Network Fault Diagnosis Using Hierarchical SVMs Based on Kernel Method

Abstract

A new method based on kernel which can measure class separability in feature space is proposed in this paper for existing error accumulation when the Hierarchical SVMs is used to diagnose multi-class network fault. This method has defined metrics of sample distribution in feature space, which are used as the rule of constructing Hierarchical SVMs. Experiment results show that this method can restrain error accumulation and has higher multi-class classification accuracy, and offer an effective way for Network fault diagnosis.