Learning with imbalanced datasets using fuzzy ARTMAP-based neural network models

Shing Chiang Tan; Junzo Watada; Zuwarie Ibrahim; Marzuki Khalid; Lee Wen Jau; Lim Chun Chew

doi:10.1109/FUZZY.2011.6007330

Learning with imbalanced datasets using fuzzy ARTMAP-based neural network models

Shing Chiang Tan^*, Junzo Watada, Zuwarie Ibrahim, Marzuki Khalid, Lee Wen Jau, Lim Chun Chew

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Citations (Scopus)

Abstract

One of the main difficulties in real-world data classification and analysis tasks is that the data distribution can be imbalanced. In this paper, a variant of the supervised learning neural network from the Adaptive Resonance Theory (ART) family, i.e., Fuzzy ARTMAP (FAM) which is equipped with a conflict-resolving facility, is proposed to classify an imbalanced dataset that represents a real problem in the semiconductor industry. The FAM model is combined with the Dynamic Decay Adjustment (DDA) algorithm to form a hybrid FAMDDA network. The classification results of FAM and FAMDDA are presented, compared, and analyzed using several classification metrics. The outcomes positively indicate the effectiveness of the proposed FAMDDA network in undertaking classification problems with imbalanced datasets.

Original language	English
Title of host publication	IEEE International Conference on Fuzzy Systems
Pages	1084-1089
Number of pages	6
DOIs	https://doi.org/10.1109/FUZZY.2011.6007330
Publication status	Published - 2011
Event	2011 IEEE International Conference on Fuzzy Systems, FUZZ 2011 - Taipei Duration: 2011 Jun 27 → 2011 Jun 30

Other

Other	2011 IEEE International Conference on Fuzzy Systems, FUZZ 2011
City	Taipei
Period	11/6/27 → 11/6/30

Keywords

Adaptive Resonance Theory Neural Networks
Data classification
imbalanced data
supervised learning

ASJC Scopus subject areas

Software
Artificial Intelligence
Applied Mathematics
Theoretical Computer Science

Access to Document

10.1109/FUZZY.2011.6007330

Cite this

@inproceedings{bfeb0ed416714d60a63d1eaadad14078,

title = "Learning with imbalanced datasets using fuzzy ARTMAP-based neural network models",

abstract = "One of the main difficulties in real-world data classification and analysis tasks is that the data distribution can be imbalanced. In this paper, a variant of the supervised learning neural network from the Adaptive Resonance Theory (ART) family, i.e., Fuzzy ARTMAP (FAM) which is equipped with a conflict-resolving facility, is proposed to classify an imbalanced dataset that represents a real problem in the semiconductor industry. The FAM model is combined with the Dynamic Decay Adjustment (DDA) algorithm to form a hybrid FAMDDA network. The classification results of FAM and FAMDDA are presented, compared, and analyzed using several classification metrics. The outcomes positively indicate the effectiveness of the proposed FAMDDA network in undertaking classification problems with imbalanced datasets.",

keywords = "Adaptive Resonance Theory Neural Networks, Data classification, imbalanced data, supervised learning",

author = "Tan, {Shing Chiang} and Junzo Watada and Zuwarie Ibrahim and Marzuki Khalid and Jau, {Lee Wen} and Chew, {Lim Chun}",

year = "2011",

doi = "10.1109/FUZZY.2011.6007330",

language = "English",

isbn = "9781424473175",

pages = "1084--1089",

booktitle = "IEEE International Conference on Fuzzy Systems",

note = "2011 IEEE International Conference on Fuzzy Systems, FUZZ 2011 ; Conference date: 27-06-2011 Through 30-06-2011",

}

TY - GEN

T1 - Learning with imbalanced datasets using fuzzy ARTMAP-based neural network models

AU - Tan, Shing Chiang

AU - Watada, Junzo

AU - Ibrahim, Zuwarie

AU - Khalid, Marzuki

AU - Jau, Lee Wen

AU - Chew, Lim Chun

PY - 2011

Y1 - 2011

N2 - One of the main difficulties in real-world data classification and analysis tasks is that the data distribution can be imbalanced. In this paper, a variant of the supervised learning neural network from the Adaptive Resonance Theory (ART) family, i.e., Fuzzy ARTMAP (FAM) which is equipped with a conflict-resolving facility, is proposed to classify an imbalanced dataset that represents a real problem in the semiconductor industry. The FAM model is combined with the Dynamic Decay Adjustment (DDA) algorithm to form a hybrid FAMDDA network. The classification results of FAM and FAMDDA are presented, compared, and analyzed using several classification metrics. The outcomes positively indicate the effectiveness of the proposed FAMDDA network in undertaking classification problems with imbalanced datasets.

AB - One of the main difficulties in real-world data classification and analysis tasks is that the data distribution can be imbalanced. In this paper, a variant of the supervised learning neural network from the Adaptive Resonance Theory (ART) family, i.e., Fuzzy ARTMAP (FAM) which is equipped with a conflict-resolving facility, is proposed to classify an imbalanced dataset that represents a real problem in the semiconductor industry. The FAM model is combined with the Dynamic Decay Adjustment (DDA) algorithm to form a hybrid FAMDDA network. The classification results of FAM and FAMDDA are presented, compared, and analyzed using several classification metrics. The outcomes positively indicate the effectiveness of the proposed FAMDDA network in undertaking classification problems with imbalanced datasets.

KW - Adaptive Resonance Theory Neural Networks

KW - Data classification

KW - imbalanced data

KW - supervised learning

UR - http://www.scopus.com/inward/record.url?scp=80053083501&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80053083501&partnerID=8YFLogxK

U2 - 10.1109/FUZZY.2011.6007330

DO - 10.1109/FUZZY.2011.6007330

M3 - Conference contribution

AN - SCOPUS:80053083501

SN - 9781424473175

SP - 1084

EP - 1089

BT - IEEE International Conference on Fuzzy Systems

T2 - 2011 IEEE International Conference on Fuzzy Systems, FUZZ 2011

Y2 - 27 June 2011 through 30 June 2011

ER -

Learning with imbalanced datasets using fuzzy ARTMAP-based neural network models

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this