Earticle

초록

영어

IRIS flower data is a class of multi variable data set, which is widely applied in data classification. This paper aims at the parameter optimization problem of least squares support vector machine (LS-SVM) in data classification, an improved particle swarm optimization(IMPSO) algorithm is introduced into the LS-SVM model for improving the learning performance and generalization ability of LS-SVM model. A new data classification method based on IMPSO algorithm and LS-SVM (IMPSO-LS-SVM) model is proposed. First, the numbers of current iteration and population are added into the control strategy of adaptive adjustment inertia weight in order to improve the performance of inertia weight of PSO algorithm. Then the IMPSO algorithm is used to search the optimal combination values of the parameters of kernel function for obtaining the IMPSO-LS-SVM. Finally, the training samples are used to comprehensively train the IMPSO-LS-SVM, and the best large-scale data classification model is constructed. The IRIS flower data is used to validate the effectiveness of the IMPSO-LS-SVM model. The result indicates that the IMPSO algorithm can effectively search the optimal combination values of the parameters, and the proposed data classification model has better generalization performance, faster training speed and higher classification precision.

목차

Abstract
 1. Introduction
 2. PSO Algorithm and LS-SVM Model
  2.1. PSO Algorithm
  2.2. LS-SVM Model
 3. IMPSO-LS-SVM Classification Model
  3.1. Improve Inertia Weight
  3.2. LS-SVM Classification Model based on Improved PSO (IMPSO-LS-SVM) Algorithm
 4. Experimental Results and Analysis
 5. Conclusion
 References

키워드

저자

• Chong Wu [ Shan Dong Institute of Pomology, Taian 271000 China ]
• Chonglu Zhong [ Research institute of tropical forestry Chinese academy of forestry, Guangzhou 510520 China ]
• Yanlei Yin [ Shan Dong Institute of Pomology, Taian 271000 China ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Hybrid Information Technology

• 간기

  격월간

• pISSN

  1738-9968

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605