Sustainable Urban Mobility for Road Information Discovery-Based Cloud Collaboration and Gaussian Processes
, Hassen Louati 2, Elham Kariri 1, Wafa Neifar 3, Mohammed A. Farahat 4, Heba M. El-Hoseny 4, Mohamed K. Hassan 5 and Mutaz H. H. Khairi 6Round 1
Reviewer 1 Report
Comments and Suggestions for AuthorsThis article proposes a novel cloud-based collaborative framework for road information estimation that leverages a fleet of priority vehicles (PVs). The goal is to advance sustainable urban mobility through improved traffic management. The framework integrates Kalman filtering and Gaussian process regression techniques for crowdsourcing road data from PVs.
The article makes an important contribution to the development of sustainable transportation systems. Leveraging real-time data from vehicles has great potential to optimize traffic flow and reduce emissions. The integrated use of Kalman filtering and Gaussian processes is a promising approach to enhance estimation accuracy. However, some aspects of the work could be strengthened:
The system design and assumptions could be described in more detail. For example, clarifying the types of sensors on PVs, communication protocols, cloud architecture, and how pseudomeasurements are generated.
The discussion of integrating the framework with physical hardware like an active suspension testbed is promising but lacks specifics.
The sustainability goals are indicated but specific metrics to quantify environmental impacts, like emissions reduction or energy efficiency, are not provided.
The simulation results focus on estimation accuracy metrics like RMSE. Expanding the validation to include sustainability metrics would better demonstrate the environmental benefits. Comparisons to existing methods using sustainability indicators would also affirm the value added.
Overall, while the collaborative estimation methodology shows promise for sustainable mobility, Addressing the mentioned aspects would significantly strengthen the manuscript and widen its appeal for sustainable transportation research.
Author Response
Special thanks to the referee for the time and effort spent to evaluate the article. A detailed letter is provided for the reviewer addressing each comment. In the revised version, the modifications suggested by reviewers are highlighted in blue.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
Comments and Suggestions for AuthorsThis paper proposes a cloud-based collaborative system for road information discovery, using KF and GP. Although the author claims that this work demonstrated a significant improvement, the simulation results are not strong with many details missed.
The suggestions are stated as follows:
1. After figure 1, Please add some introduction for the PVs in the general perspective.
2. In section “modelling and presumptions”, it is not clear what are the states of the KF.
3. L226, what is the definition of “minimum mean square error”?
4. L281, what is the definition of “road distance”?
5. L319, reference failed(??).
6. Section 5.2, what is the simulation environment? Any software used? What is the simulation time and computational resource cost?
7. Section 5.3.1. Is this RMSE a weighted sum of many factors? Please provide more details.
8. For figure 6 and 7, what is the exact definition and calculation method of “road information of interest”?
9. L351-354, please add the percentage of variance reduction.
Comments on the Quality of English Language
the Quality of English is good.
Author Response
Special thanks to the reviewer for the time and effort spent to evaluate the article. A detailed letter is provided for the reviewer addressing each comment. In the revised version, the modifications suggested by reviewers are highlighted in blue.
Author Response File: Author Response.pdf
Round 2
Reviewer 2 Report
Comments and Suggestions for AuthorsThank you for the revision.
The quality of paper looks good to me now.
