A novel neuro-cognitive approach to modeling traffic control and flow based on fuzzy neural techniques

Abstract

In many developed and developing countries, efficient monitoring and controlling of the city’s traffic have become major challenges. Conventional traffic light control methods, Preset Cycle Timing and Preset Cycle Timing with proximity sensors used today are neither sufficiently efficient nor effective to manage different traffic conditions. One solution is to employ a human operator. Unfortunately this method is expensive and error-prone due to lapse in concentration and other factors. Another alternative is to introduce an intelligent controller using fuzzy neural learning memory techniques, which have the capability to mimic human intelligence in controlling the frequency of traffic light changes at a junction. The performances of four suitable soft-computing architectures are investigated in this study as a possible platform to model and develop an intelligent traffic light control regime. These neural fuzzy learning structures construct memories that possess the intelligence and capabilities of a human operator in monitoring and managing the traffic at road intersections under different traffic scenarios. An open source traffic light simulator, Green Light District, is used to create and simulate different traffic conditions at (i) a simple traffic light intersection and (ii) a complex traffic light intersection. Traffic data generated by the simulator under the control of a human operator is then used as inputs for the training and testing of four fuzzy neural network architectures. The four architectures are Generic Self-organizing Fuzzy Neural Network (GenSoFNN), Pseudo Outer Product based Fuzzy Neural Network (POPFNN), Fuzzy Adaptive Learning Control Network (Falcon) and Multilayer Perceptrons (MLP). The performance of each of the neural network architectures was found to be promising from the simulation results derived for both simple and complex traffic light intersections. Performance was based on the mean classified rate, mean training time, mean number of rules, and standard deviation of the classified rate across the traffic conditions simulated. A technique from each of the architectures with the best results is subsequently selected for more in-depth study on its performance in a complex traffic light intersection. Although all the selected techniques from the four architectures suffered a decline in performance in the complex traffic light intersection; architectures such as GenSoFNN and Falcon continue to produce good results. The POPFNN architecture generated a large number of rules and the MLP architecture produced poor classified rates. This work has demonstrated that it is highly feasible to develop neuro-cognitive traffic control regime that can mimic the behaviors of a human operator.