Multiple Classifier Systems

1. Front Matter

   Pages I-X

   PDF

2. Theory and Algorithms

   1. Front Matter

      Pages 1-1

      PDF

   2. A Novel Bagging Ensemble Approach for Variable Ranking and Selection for Linear Regression Models

      • Chun-Xia Zhang, Jiang-She Zhang, Guan-Wei Wang

      Pages 3-14

   3. A Hierarchical Ensemble Method for DAG-Structured Taxonomies

      • Peter N. Robinson, Marco Frasca, Sebastian Köhler, Marco Notaro, Matteo Re, Giorgio Valentini

      Pages 15-26

   4. Diversity Measures and Margin Criteria in Multi-class Majority Vote Ensemble

      • Ayako Mikami, Mineichi Kudo, Atsuyoshi Nakamura

      Pages 27-37

   5. Fractional Programming Weighted Decoding for Error-Correcting Output Codes

      • Firat Ismailoglu, I. G. Sprinkhuizen-Kuyper, Evgueni Smirnov, Sergio Escalera, Ralf Peeters

      Pages 38-50

   6. Instance-Based Decompositions of Error Correcting Output Codes

      • Firat Ismailoglu, Evgueni Smirnov, Nikolay Nikolaev, Ralf Peeters

      Pages 51-63

   7. Pruning Bagging Ensembles with Metalearning

      • Fábio Pinto, Carlos Soares, João Mendes-Moreira

      Pages 64-75

   8. Multi-label Selective Ensemble

      • Nan Li, Yuan Jiang, Zhi-Hua Zhou

      Pages 76-88

   9. Supervised Selective Combination of Diverse Object-Representation Modalities for Regression Estimation

      • Olga Krasotkina, Oleg Seredin, Vadim Mottl

      Pages 89-99

   10. Detecting Ordinal Class Structures

       • Raphael Lattke, Ludwig Lausser, Christoph Müssel, Hans A. Kestler

       Pages 100-111

   11. Calibrating AdaBoost for Asymmetric Learning

       • Nikolaos Nikolaou, Gavin Brown

       Pages 112-124

   12. Building Classifier Ensembles Using Greedy Graph Edit Distance

       • Kaspar Riesen, Miquel Ferrer, Andreas Fischer

       Pages 125-134

   13. Measuring the Stability of Feature Selection with Applications to Ensemble Methods

       • Sarah Nogueira, Gavin Brown

       Pages 135-146

   14. Suboptimal Graph Edit Distance Based on Sorted Local Assignments

       • Kaspar Riesen, Miquel Ferrer, Horst Bunke

       Pages 147-156

3. Application and Evaluation

   1. Front Matter

      Pages 157-157

      PDF

   2. Multimodal PLSA for Movie Genre Classification

      • Hao-Zhi Hong, Jen-Ing G. Hwang

      Pages 159-167

   3. One-and-a-Half-Class Multiple Classifier Systems for Secure Learning Against Evasion Attacks at Test Time

      • Battista Biggio, Igino Corona, Zhi-Min He, Patrick P. K. Chan, Giorgio Giacinto, Daniel S. Yeung et al.

      Pages 168-180

   4. An Experimental Study on Combining Binarization Techniques and Ensemble Methods of Decision Trees

      • Juan J. Rodríguez, José F. Díez-Pastor, Álvar Arnaiz-González, César García-Osorio

      Pages 181-193

   5. Decision Tree-Based Multiple Classifier Systems: An FPGA Perspective

      • Mario Barbareschi, Salvatore Del Prete, Francesco Gargiulo, Antonino Mazzeo, Carlo Sansone

      Pages 194-205

This book constitutes the refereed proceedings of the 12th International Workshop on Multiple Classifier Systems, MCS 2015, held in Günzburg, Germany, in June/July 2015. The 19 revised papers presented were carefully reviewed and selected from 25 submissions. The papers address issues in multiple classifier systems and ensemble methods, including pattern recognition, machine learning, neural network, data mining and statistics. They are organized in topical sections on theory and algorithms and application and evaluation.

• Classification
• Classifier ensembles
• Classifier fusion
• Clustering
• Cost-sensitive
• Decision tree
• Ensemble learning
• Feature selection
• Feature weighting
• Kernel fusion
• Metalearning
• Movie genres
• Multi-class classification
• Parallel genetic algorithm
• Pattern recognition
• Social tags
• Stability
• Stepwise search algorithm
• Variable selection
• Visual features

• Ulm University, Ulm, Germany

  Friedhelm Schwenker

• University of Cagliari, Cagliari, Italy

  Fabio Roli

• University of Surrey, Guildford, United Kingdom

  Josef Kittler

Policies and ethics