Sciweavers

Share
TKDE
2012

DDD: A New Ensemble Approach for Dealing with Concept Drift

7 years 10 months ago
DDD: A New Ensemble Approach for Dealing with Concept Drift
—Online learning algorithms often have to operate in the presence of concept drifts. A recent study revealed that different diversity levels in an ensemble of learning machines are required in order to maintain high generalisation on both old and new concepts. Inspired by this study and based on a further study of diversity with different strategies to deal with drifts, we propose a new online ensemble learning approach called Diversity for Dealing with Drifts (DDD). DDD maintains ensembles with different diversity levels and is able to attain better accuracy than other approaches. Furthermore, it is very robust, outperforming other drift handling approaches in terms of accuracy when there are false positive drift detections. In all the experimental comparisons we have carried out, DDD always performed at least as well as other drift handling approaches under various conditions, with very few exceptions.
Leandro L. Minku, Xin Yao
Added 29 Sep 2012
Updated 29 Sep 2012
Type Journal
Year 2012
Where TKDE
Authors Leandro L. Minku, Xin Yao
Comments (0)
books