Empirical study of daily link traffic volume forecasting based on a deep neural network
These videos have been matched automatically. Contact us if they are not relevant.
These videos have been matched automatically. Contact us if they are not relevant.
View abstract on PubMed
Summary
This summary is machine-generated.This study presents a cost-effective deep neural network model to forecast daily link traffic volume, offering a viable alternative to expensive commercial software for transportation planning.
Area Of Science
- Transportation Engineering
- Data Science
- Artificial Intelligence
Background
- Accurate daily link traffic volume forecasting is crucial for transportation facility planning and demand analysis.
- High costs of commercial transport planning software limit its accessibility in developing countries.
- A need exists for affordable, data-driven methodologies for traffic volume prediction.
Purpose Of The Study
- To develop a cost-effective, data-driven methodology for forecasting daily link traffic volume.
- To utilize deep neural networks for traffic assignment modeling and volume prediction.
- To provide an alternative to commercial software for transportation planning.
Main Methods
- A data-driven approach using deep neural networks (specifically a multi-layer perception model) was employed.
- The model integrates traffic network attributes (lanes, speed, capacity, type) and network flow attributes (shortest paths, O-D demand).
- Nonlinear relationships between link traffic volume and these attributes were captured.
Main Results
- The proposed deep neural network model demonstrated comparable performance to commercial software in long-term link traffic volume forecasting.
- The model effectively captured the complex, nonlinear associations between traffic volume and network characteristics.
- Case study validation confirmed the method's accuracy and potential.
Conclusions
- The developed deep neural network approach offers a promising, cost-effective alternative to commercial transport planning software.
- This methodology can enhance traffic demand analysis and feasibility studies, particularly in resource-constrained regions.
- Further research is recommended to validate and refine the model for broader application.
These videos have been matched automatically. Contact us if they are not relevant.
These videos have been matched automatically. Contact us if they are not relevant.
Related Concept Videos
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.
The cephalic phase is a conditioned or learned response to familiar foods. Our appetite or desire for a particular food modifies the preparatory responses directed by the brain. Individuals may produce more saliva and stomach...