Earticle

초록

영어

This paper proposes an effective ensemble classifier, named PCAenSVM, which consists of ten weak Support Vector Machine classifiers based on different Principal Component Analysis thresholds. Those ten base Support Vector Machine classifiers are made up to fulfill classification tasks using Majority Voting strategy. Experiments are made on four UCI data sets and a data set from the Uppsala University to evaluate the performances of PCAenSVM. The results of PCAenSVM are compared with that of LibSVM and EnsembleSVM. Experimental results show that PCAenSVM has better classification accuracy than other two algorithms. Moreover, PCAenSVM has the same confidence level with the LibSVM, and its confidences of accuracy and sensitivity on those five data sets outperform that of the EnsembleSVM.

목차

Abstract
 1. Introduction
 2. Principal Component Analysis
 3. Support Vector Machine Classification
 4. Ensemble of Classifiers
 5. Ensemble SVC on different thresholds of PCA
 6. Experiments and Analysis
 7. Conclusion
 Acknowledgement
 References

키워드

저자

• Yukai Yao [ College of Computer and Communication, Lanzhou University of Technology, 247 Lan’gongping Road, Lanzhou 730050, China ]
• Bo Wang [ School of Information Science & Engineering, Lanzhou University, 222 South Tianshui Road, Lanzhou 730000, China ]
• Qingjun Yang [ School of Information Science & Engineering, Lanzhou University, 222 South Tianshui Road, Lanzhou 730000, China, Qinghai Province Meteorological Bureau, 19 Wusi Road, Xi’ning, China. ]
• Dongsheng Ji [ School of Information Science & Engineering, Lanzhou University, 222 South Tianshui Road, Lanzhou 730000, China ]
• Tao Ma [ School of Information Science & Engineering, Lanzhou University, 222 South Tianshui Road, Lanzhou 730000, China ]
• Xiaoyun Chen [ School of Information Science & Engineering, Lanzhou University, 222 South Tianshui Road, Lanzhou 730000, China ]

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