edited by H Bunke (University of Bern, Switzerland) & A Kandel (University of South Florida, USA)

Table of Contents (54k)
Preface (81k)
Chapter1: Fuzzification of Neural Networks for Classification Problems
Chapter 1.1: Indroduction (133k)
Chapter 1.2: Classification of Fuzzy Patterns by Trained Neural Networks (316k)
Chapter 1.3: Training of Neural Networks from Fuzzy Training Patterns (231k)
Chapter 1.4: Linguistic Rule Extraction from Neural Networks (175k)
Chapter 1.5: Training of Neural Networks from Linguistic Rules (212k)
Chapter 1.6: Interval-Arithmetic-Based Neural Networks (260k)
Chapter 1.7: Conclusion (133k)

About the Editor

Horst Bunke has been Vice President and Acting President of the International Association for Pattern Recognition (IAPR). He is a Fellow of the IAPR. He is also an associate editor of the International Journal on Document Analysis and Recognition, Pattern Analysis and Applications, editor-in-charge of the International Journal of Pattern Recognition and Artificial Intelligence, editor-in-chief of the Electronic Letters of Computer Vision and Image Analysis, and editor-in-chief of this series, Machine Perception and Artificial Intelligence. He was on the program and organization committee of many conferences and served as a referee for numerous journals and scientific organizations. He has about 400 publications, including more than 20 books and special editions of journals.
 

The field of pattern recognition has seen enormous progress since its beginnings almost 50 years ago. A large number of different approaches have been proposed. Hybrid methods aim at combining the advantages of different paradigms within a single system.

Hybrid Methods in Pattern Recognition is a collection of articles describing recent progress in this emerging field. It covers topics such as the combination of neural nets with fuzzy systems or hidden Markov models, neural networks for the processing of symbolic data structures, hybrid methods in data mining, the combination of symbolic and subsymbolic learning, and others. Also included is recent work on multiple classifier systems. Furthermore, the book deals with applications in on-line and off-line handwriting recognition, remotely sensed image interpretation, fingerprint identification, and automatic text categorization.

• Neuro-Fuzzy Systems:
  • Fuzzification of Neural Networks for Classification Problems (H Ishibuchi & M Nii)
• Neural Networks for Structural Pattern Recognition:
  • Adaptive Graphic Pattern Recognition: Foundations and Perspectives (G Adorni et al.)
  • Adaptive Self-Organizing Map in the Graph Domain (S Günter & H Bunke)
• Clustering for Hybrid Systems:
  • From Numbers to Information Granules: A Study in Unsupervised Learning and Feature Analysis (A Bargiela & W Pedrycz)
• Combining Neural Networks and Hidden Markov Models:
  • Combination of Hidden Markov Models and Neural Networks for Hybrid Statistical Pattern Recognition (G Rigoll)
  • From Character to Sentences: A Hybrid Neuro-Markovian System for On-Line Handwriting Recognition (T Artières et al.)
• Multiple Classifier Systems:
  • Multiple Classifier Combination: Lessons and Next Steps (T K Ho)
  • Design of Multiple Classifier Systems (F Roli & G Giacinto)
  • Fusing Neural Networks Through Fuzzy Integration (A Verikas et al.)
• Applications of Hybrid Systems:
  • Hybrid Data Mining Methods in Image Processing (A Klose & R Kruse)
  • Robust Fingerprint Identification Based on Hybrid Pattern Recognition Methods (D-W Jung & R-H Park)
  • Text Categorization Using Learned Document Features (M Junker et al.)