Multiple Classifier Systems

1. Front Matter

   Pages I-XII

   PDF

2. Bagging and Boosting

   1. Bagging and the Random Subspace Method for Redundant Feature Spaces

      • Marina Skurichina, Robert P. W. Duin

      Pages 1-10

   2. Performance Degradation in Boosting

      • Jeevani Wickramaratna, Sean Holden, Bernard Buxton

      Pages 11-21

   3. A Generalized Class of Boosting Algorithms Based on Recursive Decoding Models

      • Elizabeth Tapia, José C. González, Julio Villena

      Pages 22-31

   4. Tuning Cost-Sensitive Boosting and Its Application to Melanoma Diagnosis

      • Stefano Merler, Cesare Furlanello, Barbara Larcher, Andrea Sboner

      Pages 32-42

   5. Learning Classification RBF Networks by Boosting

      • Juan J. Rodríguez Diez, Carlos J. Alonso González

      Pages 43-52

3. MCS Design Methodology

   1. Data Complexity Analysis for Classifier Combination

      • Tin Kam Ho

      Pages 53-67

   2. Genetic Programming for Improved Receiver Operating Characteristics

      • W. B. Langdon, B. F. Buxton

      Pages 68-77

   3. Methods for Designing Multiple Classifier Systems

      • Fabio Roli, Giorgio Giacinto, Gianni Vernazza

      Pages 78-87

   4. Decision-Level Fusion in Fingerprint Verification

      • Salil Prabhakar, Anil K. Jain

      Pages 88-98

   5. Genetic Algorithms for Multi-classifier System Configuration: A Case Study in Character Recognition

      • K. Sirlantzis, M. C. Fairhurst, M. S. Hoque

      Pages 99-108

   6. Combined Classification of Handwritten Digits Using the ‘Virtual Test Sample Method’

      • Jörg Dahmen, Daniel Keysers, Hermann Ney

      Pages 109-118

   7. Averaging Weak Classifiers

      • Dechang Chen, Jian Liu

      Pages 119-125

   8. Mixing a Symbolic and a Subsymbolic Expert to Improve Carcinogenicity Prediction of Aromatic Compounds

      • Giuseppina Gini, Marco Lorenzini, Emilio Benfenati, Raffaella Brambilla, Luca Malvé

      Pages 126-135

4. Ensemble Classifiers

   1. Multiple Classifier Systems Based on Interpretable Linear Classifiers

      • David J. Hand, Niall M. Adams, Mark G. Kelly

      Pages 136-147

   2. Least Squares and Estimation Measures via Error Correcting Output Code

      • Reza Ghaderi, Terry Windeatt

      Pages 148-157

   3. Dependence among Codeword Bits Errors in ECOC Learning Machines: An Experimental Analysis

      • Francesco Masulli, Giorgio Valentini

      Pages 158-167

   4. Information Analysis of Multiple Classifier Fusion?

      • Jiří Grim, Josef Kittler, Pavel Pudil, Petr Somol

      Pages 168-177

   5. Limiting the Number of Trees in Random Forests

      • Patrice Latinne, Olivier Debeir, Christine Decaestecker

      Pages 178-187

   6. Learning-Data Selection Mechanism through Neural Networks Ensemble

      • Pitoyo Hartono, Shuji Hashimoto

      Pages 188-197

Driven by the requirements of a large number of practical and commercially - portant applications, the last decade has witnessed considerable advances in p- tern recognition. Better understanding of the design issues and new paradigms, such as the Support Vector Machine, have contributed to the development of - proved methods of pattern classi cation. However, while any performance gains are welcome, and often extremely signi cant from the practical point of view, it is increasingly more challenging to reach the point of perfection as de ned by the theoretical optimality of decision making in a given decision framework. The asymptoticity of gains that can be made for a single classi er is a re?- tion of the fact that any particular design, regardless of how good it is, simply provides just one estimate of the optimal decision rule. This observation has motivated the recent interest in Multiple Classi er Systems , which aim to make use of several designs jointly to obtain a better estimate of the optimal decision boundary and thus improve the system performance. This volume contains the proceedings of the international workshop on Multiple Classi er Systems held at Robinson College, Cambridge, United Kingdom (July 2{4, 2001), which was organized to provide a forum for researchers in this subject area to exchange views and report their latest results.

• Algorithmic Learning
• Bagging
• Boosting
• Classification
• Classifier SYstems
• Document Analysis
• Image ANalysis
• Machine Learning
• Multiple Classifier Systems
• Neural Networks
• Pattern Recognition
• Remote Sensing
• Time Series Analysis
• algorithm analysis and problem complexity

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

  Josef Kittler

• Department of Electrical and Electronic Engineering, University of Cagliari, Cagliari, Italy

  Fabio Roli

Policies and ethics