An approach for dynamic weighting ensemble classifiers based on cross-validation

作者：Zhu Yuquan^*; Ou Jishun; Chen Geng; Yu Haiping

来源：Journal of Computational Information Systems, 2010, 6(1): 297-305.

• Base classifiers
• Classification cross-validation
• Classification performance
• Component classifiers
• Cross validation
• Cross-validation technique
• Data sets
• Dynamic ensemble
• Ensemble classifiers
• Ensemble learning
• Generalization ability
• Multiple classifier fusion
• Training sample
• Training sets

Dynamic ensemble learning methods explore the use of different classifiers for different samples, therefore, may get better generalization ability than static ensemble learning methods. However, for most of dynamic approaches based on KNN rule, it needs to take out additional part of training samples to estimate "local classification performance" of each base classifier. When the number of training samples is not sufficient enough, it would lead to the unreliableness of estimating local performances of base classifiers, so further hurt the integrated performance. This paper presents a new dynamic ensemble model which introduces cross-validation technique in the process of evaluation to dynamically assign a weight to each component classifier. The introduction of cross-validation reduced the risk brought by the shortage of training samples. Experiments on 6 UCI data sets show that when the size of training set is not large enough, the proposed method can achieve better performance compared with some dynamic ensemble methods as well as some classical static ensemble approaches.

• 出版日期2010