Earticle

초록

영어

Because the properties of data are becoming more and more complex, the traditional data classification is difficult to realize the data classification according to the complexity characteristic of the data. Support vector machine is a machine learning method with the good generalization ability and prediction accuracy. So an improved ant colony optimization(ACO) algorithm is introduced into the support vector machine(SVM) model in order to propose a new data classification(ERURACO-SVM) method. In the ERURACO-SVM method, the pheromone evaporation rate strategy and pheromone updating rule are introduced into the ACO algorithm to improve the optimization performance of the ACO algorithm, and then the parallelism, global optimization ability, positive feedback mechanism and strong robustness of the improved ACO algorithm is used to find the optimal combination of parameters of the SVM model in order to improve the learning performance and generalization ability of the SVM model and establish the optimal data classification model. Finally, the experimental data from the UCI machine learning database are selected to validate the classification correctness of the ERURACO-SVM method. The experiment results show that the improved ACO(ERURACO) algorithm has better optimization performance for parameters selection of the SVM model and the ERURACO-SVM method has higher classification accuracy and better generalization ability.

목차

Abstract
 1. Introduction
 2. Ant Colony Optimization (ACO) Algorithm
 3. The Strategies for Improved ACO Algorithm
  3.1. The Improved Pheromone Updating Rule
  3.2. The Dynamic Evaporation Coefficient Strategy
 4. Support Vector Machine (SVM) Mode
 5. Parameter Optimization Model of SVM based on Improved ACO
 6. Experimental Results and Conclusions
 7. Conclusion
 References

키워드

저자

• Hongpeng Zhu [ Shaoyang University, Shaoyang 422000 China ]
• Xiaohong Li [ Shaoyang Medical College, Shaoyang 422000 China ] Corresponding author

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Database Theory and Application

• 간기

  격월간

• pISSN

  2005-4270

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605