Network Traffic Prediction Model Considering Road Traffic Parameters Using Artificial Intelligence Methods in VANET

Approved

Relevance and Originality

The research addresses a pressing issue in the field of intelligent transportation systems, specifically the prediction of network traffic in VANETs. Given the increasing reliance on connected vehicles and the complexity of traffic management, the study's focus is both relevant and timely. The originality of the paper is evident in its hybrid approach, integrating Random Forest and Gated Recurrent Units (GRU) to enhance traffic prediction accuracy. This combination of machine learning and deep learning techniques reflects an innovative approach to tackling challenges in vehicular networking.

Methodology

The methodology outlined in the paper is well-structured, comprising three distinct phases that methodically address traffic prediction from various perspectives (V2R, V2V, and combined). The use of Random Forest for feature selection followed by GRU for prediction is a robust choice, as it leverages the strengths of both algorithms. However, the article would benefit from a more detailed description of the dataset used, including its size, sources, and how it was preprocessed. Additionally, a clearer explanation of the criteria for feature selection would strengthen the methodology section.

Validity & Reliability

The validity of the findings is supported by the reported simulation results, which indicate superior performance of the RF-GRU-NTP model in terms of execution time and prediction errors compared to other algorithms. This suggests that the model is both effective and efficient. To enhance reliability, it would be beneficial for the authors to describe the validation techniques used, such as k-fold cross-validation or separate training and testing datasets. Discussing any potential biases or limitations in the dataset would also provide a more comprehensive view of the results.

Clarity and Structure

The article is generally well-structured, guiding the reader through the rationale, methodology, and findings clearly. However, some sections could be improved for clarity. For example, the descriptions of the V2V and V2R communications might benefit from more contextual information to aid understanding. Additionally, the writing style could be more concise in certain areas, reducing redundancy while maintaining the necessary detail. Including diagrams or flowcharts to visualize the model architecture and data flow could enhance comprehension.

Result Analysis

The result analysis effectively demonstrates the advantages of the proposed RF-GRU-NTP model, showcasing its improved performance metrics. The authors present their findings in a clear manner, highlighting key performance indicators. However, further discussion on the practical implications of these results would enhance the analysis. For instance, the potential impact of improved traffic predictions on real-world applications, such as traffic management systems or vehicle routing, could be elaborated upon. Additionally, addressing the limitations of the study and suggesting areas for future research would provide valuable insights for both academia and industry.