Combining Classifiers through Triplet-Based Belief Functions

Yaxin Bi, Shengli Wu, Xuhui Shen, Pan Xiong

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Classifier outputs in the form of continuous values have often been combined using linear sum or stacking, but little is generally known about evidential reasoning methods for combining truncated lists of ordered decisions. In this paper we introduce a novel class-indifferent method for combining such a kind of classifier decisions. Specifically we model each output given by classifiers on new instances as a list of ranked decisions that is divided into 2 subsets of decisions, which are represented by triplet-based belief functions and then are combined using Dempster’s rule of combination. We present a formalism for triplet-based belief functions and establish a range of general formulae for combining these beliefs in order to arrive at a consensus decision. In addition we carry out a comparative analysis with an alternative representation dichotomous belief functions on the UCI benchmark data. We also compare our combination method with the popular methods of stacking, boosting, linear sum and majority voting over the same benchmark data to demonstrate the advantage of our approach.
LanguageEnglish
Title of host publicationMachine Learning and Knowledge Discovery in Databases Lecture Notes in Computer Science
Pages102-116
Publication statusPublished - 2008

Fingerprint

Classifiers

Cite this

Bi, Y., Wu, S., Shen, X., & Xiong, P. (2008). Combining Classifiers through Triplet-Based Belief Functions. In Machine Learning and Knowledge Discovery in Databases Lecture Notes in Computer Science (pp. 102-116)
Bi, Yaxin ; Wu, Shengli ; Shen, Xuhui ; Xiong, Pan. / Combining Classifiers through Triplet-Based Belief Functions. Machine Learning and Knowledge Discovery in Databases Lecture Notes in Computer Science. 2008. pp. 102-116
@inbook{ad0b1fd67f1248aba92a8d10e84374bc,
title = "Combining Classifiers through Triplet-Based Belief Functions",
abstract = "Classifier outputs in the form of continuous values have often been combined using linear sum or stacking, but little is generally known about evidential reasoning methods for combining truncated lists of ordered decisions. In this paper we introduce a novel class-indifferent method for combining such a kind of classifier decisions. Specifically we model each output given by classifiers on new instances as a list of ranked decisions that is divided into 2 subsets of decisions, which are represented by triplet-based belief functions and then are combined using Dempster’s rule of combination. We present a formalism for triplet-based belief functions and establish a range of general formulae for combining these beliefs in order to arrive at a consensus decision. In addition we carry out a comparative analysis with an alternative representation dichotomous belief functions on the UCI benchmark data. We also compare our combination method with the popular methods of stacking, boosting, linear sum and majority voting over the same benchmark data to demonstrate the advantage of our approach.",
author = "Yaxin Bi and Shengli Wu and Xuhui Shen and Pan Xiong",
year = "2008",
language = "English",
isbn = "978-3-540-87478-2",
pages = "102--116",
booktitle = "Machine Learning and Knowledge Discovery in Databases Lecture Notes in Computer Science",

}

Bi, Y, Wu, S, Shen, X & Xiong, P 2008, Combining Classifiers through Triplet-Based Belief Functions. in Machine Learning and Knowledge Discovery in Databases Lecture Notes in Computer Science. pp. 102-116.

Combining Classifiers through Triplet-Based Belief Functions. / Bi, Yaxin; Wu, Shengli; Shen, Xuhui; Xiong, Pan.

Machine Learning and Knowledge Discovery in Databases Lecture Notes in Computer Science. 2008. p. 102-116.

Research output: Chapter in Book/Report/Conference proceedingChapter

TY - CHAP

T1 - Combining Classifiers through Triplet-Based Belief Functions

AU - Bi, Yaxin

AU - Wu, Shengli

AU - Shen, Xuhui

AU - Xiong, Pan

PY - 2008

Y1 - 2008

N2 - Classifier outputs in the form of continuous values have often been combined using linear sum or stacking, but little is generally known about evidential reasoning methods for combining truncated lists of ordered decisions. In this paper we introduce a novel class-indifferent method for combining such a kind of classifier decisions. Specifically we model each output given by classifiers on new instances as a list of ranked decisions that is divided into 2 subsets of decisions, which are represented by triplet-based belief functions and then are combined using Dempster’s rule of combination. We present a formalism for triplet-based belief functions and establish a range of general formulae for combining these beliefs in order to arrive at a consensus decision. In addition we carry out a comparative analysis with an alternative representation dichotomous belief functions on the UCI benchmark data. We also compare our combination method with the popular methods of stacking, boosting, linear sum and majority voting over the same benchmark data to demonstrate the advantage of our approach.

AB - Classifier outputs in the form of continuous values have often been combined using linear sum or stacking, but little is generally known about evidential reasoning methods for combining truncated lists of ordered decisions. In this paper we introduce a novel class-indifferent method for combining such a kind of classifier decisions. Specifically we model each output given by classifiers on new instances as a list of ranked decisions that is divided into 2 subsets of decisions, which are represented by triplet-based belief functions and then are combined using Dempster’s rule of combination. We present a formalism for triplet-based belief functions and establish a range of general formulae for combining these beliefs in order to arrive at a consensus decision. In addition we carry out a comparative analysis with an alternative representation dichotomous belief functions on the UCI benchmark data. We also compare our combination method with the popular methods of stacking, boosting, linear sum and majority voting over the same benchmark data to demonstrate the advantage of our approach.

M3 - Chapter

SN - 978-3-540-87478-2

SP - 102

EP - 116

BT - Machine Learning and Knowledge Discovery in Databases Lecture Notes in Computer Science

ER -

Bi Y, Wu S, Shen X, Xiong P. Combining Classifiers through Triplet-Based Belief Functions. In Machine Learning and Knowledge Discovery in Databases Lecture Notes in Computer Science. 2008. p. 102-116