AIML-Special Issue

AIML Cairo University ICGST

AIML Special Issue on: Multiple Classifier Systems

AIML ISSN: 1687-4846 Print, 1687-4854 Online, 1687-4862 CD-ROM

Universität Ulm ICGST   Cairo University        

Preface

During the past decade the method of combining multiple classifiers was established as a practical and effective approach to solve complex tasks in data mining and pattern recognition. It appears under many different names in the literature: Mixtures of experts, classifier ensembles, decision combination, multiple experts, sensor fusion networks, multiple classifier systems (MCS), etc. Many practical algorithms for combining classifiers were developed with the result that the combined system can perform with higher accuracy than each of the individual classifiers, e.g. in biometric verification systems. The formal theoretical analysis of MCS, in particular the application of MCS techniques to unsupervised clustering methods will play an increasing role in the future.

The purpose of this special issue is to bring together researchers from diverse communities working in the field of Multiple Classifier Systems to present and discuss the latest state of the art in this field.

Organized by: Neamat El Gayar and Friedhelm Schwenker

International Session Program Committee:

  • Amir Attia, Egypt

  • Hisham El-Shishiny, Egypt

  • Mohammed Kamel, Canada

  • Fabio Roli, Italy

  • Guenther Palm, Germany

  • Friedhelm Schwenker, Germany

  • Nayer Wanas, Egypt

Submission of Papers:

General templates and the referee's report of this issue.

Prospective authors should submit an electronic copy of their complete manuscript by email to hmg@link.net and friedhelm.schwenker@uni-ulm.de,  according to the mentioned timetable.  

All manuscripts will be reviewed by at least two reviewers by the organizers and program committee.

 Important Dates:

  • Submission:                        :  April 30, 2006

  • Notification of acceptance  :   May 30, 2006

  • Camera-ready                    :   June 30, 2006

 Contact Information:

 Neamat El Gayar (email: hmg@link.net )

Friedhelm Schwenker (email: friedhelm.schwenker@uni-ulm.de)

Submitted papers:

Supra Bayesian Classifier Combination

Waleed Fakhr

Computer Engineering Department, Arab Academy for Science and Technology

Heliopolis, Cairo, Egypt

Pages: 1-8

 

A Co-Training Approach for Semi-Supervised Multiple Classifiers

Mona Solyman, Neamat El Gayar

Faculty of Computers and Information, University of Cairo

5 Dr. Ahmed Zewail Street, 12613 Orman, Giza, Egypt

Pages: 9-16

 

Learning of Decision Fusion Mappings for Pattern Recognition

Friedhelm Schwenker, Christian R. Dietrich, Christian Thiel, Günther Palm

Department of Neural Information Processing, University of Ulm

89069 Ulm, Germany

Pages: 17-21

 

Combining Local Feature Scoring Methods for Text Categorization

Nayer M. Wanas(1), Dina A. Said(1), Nadia I. Hegazy(1), and Nevin M. Darwish(2)

(1) Pattern Recognition and Information Systems Group, Informatics Department, Electronics Research Institute, Cairo, Egypt

(2) Department of Computer Engineering, Faculty of Engineering, Cairo University, Cairo, Egypt

Pages: 23-33

 

Developing a Rule Extraction Methodology for Expert System Based Artificial Neural Network Ensembles

A. M. Sarhan (1), Waiel. F. Abd El-Wahed(2), T. E. Danf(3), M. Moselhy Tokhy(4)

(1) Math Dep., Faculty of Science, 2OR & DSS Dept. , Faculty of Computers and Information ,

(3) Math Dept., Faculty of Science, 4 Math Dept., Faculty of Science.

(1,2,3,4) Menofia University, Shebin El-Kom, Menofia, Egypt

Pages: 35-39