面对类别不平衡的增量在线序列极限学习机

Incremental online sequential extreme learning machine for imbalanced data

针对在线序列极限学习机对于类别不平衡数据的学习效率低、分类准确率差的问题,提出了面对类别不平衡的增量在线序列极限学习机(IOS-ELM)。该算法根据类别不平衡比例调整平衡因子,利用分块矩阵的广义逆矩阵对隐含层节点数进行寻优,提高了模型对类别不平衡数据的在线处理能力,最后通过14个二类和多类不平衡数据集对该算法有效性和可行性进行验证。实验结果表明:该算法与同类其他算法相比具有更好的泛化性和准确率,适用于类别不平衡场景下的在线学习。

In this paper,an incremental online sequential extreme learning machine(IOS-ELM)is proposed to solve the problems of low efficiency and poor classification accuracy of OS-ELM for class imbalance learning.The basic idea is to adjust the balance factor according to the category imbalance ratio in an imbalanced dataset and then determine an optimal number of hidden nodes using the generalized inverse of the block matrix,thereby improving the online learning ability of IOS-ELM.The experiments on the effectiveness and feasibility of 14 binary-class and multi-class imbalanced datasets show that the proposed IOS-ELM has better generalization capability and classification performance than other comparative methods.