Medical decision support system for extremely imbalanced datasets

详细信息    查看全文

• 作者：Swati Shilaskar ; ^{shilaskar_swati@rediffmail.com} ; ^{swati.shilaskar@vit.edu} ; Ashok Ghatol¹ ; ^{vc_2005@rediffmail.com} ; Prashant Chatur² ; ^{chatur.prashant@gcoea.ac.in}
• 关键词：Imbalanced dataset ; Evolutionary algorithm ; Medical diagnosis ; Particle swarm ; Physiological parameters ; Synthetic sampling
• 刊名：Information Sciences
• 出版年：2017
• 出版时间：April 2017
• 年：2017
• 卷：384
• 期：Complete
• 页码：205-219
• 全文大小：3661 K
• 卷排序：384

文摘

Synthetic sampling method for data conditioning of multiclass imbalanced datasets is proposed. Modified particle swarm optimization technique and Hybrid forward feature selection method for multiclass classifier is developed. Effectiveness of these techniques is demonstrated on extremely imbalanced medical datasets