A novel cost sensitive classification algorithm based on neighborhood hypergraph

被引：0
作者：
Chongqing Key Laboratory of Computational Intelligence, Chongqing University of Posts and Telecommunications, Chongqing, China [1 ]
机构：
[1] Chongqing Key Laboratory of Computational Intelligence, Chongqing University of Posts and Telecommunications, Chongqing
来源：
J. Comput. Inf. Syst. | / 1卷 / 109-121期
基金：
中国国家自然科学基金;
关键词：
Cost Sensitivity; Hyper-network; Imbalanced Data; Neighborhood Hypergraph;
D O I：
10.12733/jcis12797
中图分类号：
学科分类号：
摘要：
The classification problem for imbalance data is paid more attention to. So far, many significant methods are proposed and applied to many fields. But, more eficient methods are needed still. Cost-sensitive hypergraph may be not powerful enough to deal with the data in boundary region, although it is an eficient tool to knowledge discovery. In this paper, the cost-sensitive neighborhood hypergraph is presented, combining rough set theory and cost hypergraph. After that, a novel classification algorithm for imbalance data based on cost neighborhood hypergraph is developed, which is composed of three steps: initialization of hyper-edge, cost classification and learning of hyper-edge set. After conducting an experiment of 10-fold cross validation on 10 data sets, the propo-sed algorithm has higher average accuracy than others. ©, 2014, Journal of Computational Information Systems. All right reserved.
引用
收藏
页码：109 / 121
页数：12
相关论文
共 26 条
  • [1] Malof J.M., Mazurowski M.A., Tourassi G.D., The efiect of class imbalance on case selection for case-based classifiers: An empirical study in the context of medical decision support, Neural Networks, 25, pp. 141-145, (2012)
  • [2] Wang G., Asymmetric random subspace method for imbalanced credit risk evaluation, Software Engineering and Knowledge Engineering: Theory and Practice, 114, pp. 1047-1053, (2012)
  • [3] Suresh S., Sundararajan N., Saratchandran P., Risk-sensitive loss functions for sparse multicategory classification problems, Information Sciences, 178, 12, pp. 2621-2638, (2008)
  • [4] Addis A., Armano G., Vargiu E., Experimentally Studying Progressive Filtering in Presence of Input Imbalance, Knowledge Discovery, Knowledge Engineering and Knowledge Management, 272, pp. 56-71, (2013)
  • [5] Provost F., Machine learning from imbalanced data sets, Proceedings of the AAAI-2000 Work- shop Learning from Imbanlanced Data Sets, pp. 1-3, (2000)
  • [6] Sun Y., Kamel M.S., Wong A.K.C., Cost-sensitive boosting for classification of imbalanced data, Pattern Recognition, 40, 12, pp. 3358-3378, (2007)
  • [7] Sun K.W., Evolutionary Hypernetwork Based Classification of High Dimensional and Imbalanced Data, pp. 9-34, (2013)
  • [8] Rumelhart D.E., Norman D.A., Accretion, Tuning and Restructuring: Three Modes of Learning, (1976)
  • [9] Zhang B.T., Hypernetworks: A molecular evolutionary architecture for cognitive learning and memory, IEEE Computational Intelligence Magazine, 3, 3, pp. 49-63, (2008)
  • [10] Pawlak Z., Rough sets, International Journal of Computer and Information Sciences, 11, 5, pp. 341-356, (1982)
123