DocumentCode
178094
Title
Hellinger Distance Trees for Imbalanced Streams
Author
Lyon, R.J. ; Brooke, J.M. ; Knowles, J.D. ; Stappers, B.W.
Author_Institution
Sch. of Comput. Sci., Univ. of Manchester, Manchester, UK
fYear
2014
fDate
24-28 Aug. 2014
Firstpage
1969
Lastpage
1974
Abstract
Classifiers trained on data sets possessing an imbalanced class distribution are known to exhibit poor generalisation performance. This is known as the imbalanced learning problem. The problem becomes particularly acute when we consider incremental classifiers operating on imbalanced data streams, especially when the learning objective is rare class identification. As accuracy may provide a misleading impression of performance on imbalanced data, existing stream classifiers based on accuracy can suffer poor minority class performance on imbalanced streams, with the result being low minority class recall rates. In this paper we address this deficiency by proposing the use of the Hellinger distance measure, as a very fast decision tree split criterion. We demonstrate that by using Hellinger a statistically significant improvement in recall rates on imbalanced data streams can be achieved, with an acceptable increase in the false positive rate.
Keywords
data handling; pattern classification; Hellinger distance measurement; Hellinger distance trees; data sets possessing; decision tree; imbalanced class distribution; imbalanced learning problem; imbalanced streams; learning objective; Decision trees; Earth; Labeling; Remote sensing; Satellites; Skin; Training;
fLanguage
English
Publisher
ieee
Conference_Titel
Pattern Recognition (ICPR), 2014 22nd International Conference on
Conference_Location
Stockholm
ISSN
1051-4651
Type
conf
DOI
10.1109/ICPR.2014.344
Filename
6977056
Link To Document