Monitoring Technologies for Truck Drivers: A Systematic Review of Safety and Driving Behavior

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

This paper systematically and comprehensively introduces and evaluates current technologies for monitoring truck drivers' driving behavior. It provides an in-depth analysis of the various components and types of monitoring systems, clearly highlighting the strengths and limitations of existing technologies. The study lays a solid foundation for enhancing the safety of truck drivers in the future. While the overall theme is clear and the content detailed, there are two aspects that could be improved:
1. The full name of Forward collision warning (FCW) has been clearly explained in line 243, and the full name of FCW is also placed in line 410. Please consider whether the full name of line 410 needs to be simplified to increase readability.
2. I noticed that you mentioned in line 66 and the conclusion that High implementation costs are still a major challenge for the commercial truck transportation field. Please consider explaining this appropriately in the limitations and future research to improve the applicability of various monitoring methods in future use.
3. Figure 1 does not seem to show the information about “44 duplicate records were removed”. It is recommended that the content of the figure be improved appropriately to facilitate readers’reading.
4. Most monitoring technologies rely on sensors and cameras, but these data may be distorted under different environmental conditions (such as weather and lighting); and the sample diversity is limited, making it difficult to adapt to the differences in driving behavior among different groups. It is recommended that the paper discuss the above viewpoints in more detail based on the small sample size.
5. In future research, it is suggested that we consider integrating multiple data sources (such as facial fatigue detection data, cockpit audio, etc.) and using adaptive algorithms such as deep learning to perform dynamic driving behavior analysis to more accurately identify risky behaviors and provide safety recommendations.

Author Response

Reviewer 1 – Comment 1:

“The full name of Forward collision warning (FCW) has been clearly explained in line 243, and the full name of FCW is also placed in line 410. Please consider whether the full name of line 410 needs to be simplified to increase readability.”

Response 1:

We thank the reviewer for this valuable suggestion. In response, we have revised the text in line 403 to remove the repeated full term “Forward Collision Warning,” retaining only the acronym “FCW” in order to enhance readability and avoid redundancy, given that the full term had already been clearly introduced earlier in the manuscript.

The revised sentence now reads:

“...which include features like FCW, Lane Departure Warning (LDW), Headway Monitoring and Warning (HMW), and Speed Limit Indicators (SLI), significantly influence driver behavior and safety outcomes.”

We trust that this change improves the clarity and conciseness of the manuscript, in accordance with the reviewer’s recommendation.

Reviewer 1 – Comment 2:

“I noticed that you mentioned in line 66 and the conclusion that high implementation costs are still a major challenge for the commercial truck transportation field. Please consider explaining this appropriately in the limitations and future research to improve the applicability of various monitoring methods in future use.”

Response 2:

We thank the reviewer for this thoughtful and constructive observation. In response, we have revised both the Strengths and Limitations (Section 4.2) and Future Research (Section 4.4) sections to address in greater detail the issue of high implementation costs associated with monitoring technologies.

In Section 4.2, we now discuss the financial constraints that may hinder the adoption of these technologies, particularly among small and medium-sized fleet operators. We highlight the challenges posed by initial investment requirements, integration costs, and long-term maintenance, and underscore the importance of developing cost-efficient, modular, and open-source solutions to support broader accessibility.

Furthermore, Section 4.4 has been expanded to recommend that future research prioritize the development of scalable and economically viable alternatives, such as the use of commercially available devices (e.g., smartphones or smartwatches) and cloud-based infrastructures. We also emphasize the importance of investigating policy mechanisms—including public-private partnerships, incentive programs, and collaborative implementation models—that may facilitate adoption in cost-sensitive settings.

We trust that these additions contribute to improving the practical applicability of the findings and align with the reviewer’s recommendation.

Reviewer 1 – Comment 3:

“Figure 1 does not seem to show the information about ‘44 duplicate records were removed’. It is recommended that the content of the figure be improved appropriately to facilitate readers’ reading.”

Response 3:

We thank the reviewer for this attentive observation. We would like to clarify that the information regarding the removal of 44 duplicate records was included in the original version of Figure 1. However, during the transfer of content into the journal submission template, this specific detail was inadvertently hidden. In accordance with the reviewer’s suggestion, we have updated the figure to ensure this information is now clearly visible and appropriately presented.

Reviewer 1 – Comment 4:

“Most monitoring technologies rely on sensors and cameras, but these data may be distorted under different environmental conditions (such as weather and lighting); and the sample diversity is limited, making it difficult to adapt to the differences in driving behavior among different groups. It is recommended that the paper discuss the above viewpoints in more detail based on the small sample size.”

Response 4:

We are grateful to the reviewer for this thoughtful comment. In response, we have revised Section 4.2 (Strengths and Limitations) to address both of the issues raised in greater detail.

Firstly, we have elaborated on the limitations associated with sensor- and camera-based monitoring technologies, noting that their performance may be compromised under adverse environmental conditions such as low lighting, glare, precipitation, and road surface variability. These factors can affect data quality and system reliability, underscoring the importance of developing robust and adaptable system designs, as well as validating performance across a range of real-world scenarios.

Secondly, we have strengthened our discussion of sample-related limitations by highlighting that, in addition to small sample sizes, a lack of demographic and contextual diversity—such as variation in age, gender, driving experience, cultural background, and geographical context—reduces the generalizability of study findings. We emphasize that systems developed using homogeneous samples may struggle to adapt to the diversity of driving behaviors encountered in broader operational environments. To address this, we recommend that future research prioritize the inclusion of heterogeneous populations and conduct cross-context validation studies.

We trust that these additions improve the depth and clarity of our critical assessment and align with the reviewer’s recommendation.

Reviewer 1 – Comment 5:

“In future research, it is suggested that we consider integrating multiple data sources (such as facial fatigue detection data, cockpit audio, etc.) and using adaptive algorithms such as deep learning to perform dynamic driving behavior analysis to more accurately identify risky behaviors and provide safety recommendations.”

Response 5:

We sincerely thank the reviewer for this valuable suggestion. In response, we have expanded Section 4.4 (Future Research) to acknowledge the importance of integrating multiple data sources—such as facial indicators of fatigue, cockpit audio, physiological signals, and vehicle telemetry—as a means of enhancing the accuracy and contextual relevance of driver behavior analysis.

We have also incorporated the recommendation to explore adaptive learning approaches, including deep learning techniques, which offer strong potential for dynamically capturing complex behavioral patterns and providing real-time risk detection and safety feedback. These advanced methods can support the development of more responsive and individualized monitoring systems, thereby improving both predictive accuracy and driver acceptance.

We believe this addition strengthens the forward-looking scope of the manuscript and aligns well with current research directions in intelligent driver monitoring systems.

Reviewer 2 Report

Comments and Suggestions for Authors

The presented topic is related to the problem of reducing the number of accidents on the roads. This is an important problem.

As the authors point out, the choice and application of the verification methodology is important for its demonstration. The authors presented this in the form of research questions. This should be considered as the right approach and correct application of research methodology.

The tests carried out were properly conducted and documented. The research cycle has been comprehensively presented. In particular, the presented appendix precisely characterizes the scope of the conducted research, the procedure guidelines and indicates the level of detail of the analyses performed.

I would suggest linking the discussion more closely to the research results and outcomes obtained.

The literature has been selected correctly. Its scope is sufficient.

Author Response

Reviewer 2 – Comment:

“I would suggest linking the discussion more closely to the research results and outcomes obtained.”

Response:

We thank the reviewer for their thoughtful and encouraging feedback regarding the relevance of the topic, the clarity of the research questions, the appropriateness of the methodological approach, and the structure of the research process and supporting materials.

In response to the suggestion to strengthen the connection between the discussion and the results, we have substantially revised Section 4.1 (Key Findings). The updated section now integrates direct references to the specific outcomes reported in Section 3, including the performance and limitations of different categories of monitoring technologies (e.g., wearable devices, in-vehicle systems, ADAS, data loggers, and connected vehicle technologies), as well as the scope of monitored variables. These revisions ensure that the discussion is more explicitly grounded in the evidence presented and highlight how the findings relate to the stated research objectives.

We believe this revision improves the logical cohesion between the results and discussion sections and aligns closely with the reviewer’s recommendation.