The Application of the SubChain Salp Swarm Algorithm in the Less-Than-Truckload Freight Matching Problem
Round 1
Reviewer 1 Report
Comments and Suggestions for AuthorsThank you for inviting me to review this article. The topic is certainly important from a theoretical and practical point of view.
However, after reading the title and abstract, I had the following questions (which the future reader will probably ask themselves):
What (optimization?) problem did the authors want to address? There can be many problems at different levels – strategic (leaving aside the question of which markets the company operates in and what kind of cargo it transports): the number of transshipment terminals and their location, at the strategic level, i.e. daily operations: the choice of transport routes, matching a given shipment to a given vehicle, and whether the vehicle will go directly or to a terminal.
Another question: is it a transportation, shipping or logistics company that provides LTL services, or a manufacturing or trading company that transports its cargo?
Was the algorithm mentioned in the title developed by the authors or did they just use it to optimize the transportation LTL cargo? It is only in the further parts of the article that we learn that the authors applied this algorithm to the problem of transporting such parcels.
I think they should explain at the beginning that it is about LTL freight and not about so-called “parcels” or medium-tonnage shipments that do not fill the entire load capacity of large vehicles. For example, on the Polish transportation services market, general cargo is largely understood as loads sent on pallets and in quantities of 4-6 pallets. Twelve pallets is already a medium-tonnage load. General cargo does not have to be sent through the terminal system if the customer wants to send a shipment quickly. Please indicate in the text that you are referring to a situation where they can be transported via the terminal system.
However, these are minor comments. The most serious thing, which is immediately apparent when reading it, is that the introduction does not state the purpose of the research or explain the problem that the authors have taken on (as I mentioned above). What follows is only a hastily listed literature on small parcel delivery..
Since the authors use “The Salp Swarm 56 Algorithm”, they should first explain its essence, who developed it, for what purposes, and why the authors chose this algorithm and not others..
I don't understand what the authors' contribution is, because the research problem has not been explained. I can only guess that it is about matching loads to vehicles, but that's just a guess. I would suggest explaining it with a practical (even hypothetical) example so that the reader understands what it is about.
Section 2
I don't understand this sentence at all:
„The control system controls the horizontal movement of the trolley on the bridge, 94 and the movement and swing of the load can only be indirectly controlled by controlling 95 the Problem Descriptione movement of the trolley. »
In « principles » Authors write:
« The distribution cost for a truck is the sum of the departure cost and fuel expenses »
What are then « departure costs » if not « fuel expenses » ?
« Delivery time is calculated based on the average speed of the vehicles, without considering the impact of road conditions »
How do you combine delivery time with delivery costs? For example, is the time the starting point, meaning that, from the various solutions, you should first choose those that guarantee the set delivery time?
„The system operating cost of LTL (Less Than Truckload) logistics includes basic fees, fuel costs, handling costs, and overtime penalties »
All of this must first be thoroughly explained.
You wrote:
„The basic fee for vehicle departure refers to the depreciation and labor costs incurred due to the departure of the vehicle »
What do you mean by „fee”? You include in this „fee » « depreciation and labor costs » but this are fixed costs, which should be inclued in decisions of strategic character, when a transportation system is being designed. It seems that your trucks will be moving on the same route, so it quite specific situation, rare in practise, so again I’m asking for what kind of situations, for what kind of companies have you made your algorithm ?
My opinion is that I am probably dealing with engineers, experts in optimization methods, who focus on methodological aspects. I look at it from a practical point of view as a logistician, and the premise of “Applied Science” is that the solutions should be useful for practitioners. I have to understand the problem first before considering a tool to solve it. As such, I cannot endorse this article.
However, I fear that the authors did not take it seriously, as evidenced by the very modest introduction and conclusion with conclusions.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 2 Report
Comments and Suggestions for AuthorsThe article is original in addressing inefficiencies in LTL freight matching, a persistent challenge in logistics. The issue is well recognized, but the article offers a novel contribution by enhancing the SubChain Salp Swarm Algorithm with a subchain operation. This modification may improve both the search accuracy and speed of the algorithm, which is a crucial factor in optimizing freight matching efficiency.
The paper also contributes methodologically by validating the enhanced algorithm against eight benchmark functions, demonstrating its improved performance. This systematic evaluation strengthens the approach's credibility and underscores its broader applicability beyond logistics. Applying the improved SSSA in a simulation setting provides empirical evidence of its effectiveness in real-world freight matching scenarios.
The work may add value by bridging the gap between computational optimization and practical logistics challenges. Its key contributions lie in refining an established heuristic method and demonstrating its superiority through rigorous testing, making it a potentially significant development in the field of transportation logistics.
Certain weaknesses could be addressed to strengthen its contributions. One limitation is the lack of discussion on real-world implementation beyond simulations. Although the improved algorithm is tested on eight validation functions, the absence of real-world deployment or industry case studies leaves questions about its practical feasibility, scalability, and adaptability to dynamic logistics environments. A more compelling demonstration would include testing with actual freight data, considering unpredictable variables such as traffic patterns, shipment delays, and market fluctuations.
There is a concern about the potential computational complexity introduced by the subchain operation. While the study claims improved search accuracy and speed, there is little discussion on how the algorithm performs in large-scale, high-dimensional problems commonly encountered in logistics. Without an in-depth computational cost analysis, it remains unclear whether the trade-offs between efficiency gains and processing demands justify its practical adoption. Future research could explore comparative benchmarks against existing industry-standard algorithms to contextualize their performance in a more applied setting.
And, the problem of information asymmetry, mentioned as a core challenge in LTL freight matching, is not explicitly addressed beyond algorithmic improvements. The study could benefit from integrating external data sources, such as market demand forecasts or collaborative logistics platforms, to mitigate asymmetry issues more holistically. Addressing these aspects would not only enhance the study’s applicability but also provide a more comprehensive solution to the inefficiencies in freight matching.
The critical point resides at the conclusion: it fails to provide a meaningful synthesis of the study’s impact, offering only a broad and uncritical summary. It merely restates the methodology and results without engaging in a deeper discussion of the study’s significance, limitations, or real-world applicability. Vague claims such as "performs excellently" and "shows promising potential" lack concrete evidence or comparative analysis, making it difficult to assess the true effectiveness of the improved algorithm. While it briefly mentions real operational data, there is no indication of the dataset's scale, diversity, or relevance to industry challenges, raising concerns about the study’s generalizability. For a research in logistics optimization be truly valuable, it must contribute effectively to real-world applications, addressing practical constraints such as dynamic market conditions, computational feasibility, and integration with existing freight-matching systems. Without a clear discussion of these aspects, the study risks being an isolated theoretical exercise rather than a transformative contribution to the field. A more robust conclusion should critically reflect on both strengths and weaknesses, provide tangible evidence of practical impact, and outline future research directions to ensure its findings translate into meaningful improvements in transportation logistics.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 3 Report
Comments and Suggestions for AuthorsThere are comments to improve the paper:
- The abstract could give more concretisation on achieved results.
- Section 3 should start from research design. Please add text before the first sub-section starts.
- Section 4 should introduce the sub-sections that are placed under this section. Please add text before the first sub-section starts.
- Please, add text after the Table 3. It is recommended not to finish the sub-section with table or figure.
- Before the conclussions section the authors have to place discussion section.
- Under discussion section the authors what to show that research gaps are covered by their paper that existed previously in the literature.
- Conclussions are too short. Please add here statements about research limitation and future research directions.
- Sub-sections for 2.2 section are too short. Please, consider if they are mandatory in the paper as separate sub-sections or should it be the text of the same section. Some times there are just 2 sentences and formula under sub-section.
- Typos have to be solved such as particle swarm optimization(PSO) and Algorithm (SSA)[9].
- The authors could nunify citation, such as Zivkovic. et. al. [14] and Faris. et. al.[11]. Please, the first citation version.
The list of references should include the contemprary paper from year 2025. Please include them. Comments on methodology: The authors should provide a more detailed explanation of the subchain operation, including the rationale behind the selection strategy. Paper mentions the use of anonymized operational data from a highway freight transportation company. It is suggested to provide more detailed comparison of other real-world scenarios. The description of results could be strengthen if the authors could provide information about the validity of the results. The authors could demonstrate how the SubChain salp Swarm Algorithm (SSSA) performs with varying sizes of cargo and trucks. Such information would be useful for understanding the application of SSSA in different logistics environments.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
Comments and Suggestions for AuthorsThank you for answering my questions. The research problem is now more understandable, better explained in the Abstract, and the conclusions and summary have been developed. I just don't understand why the “Abstract” was changed to “Abstraction”? Good luck with your further research on this problem.
Reviewer 2 Report
Comments and Suggestions for AuthorsThe authors have addressed all the suggestions and feedback provided, articulating the contributions of the work. These revisions have improved the overall clarity and coherence of the text, making it more accessible and engaging for readers. The narrative now offers a well-structured discussion that highlights the practical implications of the study as well as its potential to inform future research. The improvements made not only strengthen the academic quality of the work but also increase its relevance for application.