An active learning method for data streams with concept drift

In analyzing streaming data in which the underlying data distribution may change or the concept of interest may drift over time, the ability of a classifier to adapt to drifted concepts is very important to maintaining the prediction performance. However, the true class labels of data samples are of...

Full description

Saved in:
Bibliographic Details
Published in2016 IEEE International Conference on Big Data (Big Data) pp. 746 - 752
Main Authors Cheong Hee Park, Youngsoon Kang
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.12.2016
Subjects
Active learning
Adaptive incremental classifier
Concept drift
Data models
Decision trees
Labeling
Learning systems
Streaming data
Support vector machines
Training
Uncertainty
Online AccessGet full text

Cover

More Information
Summary:In analyzing streaming data in which the underlying data distribution may change or the concept of interest may drift over time, the ability of a classifier to adapt to drifted concepts is very important to maintaining the prediction performance. However, the true class labels of data samples are often available only after some period of time or they are obtained by experts' efforts. In this paper, we develop an effective method for active learning on data streams with concept drift. The proposed method combines active learning and adaptive incremental learning. For unlabeled data samples, the degree of concept drift is estimated and used for both data selection for labeling and adaptive incremental learning of the current classifier. Experimental results on five artificial data sets and two real data sets demonstrate a competent performance of the proposed method.
DOI:10.1109/BigData.2016.7840667