Pattern recognition (Record no. 3612)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 11658nam a22002057a 4500 |
| 020 ## - INTERNATIONAL STANDARD BOOK NUMBER | |
| International Standard Book Number | 9789380931623 |
| 040 ## - CATALOGING SOURCE | |
| Transcribing agency | CUS |
| 082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER | |
| Classification number | 006.4 |
| Item number | THE/P |
| 100 ## - MAIN ENTRY--PERSONAL NAME | |
| Personal name | Theodoridis, Sergios |
| 245 ## - TITLE STATEMENT | |
| Title | Pattern recognition |
| Statement of responsibility, etc. | Sergios Theodoridis and Konstantinos Koutroumbas |
| 250 ## - EDITION STATEMENT | |
| Edition statement | 4th ed. |
| 260 ## - PUBLICATION, DISTRIBUTION, ETC. (IMPRINT) | |
| Place of publication, distribution, etc. | Amsterdam: |
| Name of publisher, distributor, etc. | Elsevier, |
| Date of publication, distribution, etc. | 2009. |
| 300 ## - PHYSICAL DESCRIPTION | |
| Extent | xvii, 961 p. |
| Other physical details | ill. |
| 505 ## - FORMATTED CONTENTS NOTE | |
| Formatted contents note | 2.5.1 Maximum Likelihood Parameter Estimation 34<br/>2.5.2 Maximum « Posferfon Probability Estimation 38<br/>2.5.3 Bayesian Inference 39<br/>2.5.4 Maximum Entropy Estimation 43<br/>2.5.5 Mixture Models 44<br/>2.5.6 Nonparametric Estimation 49<br/>2.5.7 The Naive-Bayes Classifier 59<br/>The Nearest Neighbor Rule 61<br/>Bayesian Networks 64<br/>Problems 71<br/>References 86<br/>Linear Classifiers 91<br/>Introduction 91<br/>Linear Discriminant Functions and Decision<br/>Hyperplanes 91<br/>Tlie Perceptron Algorithm 93<br/>Least Squares Methods IO3<br/>3.4.1 Mean Square Error Estimation 103<br/>3.4.2 Stochastic Approximation and the LMS Algorithm .. 105<br/>3.4.3 Sum of Error Squares Estimation 108<br/>3.5 Mean Square Estimation Revisited 110<br/>3.5.1 Mean Square Error Regression 110<br/>3.5.2 MSE Estimates Posterior Class Probabilities 112<br/>3.5.3 The Bias-Variance Dilemma 114<br/>3.6 Logistic Discrimination 117<br/>3.7 Support Vector Machines II9<br/>3.7.1 Separable Classes II9<br/>3.7.2 Nonseparable Classes 124<br/>3.7.3 The Multiclass Case 127<br/>3.7.4 /^-SVM 133<br/>3.7.5 Support Vector Machines: A Geometric<br/>Viewpoint I36<br/>3.7.6 Reduced Convex Hulls 138<br/>3.8 Problems 142<br/>References 147<br/>CHAPTER 4 Nonlinear Classifiers 151<br/>4.1 Introduction 151<br/>4.2 The XOR Problem 151<br/>4.3 Tlie Two-Layer Perceptron 153<br/>4.3.1 Classification Capabilities of the Two-Layer<br/>Perceptron 156<br/>4.4 Three-Layer Perceptrons 158<br/>4.5 Algoritlims Based on Exact Classification of the<br/>Training Set l60<br/>4.6 The Backpropagation Algorithm l62<br/>4.7 Variations on the Backpropagation Theme 169<br/>4.8 Tlie Cost Function Choice 172<br/>4.9 Choice of the Network Size 176<br/>4.10 A Simulation Example 181<br/>4.11 Networks with Weight Sharing 183<br/>4.12 Generalized Linear Classifiers 185<br/>4.13 Capacity of the /-Dimensional Space in<br/>Linear Dichotomies<br/>4.14 Polynomial Classifiers 189<br/>4.15 Radial Basis Function Networks ^90<br/>4.16 Universal Approximators 19^<br/>4.17 Probabilistic Neural Networks ^96<br/>4.18 Support Vector Machines: The Nonlinear Case 198<br/>4.19 Beyond the SVM Paradigm 203<br/>4.19.1 Expansion in Kernel Functions and Model<br/>Sparsification 205<br/>4.19.2 Robust Statistics Regression 211<br/>4.20 Decision Trees 215<br/>4.20.1 Set of Questions 218<br/>4.20.2 Splitting Criterion 218<br/>4.20.3 Stop-Splitting Rule 219<br/>4.20.4 Class Assignment Rule 219<br/>4.21 Combining Classifiers 222<br/>4.21.1 Geometric Average Rule 223<br/>4.21.2 Arithmetic Average Rule 224<br/>4.21.3 Majority Voting Rule 225<br/>4.21.4 A Bayesian Viewpoint 227<br/>4.22 The Boosting Approach to Combine Classifiers 230<br/>4.23 The Class Imbalance Problem 237<br/>4.24 Discussion 239<br/>4.25 Problems 240<br/>References 249<br/>CHAPTER 5 Feature Selection 261<br/>5.1 Introduction 261<br/>5.2 Preprocessing 262<br/>5.2.1 Outlier Removal 262<br/>5.2.2 Data Normalization 263<br/>5.2.3 Missing Data 263<br/>5.3 The Peaking Phenomenon 265<br/>5.4 Feature Selection Based on Statistical<br/>Hypothesis Testing 268<br/>5.4.1 Hypothesis Testing Basics 268<br/>5.4.2 Application of the f-Test in Feature Selection 273<br/>5.5 The Receiver Operating Characteristics (ROC) Curve 275<br/>5.6 Class Separability Measures 276<br/>5.6.1 Divergence 276<br/>5.6.2 Chernoff Bound and Bhattacharyya Distance 278<br/>5.6.3 Scatter Matrices 280<br/>5.7 Feature Subset Selection 283<br/>5.7.1 Scalar Feature Selection 283<br/>5.7.2 Feature Vector Selection 284<br/>5.8 Optimal Feature Generation 288<br/>5.9 Neural Networks and Feature Generation/Selection 298<br/>5.10 A Hint On Generalization Theory 299<br/>5.11 The Bayesian Information Criterion 309<br/>5.12 Problems 311<br/>References 318<br/>CHAPTER 6 Feature Generation I: Data Transformation and<br/>Dimensionality Reduction 323<br/>6.1 Introduction 323<br/>6.2 Basis Vectors and Images 324<br/>6.3 The Karhunen-Loeve Transform 326<br/>6.4 The Singular Value Decomposition 335<br/>6.5 Independent Component Analysis 342<br/>6.6<br/>6.5.1 ICA Based on Second- and Fourth-Order<br/>Cumulants 344<br/>6.5.2 ICA Based on Mutual Information 345<br/>6.5.3 An ICA Simulation Example 348<br/>Nonnegative Matrix Factorization 349<br/>6.7 Nonlinear Dimensionality Reduction 35O<br/>6.8<br/>6.9<br/>6.10<br/>6.7.1 Kernel PCA 35I<br/>6.7.2 Graph-Based Methods 353<br/>The Discrete FourierTransform (DFT) 363<br/>6.8.1 One-Dimensional DFT 364<br/>6.8.2 Two-Dimensional DFT 366<br/>The Discrete Cosine and Sine Transforms 366<br/>The Hadamard Transform 368<br/>6.11 The Haar Transform 369<br/>6.12 The Haar Expansion Revisited 37I<br/>6.13 Discrete Time Wavelet Transform (DTWT) 375<br/>6.14 The Multiresolution Interpretation 384<br/>6.15 Wavelet Packets jg7<br/>6.16 A Look atTwo-Dimensional Generalizations 388<br/>0-17 Applications<br/>6.18 Problems<br/>References<br/>CHAPTER 7 Feature Generation II 4..<br/>7.1 Introduction<br/>T.2 Regional Features | ^'" * * ^ ^ 2<br/>7.2 2 Locl^ forTexture Characterization 412<br/>Exttactir f^^Texture Feature<br/>7-2.3 Moments<br/>■7-2.4 Parametric Models<br/>7.3 Features for Shape and Size Characterization 435<br/>7.3.1 Fourier Features 436<br/>7.3.2 Chain Codes 439<br/>7.3.3 Moment-Based Features 441<br/>7.3.4 Geometric Features 442<br/>7.4 A Glimpse at Fractals 444<br/>7.4.1 Self-Similarity and Fractal Dimension 444<br/>7.4.2 Fractional Brownian Motion 446<br/>7.5 Typical Features for Speech and Audio Classification 451<br/>7.5.1 ShortTime Processing of Signals 452<br/>7.5.2 Cepstrum 455<br/>7.5.3 The Mel-Cepstrum 457<br/>7.5.4 Spectral Features 460<br/>7.5.5 Time Domain Features 462<br/>7.5.6 An Example 463<br/>7.6 Problems 466<br/>References 473<br/>CHAPTER 8 Template Matching 48i<br/>8.1 Introduction 481<br/>8.2 Measures Based on Optimal Path Searching Techniques 482<br/>8.2.1 Bellman's Optimality Principle and Dynamic<br/>Programming 484<br/>8.2.2 The Edit Distance 487<br/>8.2.3 Dynamic Time Warping in Speech Recognition 491<br/>8.3 Measures Based on Correlations 498<br/>8.4 Deformable Template Models 504<br/>8.5 Content-Based Information Retrieval:<br/>Relevance Feedback 5O8<br/>8.8 Problems 513<br/>References<br/>CHAPTER 9 Context-Dependent Classification 521<br/>9.1 Introduction<br/>9.2 The Bayes Classifier 52i<br/>9.3 Markov Chain Models 522<br/>9.4 The Viterbi Algorithm 523<br/>9.5 Channel Equalization 527<br/>9.6 Hidden Markov Models 552<br/>9.7 HMM with State Duration Modeling 545<br/>9.8 Training Markov Models via Neural Networks 552<br/>9.9 A discussion of Markov Random Fields 554<br/>9.10 Problems 556<br/>References 560<br/>CHAPTER 10 3L!r)';i v'ssfJ Learning; The Epilogue 567<br/>10.1 Introduction 567<br/>10.2 Error-Counting Approach 568<br/>10.3 Exploiting the Finite Size of the Data Set 569<br/>10.4 A Case Study from Medical Imaging 573<br/>10.5 Semi-Supervised Learning 577<br/>10.5.1 Generative Models 579<br/>10.5.2 Graph-Based Methods 582<br/>10.5.3 Transductive Support Vector Machines 586<br/>10.6 Problems 590<br/>References 591<br/>CHAPTER 11 Clustering; Basic Concepts 595<br/>11.1 Introduction 595<br/>11.1.1 Applications of Cluster Analysis 598<br/>11.1.2 Types of Features 599<br/>11.1.3 Definitions of Clustering 600<br/>11.2 Proximit}' Measures 602<br/>11.2.1 Definitions 602<br/>11.2.2 Proximity Measures between Two Points 604<br/>11.2.3 Proximity Functions between a Point and a Set 6l6<br/>11.2.4 Proximity Functions between Two Sets 620<br/>11.3 Problems 622<br/>References 624<br/>CHAPTER 12 Clustering Algorithms I: Sequential Algorithms 627<br/>12.1 Introduction 627<br/>12.1.1 Number of Possible Clusterings 627<br/>12.2 Categories of Clustering Algorithms 629<br/>12.3 Sequential Clustering Algorithms 633<br/>Estimation of the Number of Clusters 635<br/>12.4 A Modification of BSAS 637<br/>12.5 A Two-Threshold Sequential Scheme 638<br/>"2.6 Refinement Stages 641<br/>Neural Network Implementation 643<br/>12^^ of the Architecture 643<br/>^•2 Implementation of the BSAS Algoritlim 644<br/>12.8 Problems 646<br/>References 650<br/>CHAPTER 13 Clustering Algorithms II: Hierarchical Algorithms 653<br/>13.1 Introduction 653<br/>13.2 Agglomerative Algorithms 654<br/>13.2.1 Definition of Some Useful Quantities 655<br/>13.2.2 Agglomerative Algorithms Based on Matrix Theory . 658<br/>13.2.3 Monotonicity and Crossover 664<br/>13.2.4 Implementational Issues 667<br/>13.2.5 Agglomerative Algorithms Based on Graph Theory.. 667<br/>13.2.6 Ties in the Proximity Matrix 676<br/>13.3 The Cophenetic Matrix 679<br/>13.4 Divisive Algorithms 680<br/>13.5 Hierarchical Algorithms for Large Data Sets 682<br/>13.6 Choice of the Best Number of Clusters 690<br/>13.7 Problems 693<br/>References 697<br/>CHAPTER 14 Clustering Algorithms III: Schemes Based on<br/>Function Optimization 701<br/>14.1 Introduction 701<br/>14.2 Mixture Decomposition Schemes 703<br/>14.2.1 Compact and Hyperellipsoidal Clusters 705<br/>14.2.2 A Geometrical Interpretation 709<br/>14.3 Fuzzy Clustering Algorithms 712<br/>14.3.1 Point Representatives 716<br/>14.3.2 Quadric Surfaces as Representatives 718<br/>14.3.3 Hyperplane Representatives 728<br/>14.3.4 Combining Quadric and Hyperplane<br/>Representatives 731<br/>14.3.5 A Geometrical Interpretation 732<br/>14.3.6 Convergence Aspects of the Fuzzy Clustering<br/>Algorithms 732<br/>14.3.7 Alternating Cluster Estimation 733<br/>14.4 Possibilistic Clustering 733<br/>14.4.1 The Mode-Seeking Property 737<br/>14.4.2 An Alternative Possibilistic Scheme 739<br/>14.5 Hard Clustering Algorithms 739<br/>14.5.1 The Isodata or k-Means or c-Means Algorithm 741<br/>14.5.2 ife-Medoids Algorithms 745<br/>14.8 Vector Quantization 749<br/>14.7 Problems 752<br/>References 758<br/>CHAPTER 15 Clustering Algorithms IV 765<br/>15.1 Introduction 765<br/>15.2 Clustering Algorithms Based on Graph Theory 765<br/>15.2.1 Minimum Spanning Tree Algorithms 766<br/>15.2.2 Algorithms Based on Regions of Influence 768<br/>15.2.3 Algorithms Based on Directed Trees 770<br/>15.2.4 Spectral Clustering 772<br/>15.3 Competitive Learning Algorithms 780<br/>15.3 .1 Basic Competitive Learning Algorithm 782<br/>15.3.2 Leaky Learning Algorithm 783<br/>15.3.3 Conscientious Competitive Learning Algoritlims— 784<br/>15.3.4 Competitive Learning-Like Algorithms Associated<br/>with Cost Functions 785<br/>15.3.5 Self-Organizing Maps 786<br/>15.3.6 Supervised Learning Vector Quantization 788<br/>15.4 Binary Morphology Clustering Algorithms (BMCAs) 789<br/>15.4.1 Discretization 790<br/>15.4.2 Morphological Operations 791<br/>15.4.3 Determination of the Clusters in a Discrete Binary<br/>Set 794<br/>15.4.4 Assignment of Feature Vectors to Clusters 795<br/>15.4.5 Tlie Algorithmic Scheme 796<br/>15.5 Boundary Detection Algorithms 798<br/>15.6 Valley-Seeking Clustering Algorithms 801<br/>15.7 Clustering via Cost Optimization (Revisited) 803<br/>15.7.1 Branch and Bound Clustering Algorithms 803<br/>15.7.2 Simulated Annealing 807<br/>15.7.3 Deterministic Annealing 808<br/>15.7.4 Clustering Using Genetic Algoritlims 810<br/>15.8 Kernel Clustering Methods 811<br/>15.9 Density-Based Algorithms for Large Data Sets 815<br/>15.9.1 The DBSCAN Algorithm 815<br/>15.9.2 TheDBCLASDAlgoritlim 818<br/>15.9.3 The DENCLUE Algorithm 819<br/>15.10 Clustering Algorithms for High-Dimensional Data Sets 821<br/>15.10.1 Dimensionality Reduction Clustering Approach — 822<br/>15.10.2 Subspace Clustering Approach 824<br/>15.11 Other Clustering Algorithms 837<br/>15.12 Combination of Clusterings 839<br/>15.13 Problems 846<br/>References 852<br/>CHAPTER 16 Cluster Validity 863<br/>16.1 Introduction 863<br/>16.2 Hypothesis Testing Revisited 864<br/>16.3 Hypothesis Testing in Cluster Validity 866<br/>16.3.1 External Criteria 868<br/>16.3.2 Internal Criteria 873<br/>16.4 Relative Criteria 877<br/>16.4.1 Hard Clustering 880<br/>16.4.2 Fuzzy Clustering 887<br/>16.5 Validity of Individual Clusters 893<br/>16.5.1 External Criteria 894<br/>16.5.2 Internal Criteria 894<br/>16.6 Clustering Tendency 896<br/>16.6.1 Tests for Spatial Randomness 900<br/>16.7 Problems 905<br/>References 909 |
| 650 ## - SUBJECT | |
| Keyword | Pattern recognition |
| 650 ## - SUBJECT | |
| Keyword | Biometrics |
| 650 ## - SUBJECT | |
| Keyword | Bioinformatics |
| 650 ## - SUBJECT | |
| Keyword | Dynamic programming |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
| Koha item type | GN Books |
| Withdrawn status | Lost status | Damaged status | Not for loan | Home library | Current library | Shelving location | Date acquired | Full call number | Accession number | Date last seen | Koha item type |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Central Library, Sikkim University | Central Library, Sikkim University | General Book Section | 26/06/2016 | 006.4 THE/P | P35938 | 26/06/2016 | General Books |