A Hybrid Neuro-Genetic Approach to Short-Term Traffic Volume Prediction

This paper presents a hybrid approach to developing a short-term traffic [low prediction model. in thisapproach a primary model is synthesized based on neural networks and then the model structure is optimized throughgenetic algorithm. the proposed approach is applied to a rural highway, ghazvin-rasht road in iran. the obtainedresults are acceptable and indicate that the proposed approach can improve model accuracy while reducing modelstructure complexity. minimum achieved prediction r2 is 0.73 and number of connection links at least reduced 20o/cas a result of optimization.