Papers by Author: Ai Ming Huang

Abstract: Many network application technology need the algorithm for multi-dimensional packet classification, for example ,network security ,load balancing ,router policy, QoS etc. Considering the levels of multiattribute packet classified are excessive and traverse rule table times without number for matching classification rule, so efficiency is lower. A packet classification algorithm based on decision tree is put forward in the paper. As compared with some traditional packet classification matching algorithms, because three data are adopted including information gain, information gain ratio and Gini to solve attribute selection measurement, accuracy and matching efficiency are both advanced obviously.

Abstract: In recent years, biometrics has become one of the most promising identity verification technologies. For the limitations, it is difficult for single mode biometrics to meet requirements of modern identity verification. The paper introduced several common biometrics verification methods and procedures. The limitations of single mode biometrics were also provided and data fusion technology was introduced to solve the problem. On the basis of this, Particle Swarm Optimization (PSO) neural network algorithm was used to construct multi biometrics verification system. The results of experiment based on the method shows that it can achieve better identity verification result and meet requirements of practical applications.