A state-space model was established for the short-term traffic flow prediction problem under complex road conditions, which is based on macroscopic traffic flow forecasting. In order to solve the problem of parameter optimization on the dynamic traffic forecast model, a method to improve the performance of Unscented Kalman Filter (UKF) with orthogonal adaptive Differential Evolution (DE) was proposed. The orthogonal method maximized the diversity of the initial population in DE algorithm. The crossover operator in DE was optimized by the orthogonal method and the technology of quantification to balance the exploitation and exploration, which was more beneficial to find the model parameters of UKF. The experimental results show that, with respect to use random distribution to initialize the parameters, or set model parameters based on the experience, the use of orthogonal design method for initialization strategy, mutation operator and adaptive control strategy of parameters in differential evolution algorithm can effectively save computing resources, improve forecasting performance and accuracy, and provide better robustness.

In P2P network with two layers,intergroup replication scatters media contents into groups so as to improve the efficiency of media content delivery between the group where a request is issued and the group where the content is stored,and intragroup replication copies media contents into peers for improving the availability of the content.Simulation result show that the latency in P2P based on the architecture is 20% less than that of the FreeNet and 50% less than that of the randomly replication system.Simulation results also show that the video quality in the system is much better than that in the other two systems.The P2P-based approach is distributed,scalable,cost effective.

Simulated annealing genetic algorithm was improved and used in association rule mining. A new association rule mining algorithm based on improved simulated annealing genetic algorithm was presented. This algorithm used adaptive crossover probability and mutation probability, and restrained premature convergence effectively. Experiment results demonstrate that this method can solve association rule mining effectively.

Based on the concept of biotic community in Biology, a 3-layer model named community-population-individual was proposed. Meanwhile, a parallel genetic algorithm based on learning mechanism (PGABL) was developed on this model. As the data structure for collaborations between subpopulations, the Blackboard model was introduced. And three learning operators are designed, through which PGABL combines the advantages of genetic evolution and genetic learning that improves the performance of traditional genetic algorithm effectively. Experimental results show that PGABL is of good adaptability and stability.