Search

Internet of Vehicles, an emerging industry, is being gradually popularized and applied. This paper is to propose a new construction method to neural network ensembles that based on the key technology to multi-sensor data fusion of Internet of Vehicles system, which is an effective solution to the problems such as the information collection about vehicle traffic. Training a group of neural networks Independently, and then use discrete particle swarm optimization (PSO) algorithm and describe all possible neural network ensemble when the value of particles is 0 or 1 in multi-dimensional space. The estimated value to predict error of the network integration is expressed by correlation degree among individual networks that made up of integration, and it will be used as the fitness function during the optimization process. We will select the individual networks which has much differences among the parts that get involved in neural network ensemble.

Multidimensional Services meet the needs of user’s differences, while increase the complexity of service composition. Because of the problem of multidimensional services load balancing on the network, a mathematical model is established, which is based on a particle swarm optimization. And a algorithm is proposed in this paper, in which particle swarm optimization algorithm is applied to the network load balancing (PSOB). Based on loading conditions, the PSOB algorithm balances the load of network communication flows by adaptively adjusting services load on the network nodes. Compared to previous researches, PSOB not only is able to adjust load on the network overall to the balanced state in real time, but also prevails the whole effect and efficiency in the process of balancing. Through theoretical analysis, the scheme of PSOB application is illuminated and experimental results illustrate PSOB’s better balanced effect.

This paper describes importance that the application of economic data in the data mining algorithm and its application, which combines with the current economic data of national macro-economic indicators, presents the data warehouse model structure and its implementation characteristics, and uses SQL Server 2005 data warehouse and data mining solutions on economic data for the application of data mining solution, system architecture, algorithms implementation, and Anally discusses the application of data mining algorithms development trends and key technologies in the economic field.

With the workflow technology's gradual maturenient and development, it has brought a great deal of system's flexibility in their business processing, the multi-level interaction, the task allocation, information sharing, business statistics, and so on. Especially it can reduce the maintenance cost in the system maintenance and system upgrade, reduce the upgradeable period, and raise the working efficiency. However, when the enterprises and institutions introduces workflow management system, they often gets rid of the original or old information management system, develops a set of new software system, the development cost is relatively high. This paper proposed an implementation scheme on how to use the original system, and then upgrades seamlessly it to the flexible workflow management system that based on the workflow engine. Using OSWorkflow that has been used in industry widely to upgrade the original Java-based Web management system, it can reduce the software development workload and shorten the development period.