Data fusion-based traffic prediction and software decision support for recreational suburban roads
Clinical Snapshot
PICO Framework
| P — Population | Traffic flow data from Kandovan Road (mountainous suburban route) from 2017-2023 |
| I — Intervention | Eight machine learning and deep learning models for traffic prediction using data fusion approach |
| C — Comparator | Comparison between different ML/DL models (Deep LSTM, Random Forest, XGBRegressor, Transformer, ST-ResNet, Conv-LSTM, Bidirectional LSTM, LSTM-GAN) |
| O — Outcomes | Traffic prediction accuracy measured by MAE, RMSE, MSE, MAPE metrics and R² scores |
Bottom Line
This computational study evaluated eight machine learning models for predicting traffic flow on a mountainous suburban road in Iran, finding Random Forest Regressor performed best with R² = 0.88. While the data fusion approach incorporating weather and event data shows promise for improving traffic prediction accuracy, the single-site design limits generalizability. The development of accompanying decision-support software enhances practical utility. However, the study lacks statistical rigor with no confidence intervals or significance testing reported. For Australian applications, the methodology could be valuable but would require validation with local data and conditions. Transportation planners should consider this as preliminary evidence supporting multi-source data integration for traffic prediction, but implementation would need careful adaptation to local contexts and thorough validation before operational deployment.
Key Findings
P Value: Not reported
Effect Size: Random Forest Regressor achieved highest accuracy with R² = 0.88
Primary Outcome: Traffic prediction accuracy across eight ML/DL models
Nnt Or Sensitivity: MAE, RMSE, MSE, and MAPE metrics reported but specific values not provided in abstract
Confidence Interval: Not reported
Clinical Application
Requires significant computational resources and multi-source data integration; software development component enhances practical applicability Limited direct applicability due to different geographic, climatic, and traffic conditions; methodology could be adapted for Australian recreational roads with local data Traffic management authorities and transportation planners dealing with recreational/suburban roads
Abstract
Predicting traffic flow on mountainous suburban roads is challenging due to highly variable environmental, temporal, and traffic-related conditions. This study focuses on Kandovan Road, a critical route with complex behavioral patterns influenced by weather conditions, calendar events, and road-specific characteristics. To improve forecasting accuracy, eight machine learning and deep learning models were implemented, including Deep LSTM, Random Forest Regressor, XGBRegressor, Transformer, ST-ResNet, Conv-LSTM, Bidirectional LSTM, and LSTM-GAN. The models were trained and evaluated using traffic, weather, and event datasets from 2017 to 2023, with performance measured through MAE, RMSE, MSE, and MAPE metrics. Among the evaluated models, the Random Forest Regressor achieved the highest accuracy with an R² score of 0.88 and a low average error. This result demonstrates its strong ability to model non-linear and dynamic traffic patterns. The results indicate that integrating diverse data sources significantly enhances traffic prediction performance on mountain roads. Additionally, a dedicated traffic forecasting software system was developed to visualize real-time predictions and provide an operational decision-support tool for traffic authorities. The outcomes of this work support more efficient traffic management, improved road safety, and sustainable transportation planning in challenging terrains.
References
- 1.Afandizadeh, S., Abdolahi, S., & Mirzahossein, H. (2026). Data fusion-based traffic prediction and software decision support for recreational suburban roads. PLoS One. https://doi.org/10.1371/journal.pone.0343224
This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service