The management of traffic congestion on public roads is a critical factor in economic growth. Congestion has a significant impact on travel time, causing delays that cost billions of dollars in extra travel hours and fuel consumption. Neural network techniques are considered promising solutions for such problems. In this paper, we propose a new prediction system to solve the traffic congestion problem using two artificial neural network methods: Forward Feedback Neural Network (FFNN) and Radial Basis Function Neural Network (RBFNN). Our prediction system depends on the following input parameters: month, day, time, rain, and holiday. The results show that the FFNN model performs better than the RBFNN with low Root Mean Square Error of Cross Value (RMSECV) and Relative Error of Prediction (REP), and high Pearson's (R2).
Road Traffic Prediction based on Feed Forward and Radial Basis Function Neural Network
16.11.2022
382595 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
The Prediction Model of Macro-Road Traffic Accident Basing on Radial Basis Function
Trans Tech Publications | 2011
|The Prediction Model of Macro-Road Traffic Accident Basing on Radial Basis Function
British Library Conference Proceedings | 2011
|A Radial Basis Function Neural Network Approach to Traffic Flow Forecasting
British Library Conference Proceedings | 2003
|