| With the improvement of economic development and urbanization,transportation has become the lifeblood of the national economy.The current urban traffic also has different degrees of congestion,which also leads to a decrease in the speed of vehicles in the traffic network,increasing the queue time of the vehicles and increasing the travel cost of people.The use of intelligent data systems based on computer data processing plays an important role in urban traffic management,providing scientific theoretical guidance and technical support for traffic managelent decisions.The key to intelligent transportation systems is traffic guidance and traffic control.The premise of traffic guidance is to predict the traffic conditions of the road.By establishing a short-term traffic flow prediction model with high applicability and accuracy,this paper can help the relevant departments to improve traffic in the region by predicting the traffic flow in the future.In summary,this paper combines chaos theory,wavelet neural network and flock algorithm to conduct in-depth research on short-term traffic flow forecasting and forecasting.The main work is as follows:(1)In order to improve the convergence speed of the algorithm and the accuracy of the prediction result,the wavelet noise reduction processing is performed on the repaired data.The C-C method is used to calculate the two factors of time delay ? and embedding dimension m.The Lyapunov exponent is calculated by the small data method.According to the index greater than zero,the traffic flow data has chaotic characteristics and meets the premise of short-term traffic flow prediction.(2)Propose a short-term traffic flow prediction model using wavelet neural network.The improved flock algorithm is used to optimize the weights and translational scaling factors of wavelet neural network,and a short-term traffic flow prediction model based on improved flock algorithm is constructed.Finally,an empirical study was conducted. |
PDF Full Text Request