before 13 February 2023.
Peer reviewers are encouraged (but not required) to provide their names to the authors when submitting their peer review. If they agree to provide their name, then their personal profile page will reflect a public acknowledgment that they performed a review (even if the article is rejected). If the article is accepted, then reviewers who provided their name will be associated with the article itself.
Even if the manuscript is extremely long, the reviewers seem satisfied with the recent changes made by the authors and therefore I can recommend this article for acceptance.
[# PeerJ Staff Note - this decision was reviewed and approved by Yilun Shang, a PeerJ Section Editor covering this Section #]
The manuscript is well-written in professional English, with only minor phrasing issues that have been addressed by the authors. The article follows a conventional and well-structured format, supported by well-formatted figures and tables. Key terms are defined upon their first introduction, and mathematical expressions are formally presented, which is commendable. The authors have also appropriately provided citations for all relevant prior literature and have added new, important references as suggested in the review process. To enhance clarity and reproducibility, the authors have made their proprietary Yogyakarta POI dataset publicly available via a GitHub link and have added a new section with benchmarking on the public Solomon dataset. The manuscript also includes a new English translation and explanation for the application screenshots to improve international accessibility.
This is an original primary research study that is well-aligned with the journal's scope. The authors clearly define their research question—how to integrate multi-attribute user preferences into multi-day route optimization—and motivate the gap in existing studies on the Team Orienteering Problem with Time Windows (TOPTW). The investigation is rigorous, employing three scenarios, 50 repetitions per scenario, and a two-tailed Wilcoxon rank-sum test for statistical significance, which is a high technical standard for the field. The methods are described with sufficient detail to facilitate replication, including information on normalization, utility formulation, penalty functions, and the split-itinerary algorithm, along with pseudocode for the Discrete Komodo Algorithm. The authors have addressed the initial gap regarding the lack of a systematic sensitivity analysis for the Komodo parameters (p and smep) by adding a new section with a detailed analysis and corresponding figures.
The findings are based on robust and statistically sound data, as evidenced by the use of multiple independent trials and nonparametric significance testing. The authors have successfully strengthened the external validity of their work by expanding the experimental design to include benchmarking on the widely recognized Solomon dataset. This addition allows for a direct comparison with established high-performing heuristics, addressing the concern about the use of a single, private dataset. The new results show that KomoTrip is competitive in terms of profit values and demonstrates superior computational efficiency on this public benchmark, particularly for more complex problems. The conclusions are well-stated and linked directly to the original research question, appropriately highlighting that KomoTrip strikes a practical balance between solution quality and computational efficiency. The authors transparently report the trade-offs where fitness values sometimes lag behind other heuristics, which is an honest and accurate presentation of their results.
**PeerJ Staff Note:** It is PeerJ policy that additional references suggested during the peer-review process should only be included if the authors agree that they are relevant and useful.
**PeerJ Staff Note:** Please ensure that all review and editorial comments are addressed in a response letter and that any edits or clarifications mentioned in the letter are also inserted into the revised manuscript where appropriate.
**Language Note:** The review process has identified that the English language must be improved. PeerJ can provide language editing services - please contact us at [email protected] for pricing (be sure to provide your manuscript number and title). Alternatively, you should make your own arrangements to improve the language quality and provide details in your response letter. – PeerJ Staff
1. The manuscript is written in professional English, with only occasional minor phrasing issues. It follows a conventional structure—Title and author list, Abstract, Introduction, Related Work, Optimization Modeling, Algorithm description, Experimental Results, and Conclusion—supported by well‐formatted tables and figures.
2. Literature references are appropriate and sufficient for background and context, and the Abstract and Introduction effectively situate the work within the context of the Tourist Trip Design Problem and the metaheuristic literature.
3. All key terms (e.g. TTDP, TOPTW, MAUT, DKA) are defined when first introduced, and mathematical expressions for normalization and utility (Eqs. 22–25) are formally presented.
1. This is original primary research well aligned with the journal’s scope. The authors clearly state their research question—how to integrate multi‐attribute user preferences into multi‐day route optimization—and motivate the gap in existing TOPTW studies.
2. They conduct a rigorous investigation under three scenarios (overall performance, DOI weight combinations, varying POI counts), each repeated fifty times on an Intel i7-12700H platform, and apply two‐tailed Wilcoxon rank‐sum tests at σ = 0.05 to assess significance.
3. The Methods section provides detailed information on normalization, utility formulation, penalty functions, and the split-itinerary algorithm, along with pseudocode for the Discrete Komodo Algorithm, facilitating the replication of the study.
4. A systematic sensitivity analysis of the Komodo parameters p and smep is missing, which limits understanding of the algorithm’s robustness across different settings.
5. The study also relies solely on an 87 POI dataset from Yogyakarta, which constrains the assessment of the method’s generalizability to other regions or larger datasets.
1. The findings rest on robust, statistically sound data. The use of fifty independent trials per scenario, coupled with nonparametric significance testing, demonstrates that KomoTrip’s notable runtime improvements are consistent and not due to chance. Because all experiments are based on a single dataset and set of scenarios, the scalability and applicability of KomoTrip to other contexts remain uncertain.
2. While fitness values sometimes lag behind the original KMA and other heuristics, the authors transparently report both metrics across all cases and interpret the trade‐offs appropriately.
3. Conclusions are well-linked to the original research question and are limited to what the results support, namely that KomoTrip strikes a practical balance between efficiency and solution quality.
1. Figure captions should include on-map annotations for depot, POIs, and day labels to improve clarity.
2. Verify that all equation references are accurate and consistent.
3. Including a high-level workflow diagram of the overall algorithm before the detailed pseudocode would help readers grasp the process more quickly.
English and Clarity (Specific Line Numbers):
Although generally clear, the manuscript includes overly long or complex sentences, affecting readability. Examples include:
Lines 52–58: The explanation of TSP analogy could be simplified into shorter sentences.
Lines 60–66: The description of VRP approach contains multiple clauses making it difficult to follow.
Lines 88–90: This long sentence describing TOPTW could benefit from being split into two shorter sentences for clarity.
Lines 105–107: Complex phrasing here about multi-attribute preferences should be simplified.
Lines 405–409: Sentence describing the solution splitting algorithm is excessively long and complex; please consider breaking it up clearly.
References and Literature Coverage (Missing Recent Papers):
The manuscript overlooks important recent studies on multi-day itinerary recommendations and heuristic optimization methods. Notable missing references include:
Pérez-Cañedo, B., Novoa-Hernández, P., Porras, C., Pelta, D.A. and Verdegay, J.L., 2024. Contextual analysis of solutions in a tourist trip design problem: A fuzzy logic-based approach. Applied Soft Computing, 154, p.111351.
Sylejmani, K., Abdurrahmani, V., Ahmeti, A. and Gashi, E., 2024. Solving the tourist trip planning problem with attraction patterns using meta-heuristic techniques. Information Technology & Tourism, pp.1-46.
Figures are clear and well-labelled, but the manuscript should explicitly provide links to the raw POI dataset in a public repository, or alternatively use a recognised public benchmark.
The study frames the Team Orienteering Problem with Time Windows as a mixed-integer optimisation model and solves it with the proposed Discrete Komodo Mlipir Algorithm (DKA). The overall protocol—three scenario families, 50 stochastic replications, Wilcoxon tests—is methodologically sound, yet four design gaps must be addressed before the work can be judged state-of-the-art:
Dataset choice – All experiments are run on a proprietary Yogyakarta set. This prevents independent replication and makes cross-paper benchmarking impossible.
Benchmark coverage – The paper compares against classic heuristics but not against the current top-performing TOPTW solvers.
Public-dataset validation – KomoTrip should be re-evaluated on at least one standard collection (e.g. the Vansteenwegen TOP/TOPTW instances: https://www.mech.kuleuven.be/en/cib/op). Running exactly the same parameter settings on those instances will demonstrate robustness and allow apples-to-apples comparison with the literature.
Transparent result tables – add some tables for comparison
These additions will make the experimental design fully reproducible, let readers see how KomoTrip stacks up against today’s best algorithms, and satisfy PeerJ’s data-sharing ethos.
Current statistical treatment is solid, but the validity of the conclusions is weakened by the exclusive use of private data and by comparisons that omit the latest high-performing TOPTW heuristics. Without results on recognised public benchmarks, it is impossible to confirm that KomoTrip’s runtime advantage and competitive fitness extend beyond a single regional dataset.
How to strengthen validity
Public-dataset results: Report KomoTrip’s performance on the standard TOPTW benchmarks and place those numbers directly beside the published best-known values.
Once these steps are taken, the findings will be both statistically sound and externally credible, allowing confident claims about KomoTrip’s efficiency and effectiveness.
This paper presents a valuable contribution to the field of computational optimization and recommender systems. It provides a balanced approach, considering not only solution optimality (fitness value) but also practical running time efficiency, which is particularly important in real-world applications like itinerary recommendations.
However, there are a few points to consider for further improvement:
Complex Sentences: Several long sentences throughout the manuscript make some explanations difficult to follow. Simplifying these will greatly improve readability.
Algorithm Clarification: While generally clear, it might help if the authors briefly clarify earlier in the manuscript why sorting is necessary in the original KMA but not in KomoTrip.
Real-world Application: It would enhance the manuscript further if the authors briefly mention the practical applicability or deployment possibilities of KomoTrip beyond theoretical experimentation.
The figures and algorithms are well-presented, but a clearer visualization of a recommended multi-day itinerary example might further illustrate the practical utility of the method.
All text and materials provided via this peer-review history page are made available under a Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.