Complementary learning fuzzy neural network: An approach to imbalanced dataset

被引：5

作者：

Tan, T. Z. ^{[1
]}

Ng, G. S. ^{[1
]}

Quek, C. ^{[1
]}

机构：

[1] Nanyang Technol Univ, Ctr Computat Intelligence, Sch Comp Engn, Dept Comp Sci, Singapore 639798, Singapore

来源：

2007 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-6 | 2007年

关键词：

D O I：

10.1109/IJCNN.2007.4371318

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Imbalanced dataset is a phenomenon seen in many real life applications, especially in medical field. The conventional computational intelligence algorithms cannot effectively handle the imbalanced data because they are designed for balanced data distribution. Complementary learning fuzzy neural network is proposed as one of the approach for learning imbalanced dataset. It is shown empirically and theoretically that the effects of imbalanced dataset are minimal in this class of neuro-fuzzy system.

引用

页码：2306 / 2311

页数：6

共 18 条

[1]

Alejo R, 2006, LECT NOTES COMPUT SC, V4224, P464

[2]

ALTUN H, 2007, IN PRESS EXPERT SYST

[3]

Blake C.L., 1998, UCI repository of machine learning databases

[4]

Chen XW, 2005, IEEE IJCNN, P1883

[5]

CROSS S, 2006, ARTIFICIAL NEURAL NE

[6] A multiple resampling method for learning from imbalanced data sets [J].

Estabrooks, A ;

Jo, TH ;

Japkowicz, N .

COMPUTATIONAL INTELLIGENCE, 2004, 20 (01) :18-36

[7] Expertise for cars and birds recruits brain areas involved in face recognition [J].

Gauthier, I ;

Skudlarski, P ;

Gore, JC ;

Anderson, AW .

NATURE NEUROSCIENCE, 2000, 3 (02) :191-197

[8]

Grzymala-Busse JW, 2004, LECT NOTES COMPUT SC, V3213, P757

[9] A kernel-based two-class classifier for imbalanced data sets [J].

Hong, Xia ;

Chen, Sheng ;

Harris, Chris J. .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 2007, 18 (01) :28-41

[10]

Huang KZ, 2004, PROC CVPR IEEE, P558

← 1 2 →