| Foreword | p. vii |
| Preface | p. ix |
| Pattern Recognition: Evolution of Methodologies and Data Mining | p. 1 |
| Introduction | p. 2 |
| The pattern recognition problem | p. 3 |
| The statistical approach | p. 5 |
| The syntactic approach | p. 8 |
| Classification trees | p. 9 |
| The fuzzy set theoretic approach | p. 10 |
| The connectionist approach | p. 12 |
| Use of genetic algorithms | p. 14 |
| The hybrid approach and soft computing | p. 15 |
| Data mining and knowledge discovery | p. 16 |
| Conclusions | p. 18 |
| Imperfect Supervision in Statistical Pattern Recognition | p. 25 |
| Statistical pattern recognition | p. 26 |
| Preliminaries | p. 30 |
| Unsupervised learning | p. 38 |
| Models for imperfect supervision | p. 45 |
| Effect of imperfect supervision | p. 49 |
| Learning with an unreliable supervisor | p. 52 |
| Learning with a stochastic supervisor | p. 55 |
| Adaptive Stochastic Algorithms for Pattern Classification | p. 67 |
| Introduction | p. 67 |
| Learning automata | p. 75 |
| A common payoff game of automata for pattern classification | p. 82 |
| Three layer network consisting of teams of automata for pattern classification | p. 93 |
| Modules of learning automata | p. 103 |
| Discussion | p. 107 |
| Unsupervised Classification: Some Bayesian Approaches | p. 115 |
| Introduction | p. 115 |
| Finite mixtures of probability distributions | p. 117 |
| Bayesian approaches for mixture decomposition | p. 119 |
| Discussion | p. 133 |
| Shape In Images | p. 147 |
| High-level Bayesian image analysis | p. 148 |
| Prior models for objects | p. 149 |
| Inference | p. 154 |
| Multiple objects and occlusions | p. 157 |
| Warping and image averaging | p. 159 |
| Discussion | p. 161 |
| Decision Trees for Classification: A Review and Some New Results | p. 169 |
| Introduction | p. 169 |
| The different node splitting criteria | p. 171 |
| Pruning | p. 174 |
| Look-ahead | p. 176 |
| Other issues in decision tree construction | p. 176 |
| A new look-ahead criterion: some new results | p. 177 |
| Conclusions | p. 181 |
| Syntactic Pattern Recognition | p. 185 |
| Introduction | p. 186 |
| Primitive selection strategies | p. 188 |
| Formal linguistic model: basic definitions and concepts | p. 190 |
| High-dimensional pattern grammars | p. 194 |
| Structural recognition of imprecise patterns | p. 196 |
| Grammatical inference | p. 203 |
| Recognition of ill-formed patterns: error-correcting grammars | p. 221 |
| Fuzzy Sets as A Logic Canvas for Pattern Recognition | p. 231 |
| Introduction: fuzzy sets and pattern recognition | p. 232 |
| Fuzzy set-based transparent topologies of the pattern classifier | p. 233 |
| Supervised, unsupervised, and hybrid modes of learning | p. 245 |
| Conclusions | p. 253 |
| Fuzzy Pattern Recognition by Fuzzy Integrals and Fuzzy Rules | p. 257 |
| Introduction | p. 257 |
| Classification by fuzzy rules | p. 258 |
| Classification by fuzzy integrals | p. 266 |
| Neural Network Based Pattern Recognition | p. 281 |
| Introduction | p. 281 |
| The essence of pattern recognition | p. 282 |
| Advanced neural network architectures | p. 285 |
| Neural pattern recognition | p. 288 |
| Conclusions | p. 295 |
| Pattern Classification Based on Quantum Neural Networks: A Case Study | p. 301 |
| Introduction | p. 302 |
| Quantum neural networks | p. 303 |
| Wind profilers | p. 306 |
| Formulation of the bird removal problem | p. 309 |
| Experimental results | p. 313 |
| Conclusions | p. 325 |
| Networks of Spiking Neurons in Data Mining | p. 329 |
| Introduction | p. 330 |
| Graph algorithms | p. 332 |
| Clustering | p. 336 |
| Critical path method | p. 340 |
| The longest common subsequence | p. 342 |
| Conclusions | p. 344 |
| Genetic Algorithms, Pattern Classification and Neural Networks Design | p. 347 |
| Introduction | p. 348 |
| Overview of genetic algorithms | p. 351 |
| Description of the genetic classifiers | p. 353 |
| Determination of MLP architecture | p. 366 |
| Discussion and conclusions | p. 375 |
| Rough Sets in Pattern Recognition | p. 385 |
| Basic rough set approach | p. 385 |
| Searching for knowledge | p. 390 |
| Hybrid methods | p. 416 |
| Conclusions | p. 416 |
| Combining Classifiers: Soft Computing Solutions | p. 427 |
| Introduction | p. 427 |
| Classifier combination | p. 428 |
| Soft computing in classifier combination | p. 434 |
| Conclusions | p. 445 |
| Automated Generation of Qualitative Representations of Complex Objects by Hybrid Soft-Computing Methods | p. 453 |
| Introduction | p. 454 |
| Problem | p. 456 |
| Approach | p. 460 |
| Conclusions | p. 472 |
| Neuro-Fuzzy Models for Feature Selection and Classification | p. 475 |
| Introduction | p. 475 |
| A brief review | p. 477 |
| Neuro-fuzzy methods for feature selection | p. 480 |
| Neuro-fuzzy knowledge-based classification | p. 490 |
| Results | p. 494 |
| Conclusions and Discussion | p. 497 |
| Adaptive Segmentation Techniques for Hyperspectral Imagery | p. 507 |
| Introduction | p. 508 |
| Hyperspectral imaging system | p. 510 |
| Segmentation of hyperspectral imagery | p. 510 |
| Adaptive segmentation based on iterative local feature extraction | p. 512 |
| Adaptive unsupervised segmentation | p. 522 |
| Conclusions | p. 528 |
| Pattern Recognition Issues in Speech Processing | p. 531 |
| Introduction | p. 531 |
| Nature of speech signal | p. 535 |
| Feature extraction in speech | p. 539 |
| Pattern recognition models for speech recognition | p. 541 |
| Challenges in pattern recognition tasks in speech | p. 549 |
| Writing Speed and Writing Sequence Invariant On-Line Handwriting Recognition | p. 559 |
| Introduction | p. 559 |
| Writing speed invariance | p. 562 |
| Writing sequence invariance | p. 568 |
| Recognizer | p. 572 |
| Conclusions | p. 572 |
| Tongue Diagnosis Based on Biometric Pattern Recognition Technology | p. 575 |
| Introduction | p. 576 |
| Tongue image capturing | p. 582 |
| Segmentation of tongue images | p. 583 |
| Tongue feature extraction | p. 590 |
| Tongue classification | p. 594 |
| Conclusions | p. 595 |
| Index | p. 599 |
| About the editors | p. 611 |
| Table of Contents provided by Syndetics. All Rights Reserved. |
