Multiple Classifier Systems

1. Front Matter

   PDF

2. Invited Papers

   1. Classifier Ensembles for Changing Environments

      • Ludmila I. Kuncheva

      Pages 1-15

   2. A Generic Sensor Fusion Problem: Classification and Function Estimation

      • Nageswara S. V. Rao

      Pages 16-30

3. Bagging and Boosting

   1. AveBoost2: Boosting for Noisy Data

      • Nikunj C. Oza

      Pages 31-40

   2. Bagging Decision Multi-trees

      • Vicent Estruch, César Ferri, José Hernández-Orallo, Maria José Ramírez-Quintana

      Pages 41-51

   3. Learn++.MT: A New Approach to Incremental Learning

      • Michael Muhlbaier, Apostolos Topalis, Robi Polikar

      Pages 52-61

   4. Beyond Boosting: Recursive ECOC Learning Machines

      • Elizabeth Tapia, José C. González, Alexander Hütermann, Javier García

      Pages 62-71

   5. Exact Bagging with k-Nearest Neighbour Classifiers

      • Bruno Caprile, Stefano Merler, Cesare Furlanello, Giuseppe Jurman

      Pages 72-81

4. Combination Methods

   1. Yet Another Method for Combining Classifiers Outputs: A Maximum Entropy Approach

      • Marco Saerens, François Fouss

      Pages 82-91

   2. Combining One-Class Classifiers to Classify Missing Data

      • Piotr Juszczak, Robert P. W. Duin

      Pages 92-101

   3. Combining Kernel Information for Support Vector Classification

      • Isaac Martín de Diego, Javier M. Moguerza, Alberto Muñoz

      Pages 102-111

   4. Combining Classifiers Using Dependency-Based Product Approximation with Bayes Error Rate

      • Hee-Joong Kang

      Pages 112-121

   5. Combining Dissimilarity-Based One-Class Classifiers

      • Elżbieta Pękalska, Marina Skurichina, Robert P. W. Duin

      Pages 122-133

   6. A Modular System for the Classification of Time Series Data

      • Lei Chen, Mohamed Kamel, Ju Jiang

      Pages 134-143

   7. A Probabilistic Model Using Information Theoretic Measures for Cluster Ensembles

      • Hanan Ayad, Otman Basir, Mohamed Kamel

      Pages 144-153

   8. Classifier Fusion Using Triangular Norms

      • Piero Bonissone, Kai Goebel, Weizhong Yan

      Pages 154-163

   9. Dynamic Integration of Regression Models

      • Niall Rooney, David Patterson, Sarab Anand, Alexey Tsymbal

      Pages 164-173

   10. Dynamic Classifier Selection by Adaptive k-Nearest-Neighbourhood Rule

       • Luca Didaci, Giorgio Giacinto

       Pages 174-183

5. Design Methods

   1. Spectral Measure for Multi-class Problems

      • Terry Windeatt

      Pages 184-193

   2. The Relationship between Classifier Factorisation and Performance in Stochastic Vector Quantisation

      • David Windridge, Robin Patenall, Josef Kittler

      Pages 194-203

The fusion of di?erent information sourcesis a persistent and intriguing issue. It hasbeenaddressedforcenturiesinvariousdisciplines,includingpoliticalscience, probability and statistics, system reliability assessment, computer science, and distributed detection in communications. Early seminal work on fusion was c- ried out by pioneers such as Laplace and von Neumann. More recently, research activities in information fusion have focused on pattern recognition. During the 1990s,classi?erfusionschemes,especiallyattheso-calleddecision-level,emerged under a plethora of di?erent names in various scienti?c communities, including machine learning, neural networks, pattern recognition, and statistics. The d- ferent nomenclatures introduced by these communities re?ected their di?erent perspectives and cultural backgrounds as well as the absence of common forums and the poor dissemination of the most important results. In 1999, the ?rst workshop on multiple classi?er systems was organized with the main goal of creating a common international forum to promote the diss- ination of the results achieved in the diverse communities and the adoption of a common terminology, thus giving the di?erent perspectives and cultural ba- grounds some concrete added value. After ?ve meetings of this workshop, there is strong evidence that signi?cant steps have been made towards this goal. - searchers from these diverse communities successfully participated in the wo- shops, and world experts presented surveys of the state of the art from the perspectives of their communities to aid cross-fertilization.

• Bagging
• Boosting
• Performance
• Random Forest
• classification
• classifier systems
• cognition
• learning
• learning classifier systems
• machine learning
• multiple classifier systems
• neural networks
• speech recognition
• statistical learning
• verification

• Department of Electrical and Electronic Engineering, Piazza d’Armi, University of Cagliari, Cagliari, Italy

  Fabio Roli

• Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK

  Josef Kittler

• Centre for Vision, Speech and Signal Proc (CVSSP), University of Surrey, Guildford, United Kingdom

  Terry Windeatt

Policies and ethics