Adaptive Distance-Based Voting Classification
Chun-Hua Hung, Shie-Jue Lee · 2013
Data mining is used widely to mine hidden knowledge and information from huge data. Classification is an important task in data mining, and it has been successfully applied in various fields. We propose a multi-class classification method, Adaptive Distance-Based Voting Classification (ADVC), based on voting on the distances of the global training samples with adaptive and practical voting thresholds. Experiments on various datasets demonstrate the effectiveness of the proposed method.