On the window size for classification in changing environments

Authors:
Ludmila I. Kuncheva;Indrė/ Ž/liobaitė/
Affiliations:
(Correspd. Bangor Univ., Dean St., Bangor Gwynedd LL57 1UT, UK. Tel.: +44 1248383661/ Fax: +44 1248361429/ E-mail: l.i.kuncheva@bangor.ac.uk) School of Computer Science, Bangor University, Bangor, ...;Faculty of Mathematics and Informatics, Vilnius University, Vilnius, Lithuania
Venue:
Intelligent Data Analysis
Year:
2009

Citing 8
Cited 5

Effects of Sample Size in Classifier Design

IEEE Transactions on Pattern Analysis and Machine Intelligence
Small Sample Size Effects in Statistical Pattern Recognition: Recommendations for Practitioners

IEEE Transactions on Pattern Analysis and Machine Intelligence
Learning in the presence of concept drift and hidden contexts

Machine Learning
Guest Editors‘ Introduction

Machine Learning - Special issue on context sensitivity and concept drift
Detecting Concept Drift with Support Vector Machines

ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)
Incremental learning and concept drift: Editor's introduction: Guest-editorial

Intelligent Data Analysis
Expected Classification Error of the Euclidean Linear Classifier under Sudden Concept Drift

FSKD '08 Proceedings of the 2008 Fifth International Conference on Fuzzy Systems and Knowledge Discovery - Volume 02

A robust incremental learning method for non-stationary environments

Neurocomputing
Online linear and quadratic discriminant analysis with adaptive forgetting for streaming classification

Statistical Analysis and Data Mining
Next challenges for adaptive learning systems

ACM SIGKDD Explorations Newsletter
A survey on concept drift adaptation

ACM Computing Surveys (CSUR)
Classifying evolving data streams with partially labeled data

Intelligent Data Analysis

Quantified Score

Hi-index	0.00

Visualization

Abstract

Classification in changing environments (commonly known as concept drift) requires adaptation of the classifier to accommodate the changes. One approach is to keep a moving window on the streaming data and constantly update the classifier on it. Here we consider an abrupt change scenario where one set of probability distributions of the classes is instantly replaced with another. For a fixed 'transition period' around the change, we derive a generic relationship between the size of the moving window and the classification error rate. We derive expressions for the error in the transition period and for the optimal window size for the case of two Gaussian classes where the concept change is a geometrical displacement of the whole class configuration in the space. A simple window resize strategy based on the derived relationship is proposed and compared with fixed-size windows on a real benchmark data set data set (Electricity Market).