期刊名称：International Journal of Computer Science & Information Technology (IJCSIT)
印刷版ISSN：0975-4660
电子版ISSN：0975-3826
出版年度：2015
卷号：7
期号：2
页码：183
出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：Short term traffic forecasting has been a very important consideration in many areas of transportationresearch for more than 3 decades. Short-term traffic forecasting based on data driven methods is one of themost dynamic and developing research arenas with enormous published literature. In order to improveforecasting model accuracy of wavelet neural network, an adaptive particle swarm optimization algorithmbased on cloud theory was proposed, not only to help improve search performance, but also speed upindividual optimizing ability. And the inertia weight adaptively changes depending on X-conditional cloudgenerator which has the stable tendency and randomness property .Then the adaptive particle swarmoptimization algorithm based on cloud theory was used to optimize the weights and thresholds of waveletBP neural network, Instead of traditional gradient descent method . At last, wavelet BP neural network wastrained to search for the optimal solution. Based on above theory, an improved wavelet neural networkmodel based on modified particle swarm optimization algorithm was proposed and the availability of themodified prediction method was proved by predicting the time series of real traffic flow. At last, thecomputer simulations have shown that the nonlinear fitting and accuracy of the modified predictionmethods are better than other prediction methods.
