基于量子神经网络的道路交通事故预测

Road traffic accidents forecasting is one of the key issues of the road traffic safety. A new forecasting model based on quantum neural network (QNN) is proposed to solve the problems of precision inadequacy and low convergence rate of BP neural network in road traffic accidents forecasting. The numbers of the training samples are enlarged by phase-space reconstruction of the road traffic accidents time series. The activation function of model superposition is used in the hidden-layer neurons to partition the feature space of road traffic accidents data into multi-layer rundles. Both the matching speed of the input data and feature space and the convergence rate of model are improved. The quantum interval is adjusted dynamically in the training process to adapt the strong randomness. The results show that the QNN model adapt the characteristics of road traffic accidents data well, and its prediction accuracy and convergence rate are superior to that of improved BP neural network.