Multi-stage Multi-objective Evolving SVMs Ensemble Using NSGA-II

摘要：

In this paper, the algorithm design of the support vector machines (SVMs) ensemble in a practical multi-stage framework is analyzed which can be implemented efficiently by evolutionary multiobjective optimization algorithm. The designing of SVMs ensemble is considered in three stages: first, the bootstrap method and a strategy of dynamical parameter range adjustment are used to generate more diverse base SVMs, and the NSGA-II algorithm which can efficiently tune the parameters of SVMs is applied to ensure the accuracy of base SVMs;Second, the NSGA-II algorithm is used again to select the member of ensemble based on the accuracy and diversity of the ensemble we have measured;Last, the reliability of different class is computed and combined to decide the outputs of ensemble in terms of the decision values of base SVMs. The proposed algorithm is applied to the UCI datasets, some useful results has been concluded for the future work in this field.

关键词： support vector machines ensemble learning Genetic algorithm(Gas) NSGA-II

作者: YANG Lei XIAO Huai-Tie

作者单位: ATR key Lab National University of Defense Technology Changsha,China

会议类型: 国际会议

会议名称: 2010 IEEE International Conference on Intelligent Computing and Intelligent Systems(2010 IEEE 智能计算与智能系统国际会议 ICIS 2010)

会议地点: 厦门

会议语种:英文

页码: 856-860

在线出版日期: 2010-10-29（万方平台首次上网日期，不代表论文的发表时间）