Deakin University
Browse

Fuzzy-based feature and instance recovery

Version 2 2024-06-06, 05:42
Version 1 2016-04-26, 16:21
chapter
posted on 2024-06-06, 05:42 authored by S Liu, J Zhang, Y Wang, Y Xiang
The severe class distribution shews the presence of underrepresented data, which has great effects on the performance of learning algorithm, is still a challenge of data mining and machine learning. Lots of researches currently focus on experimental comparison of the existing re-sampling approaches. We believe it requires new ways of constructing better algorithms to further balance and analyse the data set. This paper presents a Fuzzy-based Information Decomposition oversampling (FIDoS) algorithm used for handling the imbalanced data. Generally speaking, this is a new way of addressing imbalanced learning problems from missing data perspective. First, we assume that there are missing instances in the minority class that result in the imbalanced dataset. Then the proposed algorithm which takes advantages of fuzzy membership function is used to transfer information to the missing minority class instances. Finally, the experimental results demonstrate that the proposed algorithm is more practical and applicable compared to sampling techniques.

History

Volume

9621

Chapter number

58

Pagination

605-615

ISSN

0302-9743

eISSN

1611-3349

ISBN-13

9783662493816

Language

eng

Publication classification

B Book chapter, B1 Book chapter

Copyright notice

2016, Springer

Extent

77

Editor/Contributor(s)

Nguyen NT, Trawinski B, Fujita H, Hong TP

Publisher

Springer

Place of publication

Berlin, Germany

Title of book

Intelligent information and database systems : 8th Asian conference, ACIIDS 2016, Da Nang, Vietnam, March 14-16, 2016, proceedings, part I

Series

Lecture notes in computer science