Comparison of probabilistic neural network with multilayer perceptron and support vector machine for detecting traffic incident on expressway based on simulation data

This research focuses on comparing probabilistic neural network with multilayer perceptron and support vector machine for detecting traffic incident on expressway based on simulation data. The data used in this experiment contains speed, density, occupancy, traffic flow, and time headway at specific location on expressway, as well as both upstream and downstream detectors. These data are generated by using the traffic modelling software, AIMSUN. Four indicators are used in evaluating the model's performance which are detection rate, false alarm rate, mean time to detect, and classification rate. The result of these three models is not much different. These three models can mostly detect traffic incident and greatly classify between non-incident and incident situation. These model's accuracy are more than 95 percent in training data and more than 75 percent in validating data.