A dynamic classifier ensemble selection approach for noise data

作者：Xiao Jin; He Changzheng^*; Jiang Xiaoyi; Liu Dunhu

来源：Information Sciences, 2010, 180(18): 3402-3421.

DOI：10.1016/j.ins.2010.05.021

• Multiple classifier systems
• GMDH
• Dynamic ensemble selection
• Noise-immunity ability

Dynamic classifier ensemble selection (DCES) plays a strategic role in the field of multiple classifier systems. The real data to be classified often include a large amount of noise, so it is important to study the noise-immunity ability of various DCES strategies. This paper introduces a group method of data handling (GMDH) to DCES, and proposes a novel dynamic classifier ensemble selection strategy GDES-AD. It considers both accuracy and diversity in the process of ensemble selection. We experimentally test GDES-AD and six other ensemble strategies over 30 UCI data sets in three cases: the data sets do not include artificial noise, include class noise, and include attribute noise. Statistical analysis results show that GDES-AD has stronger noise-immunity ability than other strategies. In addition, we find out that Random Subspace is more suitable for GDES-AD compared with Bagging. Further, the bias-variance decomposition experiments for the classification errors of various strategies show that the stronger noise-immunity ability of GOES-AD is mainly due to the fact that it can reduce the bias in classification error better.

• 出版日期2010-9-15
• 单位成都信息工程大学; 四川大学