Aggregation of Classifiers: A Justifiable Information Granularity Approach
- 16 April 2018
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 49 (6) , 2168-2177
Abstract
In this paper, we introduced a new approach of combining multiple classifiers in a heterogeneous ensemble system. Instead of using numerical membership values when combining, we constructed interval membership values for each class prediction from the meta-data of observation by using the concept of information granule. In the proposed method, the uncertainty (diversity) of the predictions produced by the base classifiers is quantified by the interval-based information granules. The decision model is then generated by considering both bound and length of the intervals. Extensive experimentation using the UCI datasets has demonstrated the superior performance of our algorithm over other algorithms including six fixed combining methods, one trainable combining method, AdaBoost, bagging, and random subspace.Keywords
All Related Versions
This publication has 48 references indexed in Scilit:
- The design of fuzzy information granules: Tradeoffs between specificity and experimental evidenceApplied Soft Computing, 2009
- Rudiments of rough setsInformation Sciences, 2007
- Toward a generalized theory of uncertainty (GTU)––an outlineInformation Sciences, 2005
- Decision templates for multiple classifier fusion: an experimental comparisonPattern Recognition, 2001
- From computing with numbers to computing with words. From manipulation of measurements to manipulation of perceptionsIEEE Transactions on Circuits and Systems I: Regular Papers, 1999
- Expected classification error of the Fisher linear classifier with pseudo-inverse covariance matrixPattern Recognition Letters, 1998
- On combining classifiersIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998
- Shadowed sets: representing and processing fuzzy setsIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 1998
- The random subspace method for constructing decision forestsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998
- Combining multiple neural networks by fuzzy integral for robust classificationIEEE Transactions on Systems, Man, and Cybernetics, 1995