A Model-Free Subject Selection Method for Active Learning Classification Procedures

To construct a classification rule via an active learning method, during the learning process, users select training subjects sequentially, without knowing their labels, based on the model learned at the current stage. For a parametric-model-based classification rule, methods of statistical experime...

Full description

Saved in:
Bibliographic Details
Published inJournal of classification Vol. 38; no. 3; pp. 544 - 555
Main Authors Ke, Bo-Shiang, Chang, Yuan-chin Ivan
Format Journal Article
LanguageEnglish
Published New York Springer US 01.10.2021
Springer Nature B.V
Subjects
Active learning
Bioinformatics
Classification
Classifiers
Design of experiments
Learning
Marketing
Mathematics and Statistics
Pattern Recognition
Psychometrics
Signal,Image and Speech Processing
Statistical methods
Statistical Theory and Methods
Statistics
Support vector machines
ROC curve
Active learning
Subject selection
Classification
Influential index
AUC
Online AccessGet full text

Cover

More Information
Summary:To construct a classification rule via an active learning method, during the learning process, users select training subjects sequentially, without knowing their labels, based on the model learned at the current stage. For a parametric-model-based classification rule, methods of statistical experimental design are popular guidelines for selecting new learning subjects. However, there is a lack of a counterpart for non-parametric-model-based classifiers, such as support vector machines. Thus, we propose a subject selection scheme via an extended influential index for the area under a receiver operating characteristic curve, which is applicable to general classifiers with continuous scores.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0176-4268
1432-1343
DOI:10.1007/s00357-021-09388-3