改进人工蜂群优化的极限学习机

Extreme learning machine optimized by improved ABC

针对极限学习机(ELM)在训练过程中需要大量隐含层节点的问题,提出了差分进化与克隆算法改进人工蜂群优化的极限学习机(DECABC-ELM),在人工蜂群算法的基础上,引入了差分进化算法的差分变异算子和免疫克隆算法的克隆扩增算子,改进了人工蜂群收敛速度慢等缺点,使用改进的人工蜂群算法计算ELM的隐含层节点参数。将算法应用于回归和分类数据集,并与其他算法进行比较,获得了良好的效果。

Aiming at problem that extreme learning machine（ELM） needs numerous hidden layer nodes in training process,a new improved differential evolution and clone artificial bee colony（ABC） optimized extreme learning machine（DECABC-ELM） is proposed. In DECABC-ELM,differential evolution mutation operator of differential evolution algorithm and clone-increase operator of immune clonal algorithm are introduced into ABC algorithm to improve the slow convergence speed of it,then the improved ABC is used to calculate the hidden layer node parameters of ELM.DECABC-ELM are used in regression and classification data set and compare with other algorithms,it shows that DECABC-ELM performs better than other algorithms.