Set Analysis of Coincident Errors and Its Applications for Combining Classifiers

There is a common agreement in many recent publications related to pattern recognition that dependency among classifier outputs plays a key role in combining classifiers [1]–[7]. Diversity, independence, disagreement and most recently negative dependency are the terms often used to express a desirable relation among classifiers to ensure the maximum improvement of the fusion system [4]–[7]. In this variety of concepts the idea is the same: how to measure relationship among classifiers from their outputs so that it is possible to say something about the combined classifier performance? Recent investigations indicate that error coincidences seem to be the most valuable information in this pursuit [7]–[9].

[1]  Ludmila I. Kuncheva,et al.  Measures of Diversity in Classifier Ensembles and Their Relationship with the Ensemble Accuracy , 2003, Machine Learning.

[2]  Bogdan Gabrys,et al.  Analysis of the Correlation Between Majority Voting Error and the Diversity Measures in Multiple Classifier Systems , 2001 .

[3]  Amanda J. C. Sharkey,et al.  Combining Artificial Neural Nets: Ensemble and Modular Multi-Net Systems , 1999 .

[4]  Jin Hyung Kim,et al.  Optimal approximation of discrete probability distribution with kth-order dependency and its application to combining multiple classifiers , 1997, Pattern Recognit. Lett..

[5]  Robert P. W. Duin,et al.  Limits on the majority vote accuracy in classifier fusion , 2003, Pattern Analysis & Applications.

[6]  Keith Devlin,et al.  The Joy of Sets , 1993 .

[7]  K. Devlin.  Fundamentals of contemporary set theory , 1979 .

[8]  Ching Y. Suen,et al.  Application of majority voting to pattern recognition: an analysis of its behavior and performance , 1997, IEEE Trans. Syst. Man Cybern. Part A.

[9]  Bev Littlewood,et al.  Conceptual Modeling of Coincident Failures in Multiversion Software , 1989, IEEE Trans. Software Eng..

[10]  Galina L. Rogova,et al.  Combining the results of several neural network classifiers , 1994, Neural Networks.

[11]  Noel E. Sharkey,et al.  Combining diverse neural nets , 1997, The Knowledge Engineering Review.

[12]  C. J. Whitaker,et al.  Ten measures of diversity in classifier ensembles: limits for two classifiers , 2001 .

[13]  Ludmila I. Kuncheva,et al.  Relationships between combination methods and measures of diversity in combining classifiers , 2002, Inf. Fusion.

[14]  Derek Partridge,et al.  Software Diversity: Practical Statistics for Its Measurement and Exploitation | Draft Currently under Revision , 1996 .

[15]  Roberto Battiti,et al.  Democracy in neural nets: Voting schemes for classification , 1994, Neural Networks.

[16]  Derek Partridge,et al.  Strategies for improving neural net generalisation , 2005, Neural Computing & Applications.

[17]  Fabio Roli,et al.  An approach to the automatic design of multiple classifier systems , 2001, Pattern Recognit. Lett..