Hugendubel.info - Die B2B Online-Buchhandlung 

Merkliste
Die Merkliste ist leer.
Bitte warten - die Druckansicht der Seite wird vorbereitet.
Der Druckdialog öffnet sich, sobald die Seite vollständig geladen wurde.
Sollte die Druckvorschau unvollständig sein, bitte schliessen und "Erneut drucken" wählen.

Applied Soft Computing Technologies: The Challenge of Complexity

E-BookPDF1 - PDF WatermarkE-Book
840 Seiten
Englisch
Springer Berlin Heidelbergerschienen am11.08.20062006
This volume presents the proceedings of the 9th Online World Conference on Soft Computing in Industrial Applications, held on the World Wide Web in 2004. It includes lectures, original papers and tutorials presented during the conference. The book brings together outstanding research and developments in soft computing, including evolutionary computation, fuzzy logic, neural networks, and their fusion, and its applications in science and technology.mehr
Verfügbare Formate
BuchKartoniert, Paperback
EUR320,99
E-BookPDF1 - PDF WatermarkE-Book
EUR309,23

Produkt

KlappentextThis volume presents the proceedings of the 9th Online World Conference on Soft Computing in Industrial Applications, held on the World Wide Web in 2004. It includes lectures, original papers and tutorials presented during the conference. The book brings together outstanding research and developments in soft computing, including evolutionary computation, fuzzy logic, neural networks, and their fusion, and its applications in science and technology.
Details
Weitere ISBN/GTIN9783540316626
ProduktartE-Book
EinbandartE-Book
FormatPDF
Format Hinweis1 - PDF Watermark
FormatE107
Erscheinungsjahr2006
Erscheinungsdatum11.08.2006
Auflage2006
ReiheAdvances in Intelligent and Soft Computing
Reihen-Nr.34
Seiten840 Seiten
SpracheEnglisch
IllustrationenXXXIII, 840 p. 324 illus.
Artikel-Nr.1423625
Rubriken
Genre9200

Inhalt/Kritik

Inhaltsverzeichnis
1;WSC9 - Honorary Chair s Message;6
2;WFSC Chairperson s Message;7
3;WSC9 Chair s Welcome Message;8
4;WSC9 - Organization;10
5;WSC9 Technical Sponsors;14
6;Contents;16
7;List of Contributors;24
8;Part I Plenary Presentations;36
8.1;Applying Fuzzy Sets to the SemanticWeb: The Problem of Retranslation;37
8.1.1;1. Computing with Words and the SemanticWeb;37
8.1.2;2. The Retranslation Process;38
8.1.3;3. Determining the Validity of a Retranslation;39
8.1.4;4. Measuring the Closeness of Fuzzy Subsets;41
8.1.5;5. Measuring the Fuzziness and Specificity;42
8.1.6;6. Providing Retranslations that Give Particular Perceptions;44
8.1.7;7. Multicriteria Evaluation;49
8.1.8;8. Conclusion;51
8.1.9;9. References;52
8.2;Granular Computing: An Overview;53
8.2.1;1. From Information Granules to Granular Computing;53
8.2.2;2. Formalisms of Granular Computing;55
8.2.2.1;2.1. Interval analysis;55
8.2.2.2;2.2. Fuzzy sets;56
8.2.2.3;2.3. Rough sets;59
8.2.3;3. The Development of Information Granules;61
8.2.4;4. Quantifying Granularity: Generality Versus Specificity;62
8.2.5;5. Communication between Systems of Information Granules;63
8.2.6;6. Granular Computing and Computational Intelligence;65
8.2.7;7. Conclusions;67
8.2.8;References;67
9;Part II Classification and Clustering;70
9.1;Parallel Neuro Classifier for Weld Defect Classification;71
9.1.1;1 Introduction;71
9.1.2;2 Neural Networks;73
9.1.2.1;2.1 Selection of Classifier;73
9.1.2.2;2.2 Classifier Performance Evaluation Methods;74
9.1.3;3 LVQ Implementation on PARAM 10000;74
9.1.3.1;3.1 Single Architecture Single Processor;74
9.1.3.2;3.2 Single Architecture Multiple Processor;76
9.1.4;5 Neural Networks Modeling for Weld Classification;78
9.1.4.1;5.1 Input and Output Parameters;78
9.1.4.2;5.2 Neural Network Architecture and Training;79
9.1.5;6 Results and Discussion;80
9.1.5.1;6.1 Results from Single Architecture Single Processor Simulator;80
9.1.5.2;6.2 Single Architecture Multiple Processor;84
9.1.6;7 Summary;85
9.1.7;Acknowledgments;86
9.1.8;References;86
9.1.9;Appendix: Brief Introduction to PARAM 10000;88
9.2;An Innovative Approach to Genetic Programming-based Clustering;89
9.2.1;1 Introduction;89
9.2.2;2 Data Clustering;90
9.2.3;3 Our Genetic Programming System for Data Clustering;91
9.2.4;4 Evaluation Indices and Database;94
9.2.5;5 Experimental Findings;95
9.2.6;6 Conclusions and Future Work;97
9.2.7;References;98
9.3;An Adaptive Fuzzy Min-Max Conflict-Resolving Classifier;99
9.3.1;1 Introduction;100
9.3.2;2 The Ordering Algorithm, Fuzzy ARTMAP, and Dynamic Decay Adjustment Algorithm;101
9.3.3;2.2 Fuzzy ARTMAP (FAM);102
9.3.4;2.3 Dynamic Decay Adjustment (DDA) Algorithm;103
9.3.5;3 The Ordered FAMDDA;104
9.3.6;4 Benchmark Datasets: Experiments and Results;105
9.3.7;5 The Circulating Water (CW) System;107
9.3.8;6 Summary;109
9.3.9;Acknowledgements;109
9.4;A Method to Enhance the Possibilistic C-Means with Repulsion Algorithm based on Cluster Validity Index;111
9.4.1;1 Introduction;111
9.4.2;3. Possibilistic Fuzzy Clustering with Repulsion;114
9.4.3;4. Tests Examples;115
9.4.4;5. Conclusions;119
9.4.5;References;120
10;Part III Optimization;123
10.1;Design Centering and Tolerancing with Utilization of Evolutionary Techniques;125
10.1.1;1 Introduction;125
10.1.2;2 Design Centering and Tolerancing Methods;126
10.1.3;3 New Method Description;126
10.1.4;4 Computational Examples;128
10.1.5;5 Conclusions;131
10.1.6;References;132
10.2;Curve Fitting with NURBS using Simulated Annealing;133
10.2.1;1 Introduction;133
10.2.2;2 Literature Survey;134
10.2.3;3 NURBS;135
10.2.4;4 Simulated Annealing;136
10.2.5;5 The Proposed Method;139
10.2.6;6 Experimental Results;143
10.2.7;7 Conclusions;144
10.2.8;Acknowledgement;145
10.2.9;References;145
10.3;Multiobjective Adaptive Representation Evolutionary Algorithm (MAREA) - a new evolutionary algorithm for multiobjective optimization;147
10.3.1;1 Introduction;147
10.3.2;2 AREA Technique;148
10.3.2.1;2.1 Solution representation;148
10.3.2.2;2.2 Mutation;148
10.3.2.3;2.3 Transmutation;148
10.3.2.4;2.4 O.spring acceptance;149
10.3.3;3 MAREA Algorithm;149
10.3.3.1;3.1 Stage I - Convergence to the Pareto front;149
10.3.3.2;3.2 Stage II - Dispersion on the Pareto front.;150
10.3.4;4 Test Functions;150
10.3.5;5 Performance Metrics;151
10.3.5.1;5.1 Convergence metric;151
10.3.6;6 Numerical Experiments;152
10.3.7;7 Conclusions and Further Work;152
10.3.8;References;155
10.4;Adapting Multi-Objective Meta-Heuristics for Graph Partitioning;157
10.4.1;1 Introduction;157
10.4.2;2 The Graph Partitioning Problem;158
10.4.3;3 Adapting Local Search MOMHs for GPP;159
10.4.3.1;3.1 Sera.ni s Multi-Objective Simulated Annealing (SMOSA);159
10.4.3.2;3.2 Ulungu s Multi-Objective Simulated Annealing (UMOSA);160
10.4.3.3;3.3 Czyzak s Pareto Simulated Annealing (PSA);161
10.4.3.4;3.4 Hansen s Multi-Objective Tabu Search (MOTS);162
10.4.4;4 Experimental Results;162
10.4.4.1;4.1 Parameter Setting;163
10.4.4.2;4.2 Metrics used to evaluate the quality of the solutions;163
10.4.4.3;4.3 Analysis of the results;164
10.4.5;5 Conclusions;165
10.4.6;Acknowledges;165
10.4.7;References;166
11;Part IV Diagnosis and Fault Tolerance;168
11.1;Genetic Algorithms for Artificial Neural Net-based Condition Monitoring System Design for Rotating Mechanical Systems;169
11.1.1;Introduction;170
11.1.2;Using Genetic Algorithms and ANNs;171
11.1.3;Artificial Neural Networks;173
11.1.4;Problem Description and Methods;174
11.1.5;Feature Extraction;175
11.1.6;Implementation;177
11.1.7;Results and Discussion;180
11.1.8;Conclusion and Future Work;181
11.1.9;Acknowledgments;182
11.1.10;References;182
11.2;The Applications of Soft Computing in Embedded Medical Advisory Systems for Pervasive Health Monitoring;185
11.2.1;1 Introduction;185
11.2.2;2 Building the Medical Knowledge Base;186
11.2.2.1;2.1 Temporal Fuzzy Variables;187
11.2.2.2;2.2 Weighted Medical Rules;188
11.2.3;3 Embedded Medical Advisory Systems;189
11.2.3.1;3.1 Accompanied Knowledge Base;190
11.2.3.2;3.2 Inference Machine;190
11.2.3.3;3.3 Shell;191
11.2.4;4 Prototyping System;192
11.2.5;5 Conclusion;193
11.2.6;Acknowledgments;193
11.2.7;References;194
11.3;Application of Fuzzy Inference Techniques to FMEA;195
11.3.1;1. Introduction;195
11.3.2;2. Failure Risk Evaluation, Ranking, and Prioritization Issues in FMEA;196
11.3.3;3. Fuzzy Production Rules and Weighted Fuzzy Production Rules;197
11.3.4;4. A Generic Modeling Approach to the Fuzzy RPN Function;198
11.3.4.1;4.1 Fuzzy Membership Functions;198
11.3.4.2;4.2 Fuzzy Rule Base;199
11.3.4.3;4.3 Properties of the Proposed Fuzzy RPN Model;200
11.3.4.3.1;4.3.1 Monotone output;200
11.3.4.3.2;4.3.2 Output resolution (Sensitivity of output to the changes of input);200
11.3.5;5. A Case Study on the Test Handler Process;200
11.3.5.1;5.1 Experiment I Failure Risk Evaluation, Ranking, and Prioritization -;201
11.3.5.2;5.2 Experiment II Study of the monotone property -;202
11.3.5.3;5.3 Experiment III Study of the output resolution property -;203
11.3.6;6. Conclusion;204
11.3.7;7. References;204
11.4;Bayesian Networks Approach for a Fault Detection and Isolation Case Study;207
11.4.1;1 Introduction;207
11.4.2;2 Bayesian Networks Approach for FDI;208
11.4.3;3 Benchmark Specifications;209
11.4.4;4 Performance Indices;210
11.4.5;5 The FDI System;211
11.4.5.1;5.1 Train and Test Synthetic Data;211
11.4.5.2;5.2 FDI on Synthetic Data;212
11.4.5.3;5.3 FDI on Real Data;213
11.4.6;6 Conclusions;216
11.4.7;Acknowledgments;216
11.4.8;References;216
12;Part V Tracking and Surveillance;219
12.1;Path Planning Optimization for Mobile Robots Based on Bacteria Colony Approach;221
12.1.1;1 Introduction;221
12.1.2;2 Bacteria Colony;222
12.1.3;3 Trajectory Planning of Mobile Robots;225
12.1.4;4 Simulation Results;226
12.1.4.1;4.1 Case study 1: Environment with 4 obstacles;226
12.1.4.2;4.2 Case study 2: Environment with 12 obstacles;228
12.1.5;5 Conclusion and future works;231
12.1.6;References;231
12.2;An Empirical Investigation of Optimum Tracking with Evolution Strategies;233
12.2.1;1 Introduction;233
12.2.2;2 Related Work;234
12.2.3;3 Methodology;235
12.2.4;4 Results;236
12.2.4.1;4.1 Linear dynamics and linear dependence on population size;237
12.2.4.2;4.2 Linear dynamics and squared dependence on population size;239
12.2.4.3;4.3 Random dynamics;240
12.2.5;5 Conclusion;240
12.2.6;References;241
12.3;Implementing a Warning System for Stromboli Volcano;243
12.3.1;1 Introduction;243
12.3.2;2 System The Stromboli Volcanic Areas and the THEODORO;245
12.3.2.1;2.1 The THEODORO Measuring System;245
12.3.3;3 Data Analysis;246
12.3.3.1;3.1 Estimating DMVSD;249
12.3.3.2;3.1 Estimating MPEASD;249
12.3.4;4 Implementing a Warning System for THEODOROS;250
12.3.5;5 Conclusions;252
12.3.6;References;252
13;Part VI Scheduling and Layout;254
13.1;A Genetic Algorithm with a Quasi-local Search for the Job Shop Problem with Recirculation;255
13.1.1;1 Introduction;255
13.1.2;2 Classical Job Shop and Job Shop with Recirculation;256
13.1.2.1;2.1 Disjunctive Graph;256
13.1.2.2;2.2 Complexity and Types of Solutions;257
13.1.2.3;2.3 Neighbourhood Schemes;257
13.1.3;3 Proposed Methodology;258
13.1.3.1;3.1 Solution Representation;259
13.1.3.2;3.2 Solutions Decoding;259
13.1.3.3;3.3 Genetic Correction;261
13.1.3.4;3.4 Genetic Operators;261
13.1.3.5;3.5 The Genetic Algorithm;263
13.1.4;4 Computational Experiments;263
13.1.5;5 Conclusions;266
13.1.6;References;266
13.2;A Multiobjective Metaheuristic for Spatial-based Redistricting;269
13.2.1;1 Introduction;269
13.2.2;2 The Multiobjective Metaheuristic;270
13.2.2.1;2.1 General Redistricting Problem Definition;270
13.2.2.2;2.2 Seed Solution Initiator;271
13.2.2.3;2.3 Neighbouring Move and Generated Subset Combination;272
13.2.2.4;2.4 Multiobjective Decision Rules and Measurement;273
13.2.3;3 Experiment;274
13.2.3.1;3.1 Analysis of the Coverage of Approximation of Non- Dominated set;277
13.2.3.1.1;3.1.1 Analysis of the Distance Measurement for Dominancy Comparison;277
13.2.3.1.2;3.1.2 The -value;278
13.2.3.1.3;3.1.3 The -parameter;279
13.2.3.2;3.2 Analysis of the Number of Objectives Defined;279
13.2.4;4 Conclusion;279
13.2.5;5 References;281
13.2.6;Appendix: Algorithm for the proposed multiobjective metaheuristic;282
13.3;Solving Facility Layout Problems with a Set of Geometric Hard-constraints using Tabu Search;285
13.3.1;1 Introduction;285
13.3.2;2 Problem Scope;286
13.3.2.1;2.1 Objective Function;287
13.3.3;3 Solution Approach;288
13.3.3.1;3.1 Improvement on the Initial Solution;289
13.3.3.2;3.2 Tabu List Configuration;290
13.3.3.3;3.3 Neighborhood Structures;290
13.3.3.4;3.4 Strategy of Prohibition and of Liberation;290
13.3.4;4 Results;291
13.3.5;5 Conclusion;292
13.3.6;Acknowledgments;295
13.3.7;References;295
14;Part VII Complexity Management;298
14.1;Empathy: A Computational Framework for Emotion Generation;299
14.1.1;1 Introduction;299
14.1.2;2 The Empathy Model;300
14.1.3;3 Emotions and A.ective Phenomena;302
14.1.3.1;3.1 Emotion Blends and Mixed Emotions;303
14.1.3.2;3.2 Emotion Intensity;304
14.1.4;4 Emotional Behaviors;304
14.1.4.1;4.1 Behavior Selection;305
14.1.5;5 Cindy;307
14.1.5.1;5.1 Implementation details;308
14.1.6;6 Conclusions and Future Work;310
14.1.7;References;310
14.2;Intelligent Forecast with Dimension Reduction;313
14.2.1;1 Introduction;313
14.2.2;2 Time-series Prediction;314
14.2.3;3 Inductive Learning;315
14.2.3.1;3.1 Multi Layer Perceptron (MLP);316
14.2.3.2;3.2 Support Vector Regression (SVR);316
14.2.4;4 Model Selection;317
14.2.4.1;4.1 Simulated Annealing;317
14.2.5;5 Dimension Reduction;318
14.2.5.1;5.1 Analysis (PCA) Linear Dimension Reduction with Principal Component;318
14.2.5.2;5.2 Component Analysis (KPCA) Non-linear Dimension Reduction with Kernel Principal;319
14.2.6;6 Meta-Heuristic;320
14.2.7;7 Time-Series Prediction Framework;320
14.2.8;8 Experiments;321
14.2.9;9 Conclusions;324
14.2.10;References;325
14.3;Stochastic Algorithm Computational Complexity Comparison on Test Functions;327
14.3.1;1 Introduction;327
14.3.2;2 Brief on Test Case Stochastic Algorithms;328
14.3.2.1;2.1 Evolutionary Strategy ES-(1+1);328
14.3.2.2;2.2 Evolution Strategy Self-Adaptation ES-(1+5)-sSA;329
14.3.2.3;2.3 Di.erential Evolution (DE/rand/1/bin);331
14.3.2.4;2.4 Particle Swarm Optimization (PSO);332
14.3.3;3 Stochastic Algorithm Computational Complexity Comparison: Test Set-Up;333
14.3.3.1;3.1 Test Functions;334
14.3.3.2;3.2 Results;335
14.3.4;4 A New Hybrid Algorithm: PSO-DE;335
14.3.5;5 Conclusions;336
14.3.6;References;336
14.4;Nonlinear Identification Method of a Yo-yo System Using Fuzzy Model and Fast Particle Swarm Optimisation;337
14.4.1;1. Introduction;337
14.4.2;2. Takagi-Sugeno Fuzzy System;338
14.4.3;3. PSO for Optimization of TS Fuzzy System;340
14.4.3.1;3.1. Fast Particle Swarm Optimisation;342
14.4.4;4. Yo-yo Motion Process;343
14.4.5;5. Analysis Results of Identification;345
14.4.6;6. Conclusion and Future Works;347
14.4.7;References;347
15;Part VIII Manufacturing and Production;350
15.1;Hybrid Type-1-2 Fuzzy Systems for Surface Roughness Control;351
15.1.1;1 Introduction;351
15.1.2;2 Method;353
15.1.2.1;2.1 Fuzzy Knowledge Discovery;353
15.1.2.2;2.2 Type Reducer and Iterative Evolutionary Learning;355
15.1.2.3;2.2 Performance Analysis;356
15.1.2.3.1;2.2.1 Membership function and rules;356
15.1.3;3 Results;358
15.1.3.1;3.1 Comparison of type-1 and hybrid Fuzzy Logic systems;358
15.1.4;4 Conclusions;359
15.1.5;5 References;360
15.2;Comparison of ANN and MARS in Prediction of Property of Steel Strips;363
15.2.1;1. Introduction;363
15.2.2;2. Method;365
15.2.2.1;2.1 Data;365
15.2.2.2;2.2 Predictive Models;366
15.2.2.2.1;2.2.1 ANN Model Development;367
15.2.2.2.2;2.2.2 MARS Model Development;369
15.2.3;3. Results and Discussion;370
15.2.4;4. Conclusion;374
15.2.5;Acknowledgements;375
15.2.6;References;375
15.3;Designing Steps and Simulation Results of a Pulse Classification System for the Electro Chemical Discharge Machining (ECDM) Process - An Artificial Neural Network Approach;377
15.3.1;1 Introduction;377
15.3.2;2 Pulse Types in the ECDM Process;378
15.3.3;3 Experimental Setup;379
15.3.4;4 Designing of the Classification System;379
15.3.4.1;4.1 Neural Network Architecture;380
15.3.4.2;4.2 Feature Extraction;380
15.3.4.3;4.3 The Preparation of a Training Data Set and a Test Data Set;381
15.3.4.4;4.4 Number of Layers and Number of Neurons in Each Layer;381
15.3.5;5 Definition of Classification Accuracy;382
15.3.6;6 Simulated Results;382
15.3.7;7 Classification Accuracy;384
15.3.8;8 Process Control System;384
15.3.9;9 Conclusions;385
15.3.10;References;385
16;Part IX Signal Processing;388
16.1;Hybrid Image Segmentation based on Fuzzy Clustering Algorithm for Satellite Imagery Searching and Retrieval;389
16.1.1;1 Introduction;389
16.1.2;2 Image Segmentation and Feature Extraction Techniques;390
16.1.2.1;2.1 Color Feature Extraction;390
16.1.2.2;2.2 Texture Feature Extraction;393
16.1.2.3;2.3 Fuzzy C-means Clustering;396
16.1.2.4;2.4 Region Merging and Labeling;397
16.1.2.5;2.4 Region Feature Extraction;399
16.1.3;3 Experimentation;400
16.1.4;4 Results and Discussion;402
16.1.5;5 Summary;404
16.1.6;Acknowledgments;404
16.1.7;References;404
16.2;Boosting the Performance of the Fuzzy Min-Max Neural Network in Pattern Classification Tasks;407
16.2.1;1. Introduction;407
16.2.2;2. Fuzzy Min-Max Neural Network and AdaBoost;408
16.2.2.1;2.1 Fuzzy Min-Max Neural Network;408
16.2.2.2;2.2 AdaBoost;411
16.2.2.2.1;2.2.1 Bootstrapping;413
16.2.3;3 Case Studies;414
16.2.3.1;3.1 Wisconsin Breast Cancer Data;414
16.2.3.2;3.2 Pima Indians Diabetes Data;416
16.2.3.3;3.3 Myocardial Infraction (MI) Data;418
16.2.4;4 Conclusions;420
16.2.5;References;421
16.3;A Genetic Algorithm for Solving BSS-ICA;423
16.3.1;1 Introduction;423
16.3.2;2 Basis Genetic Algorithms;424
16.3.3;3 Mutation Operator based on neighborhood philosophy;424
16.3.4;4 ICA and Convex Optimization under Discrepancy Constraints;425
16.3.5;5 A New Statistical Independence Criterion: the Search for a Suitable Fitness Function;426
16.3.6;6 Guided Genetic Algorithm;429
16.3.7;7 Simulations;430
16.3.8;8 Conclusions;432
16.3.9;References;432
17;Part X Computer Security;434
17.1;RDWT Domain Watermarking based on Independent Component Analysis Extraction;435
17.1.1;1 Introduction;435
17.1.2;2 RWDT;436
17.1.3;3 Adaptive Watermark Embedding;438
17.1.4;4 Intelligent Watermark Extraction Based on ICA;440
17.1.5;5 Experimental Results;441
17.1.6;6. Conclusions;446
17.1.7;Reference;447
17.2;Towards Very Fast Modular Exponentiations Using Ant Colony;449
17.2.1;1 Introduction;449
17.2.2;2 Addition Chain Minimisation;450
17.2.2.1;2.1 Addition Chain-Based Methods;451
17.2.2.2;2.2 Addition Chain Minimisation Problem;452
17.2.3;3 Ant Systems and Algorithms;452
17.2.4;4 Addition Chain Minimisation Using Ant System;454
17.2.4.1;4.1 The Ant System Shared Memory;454
17.2.4.2;4.2 The Ant Local Memory;454
17.2.4.3;4.3 Addition Chain Characteristics;455
17.2.4.4;4.4 Pheromone Trail and State Transition Function;456
17.2.5;5 Performance Comparison;457
17.2.6;6 Conclusion;458
17.2.7;References;458
17.3;Taming the Curse of Dimensionality in Kernels and Novelty Detection;459
17.3.1;1 Introduction;459
17.3.2;2 Recent Work;460
17.3.3;3 Analytical Investigation;461
17.3.3.1;3.1 The Curse of Dimensionality, Kernels, and Class Imbalance;461
17.3.3.2;3.2 Kernel Behavior in High Dimensional Input Space;463
17.3.3.3;3.3 The Impact of Dimensionality on the One-Class SVM;466
17.3.4;4 A Framework to Overcome High Dimensionality;467
17.3.5;5 Discussion and Conclusion;470
17.3.6;References;470
18;Part XI Bioinformatics;474
18.1;A Genetic Algorithm with Self-sizing Genomes for Data Clustering in Dermatological Semeiotics;475
18.1.1;1 Introduction;475
18.1.2;2 Data Clustering;476
18.1.2.1;2.2 Homogeneity and Separability;477
18.1.3;3 A Self-sizing Genome Genetic Algorithm;478
18.1.3.1;3.1 Genetic Algorithms and Data Clustering;478
18.1.3.2;3.2 SGGA for Data Clustering;478
18.1.4;4 Data Set and Pathology Addressing Index;480
18.1.4.1;4.1 The Considered Data Set;480
18.1.4.2;4.2 Pathology Addressing Index;480
18.1.5;5 Experimental Results of SGGA;481
18.1.5.1;5.1 SGGA Performance as a Data Clustering Tool;481
18.1.5.2;5.2 Comparison of Found Syndromes with Known Pathologies;482
18.1.6;6 Conclusions and Future Works;484
18.1.7;References;484
18.2;MultiNNProm: A Multi-Classifier System for Finding Genes;485
18.2.1;1 Introduction;485
18.2.2;2 Biological Background;486
18.2.3;3 Why use Multiple Classifiers?;487
18.2.3.1;3.2 The LAP and LOP Methods for Combining Classifiers;488
18.2.3.1.1;3.2.1 The LAP Method;489
18.2.3.1.2;3.2.2 The LOP Method;489
18.2.3.1.3;3.2.3 The LOP2 Method;489
18.2.4;4 Description of the MultiNNProm System;490
18.2.4.1;4.1 Overview of the System;490
18.2.4.2;4.2 The Probability Function;491
18.2.4.3;4.3 Result Aggregation;492
18.2.5;5 Experimental Results;493
18.2.5.1;5.1. Performance Evaluation of the Individual Classifiers;493
18.2.5.2;5.2 Performance Evaluation of the Combined System;494
18.2.6;6 Conclusion;496
18.2.7;References;496
18.3;An Overview of Soft Computing Techniques Used in the Drug Discovery Process;499
18.3.1;1 Introduction;499
18.3.2;2 Drug Discovery;501
18.3.2.1;2.1 The Drug Discovery Process;501
18.3.2.1.1;2.1.1 Target Identification;501
18.3.2.1.2;2.1.2 Target Validation;502
18.3.2.1.3;2.1.3 Lead Identification;503
18.3.2.1.4;2.1.4 Lead Optimisation;504
18.3.2.2;2.2 Limitations of Classical Techniques;505
18.3.3;3 Soft Computing Techniques in Drug Discovery;506
18.3.3.1;3.1 SC in Target Identification;506
18.3.3.2;3.2 SC in Target Validation;507
18.3.3.3;3.3 SC in Lead Identification;507
18.3.3.4;3.4 SC in Lead Optimisation;508
18.3.4;4 Discussion;510
18.3.5;5 Conclusions;511
18.3.6;Acknowledgments;511
18.3.7;References;511
19;Part XII Text Processing;516
19.1;Ontology-Based Automatic Classification of Web Pages;517
19.1.1;1. Introduction;517
19.1.2;2. Related works and Background information;518
19.1.2.1;2.1 Document Classification;518
19.1.2.2;2.2 Ontology;519
19.1.3;3. Document Classification using Ontology;519
19.1.3.1;3.1 Ontology Structure;519
19.1.3.2;3.2 Building Domain Ontology for Document Classification;520
19.1.3.3;3.3 Document Classification Using Ontology;521
19.1.4;4. Experimental Procedures;524
19.1.5;5. Conclusion and Future Research;526
19.1.6;References;527
19.2;Performance Analysis of Naïve Bayes Classification, Support Vector Machines and Neural Networks for Spam Categorization;529
19.2.1;1 Introduction;529
19.2.2;2 Related Works;530
19.2.3;3 Corpus;531
19.2.4;4 Feature Representation;531
19.2.5;5 Classification Methods;532
19.2.5.1;5.1 Neural Networks (NN);532
19.2.5.2;5.2 Support Vector Machines;533
19.2.5.3;5.3 Naïve Bayes;533
19.2.6;6 Results;534
19.2.6.1;6.1 Comparison of NB, NN and SVM;536
19.2.7;7 Conclusions & Future Work;537
19.2.8;References;538
19.3;Sentence Extraction Using Asymmetric Word Similarity and Topic Similarity;539
19.3.1;1 Introduction;539
19.3.2;2 Mass Assignments Theory and Fuzzy Sets;540
19.3.2.1;2.1 Semantic Unification;541
19.3.3;3 Computation of Similarity;542
19.3.3.1;3.1 Word similarity;542
19.3.3.2;3.2 Topic Similarity;545
19.3.4;4 Sentence Extraction;545
19.3.5;5 Experimental Results;545
19.3.5.1;5.1 DUC Collection;546
19.3.6;6 Conclusions;548
19.3.7;References;548
20;Part XIII Algorithm Design;550
20.1;Designing Neural Networks Using Gene Expression Programming;551
20.1.1;Introduction;551
20.1.2;Genes with Multiple Domains for Designing NNs;552
20.1.3;Special Genetic Operators;554
20.1.4;Domain-specific Transposition;555
20.1.5;Intragenic Two-point Recombination;556
20.1.6;Direct Mutation of Weights and Thresholds;560
20.1.7;Solving Problems with NNs Designed by GEP;562
20.1.8;Neural Network for the Exclusive-or Problem;562
20.1.9;Neural Network for the 6-Multiplexer;565
20.1.10;Conclusions;568
20.1.11;References;568
20.2;Particle Swarm Optimisation from lbest to gbest;571
20.2.1;1 Introduction;571
20.2.2;2 Particle Swarm Optimization Algorithm;572
20.2.3;3 gbest Model vs. lbest Model;573
20.2.4;4 Algorithm Description from lbest to gbest;573
20.2.5;5 Benchmark Test Functions;574
20.2.6;6 Experiment Setting;575
20.2.7;7 Results and Discussions;575
20.2.8;8 Conclusion;578
20.2.9;Acknowledgments;578
20.2.10;References;578
20.3;Multiobjective 0/1 Knapsack Problem usingAdaptive e -Dominance;581
20.3.1;1 Introduction;581
20.3.2;2 Multiobjective 0/1 Knapsack Problem;582
20.3.3;3 e-Dominance;583
20.3.4;4 e-MOKA Technique;583
20.3.5;5 Adaptive e-MOKA;584
20.3.6;6 Experimental Results;585
20.3.6.1;6.1 C-Metric;585
20.3.6.2;6.2 Numerical Comparisons;586
20.3.7;7 Conclusions;588
20.3.8;References;589
21;Part XIV Control;592
21.1;Closed Loop Control for Common Rail Diesel Engines based on Rate of Heat Release;593
21.1.1;1 Introduction;593
21.1.2;2 Combustion Process in Diesel Engines: Rate of Heat Release;595
21.1.3;3 E.ective ROHR Forecasting Model Requirements;596
21.1.4;4 Soft Computing Techniques Based Model Forecasting ROHR;597
21.1.4.1;4.1 . Transform;597
21.1.4.2;4.2 Clustering;599
21.1.4.3;4.3 Set-up of the Grey-Box Model;600
21.1.5;5 Test Case;601
21.1.6;6 Conclusions;602
21.1.7;References;602
21.2;A MIMO Fuzzy Logic Autotuning PID Controller: Method and Application;603
21.2.1;1 Introduction;603
21.2.2;2 FUZZY PID CONTROLLER (FPID) SISO CASE;604
21.2.2.1;2.1 FPID SISO Structure;605
21.2.2.2;2.2 Simulation and Experimental Results for the FPID-SISO;607
21.2.3;3 FUZZY PID CONTROLLER: MIMO CASE;610
21.2.3.1;3.1 A. FPID MIMO Structure;610
21.2.3.2;3.2 Results for the FPID- MIMO - Double Tanks Case;612
21.2.4;4 Conclusion;613
21.2.5;References;614
21.3;Performance of a Four Phase Switched Reluctance Motor Speed Control Based On an Adaptive Fuzzy System: Experimental Tests, Analysis and Conclusions;615
21.3.1;1 Introduction;615
21.3.1.1;1.1 Motor Type;616
21.3.1.2;1.2 Power Circuit Topology;616
21.3.1.3;1.3 Learning Controller;617
21.3.2;2 Neuro-fuzzy Design;618
21.3.3;2.1 Neuro-Fuzzy Parameters;619
21.3.3.1;2.1.1 Universe of Discourse;620
21.3.3.2;2.1.2 Membership Functions;621
21.3.3.3;2.1.3 Distribution of Membership Functions;621
21.3.3.4;2.1.4 Setting the Learning Rate;621
21.3.3.5;2.1.5 Number of Membership Functions;621
21.3.4;3 Verification Tests;624
21.3.4.1;3.1 Weights Distribution;624
21.3.4.2;3.2 Learning Rate;624
21.3.5;4 Experimental Results;626
21.3.5.1;4.1 Control Surface;628
21.3.5.2;4.2 PID Controller;629
21.3.6;5 Conclusions;631
21.3.7;References;632
22;Part XV Hybrid Intelligent Systems using Fuzzy Logic, Neural Networks and Genetic Algorithms;635
22.1;Modular Neural Networks and Fuzzy Sugeno Integral for Face and Fingerprint Recognition;637
22.1.1;1 Introduction;637
22.1.2;2 Modular Neural Networks;638
22.1.2.1;2.1 Multiple Neural Networks;639
22.1.2.2;2.2 Main Architectures with Multiple Networks;640
22.1.2.3;2.3 Modular Neural Networks;640
22.1.2.4;2.4 Advantages of Modular Neural Networks;641
22.1.2.5;2.5 Elements of Modular Neural Networks;641
22.1.2.6;2.6 Main Task Decomposition into Subtasks;642
22.1.2.7;2.7 Communication Between Modules;642
22.1.2.8;2.8 Response Integration;642
22.1.3;3 Methods of Response Integration;643
22.1.3.1;3.1 Fuzzy Integral and Fuzzy Measures;644
22.1.4;4 Proposed Architecture and Results;645
22.1.4.1;4.2 Proposed Architecture;646
22.1.4.2;4.2 Description of the Integration Module;647
22.1.4.3;4.3 Summary of Results;648
22.1.5;5 Conclusions;651
22.1.6;Acknowlegments;651
22.1.7;References;651
22.2;Evolutionary Modeling Using A Wiener Model;653
22.2.1;1 Introduction;653
22.2.2;2 System Description;655
22.2.3;3 Evolutionary Optimization Technique;657
22.2.4;4 Training Signal Generation;659
22.2.5;5 Experimental Results;659
22.2.6;6 Conclusions;662
22.2.7;7 Acknowledgment;665
22.2.8;8 References;665
22.3;Evolutionary Computing for Topology Optimization of Fuzzy Systems in Intelligent Control;667
22.3.1;1 Introduction;667
22.3.2;2 Genetic Algorithms for Optimization;668
22.3.2.1;2.1 Genetic Algorithm for Optimization;669
22.3.3;3. Evolution of Fuzzy Systems;670
22.3.4;4 Type-2 Fuzzy Logic;672
22.3.5;5 Application to Intelligent Control;674
22.3.5.1;5.1 Anesthesia Control Using Fuzzy Logic;675
22.3.5.2;5.2 Characteristics of the Fuzzy Controller;676
22.3.5.3;5.3 Genetic Algorithm Specification;676
22.3.5.4;5.4 Representation of the Chromosome;677
22.3.6;6 Simulation Results;677
22.3.7;7 Conclusions;680
22.3.8;Acknowledgments;680
22.3.9;References;680
23;Part XVI Recent Developments in Support Vector and Kernel Machines;683
23.1;Analyzing Magni.cation Factors and Principal Spread Directions in Manifold Learning;685
23.1.1;1 Introduction;685
23.1.2;2 Dimensionality Reduction;687
23.1.3;3 SVD-based Magni.cation Factors and Principal Spread Directions;688
23.1.3.1;3.1 Magnification Factors;689
23.1.3.2;3.2 Principal Spread Directions;691
23.1.3.3;3.3 The Proposed Approach;691
23.1.4;4 Experiments;692
23.1.5;5 Conclusions;697
23.1.6;Acknowledgements;697
23.1.7;References;697
23.2;Bag Classification Using Support Vector Machines;699
23.2.1;1 Introduction;700
23.2.2;2 Classification Approach;700
23.2.3;3 Image Processing;702
23.2.4;4 Experimental Results;703
23.2.4.1;4.1 Methodology;703
23.2.4.2;4.2 Kernel Optimization Experiment for Bag Classification;703
23.2.4.3;4.3 Optimal Feature Selection;704
23.2.5;5 Analysis of the Results;706
23.2.6;6 Conclusions;707
23.2.7;Acknowledgments;707
23.2.8;References;707
23.3;The Error Bar Estimation for the Soft Classi.cation with Gaussian Process Models;709
23.3.1;1 Introduction;709
23.3.2;2 Support Vector Machine Method for Classi.cation;710
23.3.3;3 From Hard Classi.cation to Soft Classi.cation;712
23.3.4;4 Computation Method for the Error Bar;713
23.3.5;5 Conclusion;715
23.3.6;References;715
23.4;Research of Mapped Least Squares SVM Optimal Configuration;719
23.4.1;1 Introduction;719
23.4.2;2 Mapped LS-SVM and Model Selection;720
23.4.2.1;2.1 Least Squares (LS) SVM;720
23.4.2.2;2.2 Model Selection;721
23.4.2.3;2.3 Mapped LS-SVM;722
23.4.3;3 Physical Property of Mapped LS-SVM;724
23.4.3.1;3.1 Image Intensity Surface Function;724
23.4.3.2;3.2 Filters of Mapped LS-SVM;724
23.4.3.3;3.3 Physical Interpretation;725
23.4.4;4 Optimal Configuration of Mapped LS-SVM;727
23.4.5;5 Conclusions;728
23.4.6;References;728
23.5;Classifying Unlabeled Data with SVMs;729
23.5.1;1 Introduction;729
23.5.2;2 Quadric Program Problem of Classifying Unlabeled Data;730
23.5.2.1;2.1 Partial Related Works;730
23.5.2.2;2.2 Primal Problem;730
23.5.2.3;2.3 Dual Problem;731
23.5.3;3 Semi-supervised Learning;733
23.5.4;4 Conclusions;735
23.5.5;Acknowledgments;735
23.5.6;Reference;736
24;Part XVII Robotics;738
24.1;Car Auxiliary Control System Using Type-II Fuzzy Logic and Neural Networks;739
24.1.1;1 Introduction;739
24.1.2;2 Fuzzy Controller;740
24.1.2.1;2.1 Define fuzzy sets;740
24.1.2.2;2.2 Processes;741
24.1.2.3;2.3 Type-II Fuzzy Logic;742
24.1.3;3 Neural Networks;743
24.1.4;4 Simulations and Results;744
24.1.4.1;4.1 Type-I fuzzy logic system;744
24.1.4.2;4.2 Type-II fuzzy logic system;745
24.1.4.3;4.3 Results;747
24.1.5;5 Conclusions;750
24.1.6;6 References;750
24.2;Evolving Neural Controllers for Collective Robotic Inspection;751
24.2.1;1 Introduction;751
24.2.2;2 Evolutionary Methodology;753
24.2.2.1;2.1 Encoding of Arti.cial Neural Networks;753
24.2.2.2;2.2 Initialization;753
24.2.2.3;2.3 Genetic Operations;754
24.2.3;3 Case Study: Collective Robotic Inspection;755
24.2.3.1;3.1 Application Background;755
24.2.3.2;3.2 Experiment Setup and Simulation;755
24.2.3.3;3.3 Hand-coded Controller;757
24.2.4;4 Results and Discussions;757
24.2.4.1;4.1 Single Robot Single Object (SRSO) Scenario;758
24.2.4.2;4.2 Single Robot Multiple Objects (SRMO) Scenario;759
24.2.4.3;4.3 Multiple Robots Multiple Objects (MRMO) Scenario;760
24.2.5;5 Conclusion and Future Work;762
24.2.6;Acknowledgments;763
24.2.7;References;763
24.3;A Self-Contained Traversability Sensor for Safe Mobile Robot Guidance in Unknown Terrain;765
24.3.1;1 Introduction;765
24.3.2;2 Intelligence Hierarchy for Sensor Devices;767
24.3.3;3 Cognitive Sensor Technology;768
24.3.3.1;3.1 Cognitive Sensor Design Process;769
24.3.3.2;3.2 Motivation and Aims;770
24.3.4;4 Traversability Sensor Design;771
24.3.4.1;4.1 Intelligent Software for Terrain Assessment;773
24.3.4.1.1;4.1.1 Terrain Image Processing;774
24.3.4.1.2;4.1.2 Fuzzy Logic Reasoning;774
24.3.5;5 Experimental Validation;776
24.3.6;6 Discussion;778
24.3.7;7 Conclusions;780
24.3.8;Acknowledgments;781
24.3.9;References;781
24.4;Fuzzy Dispatching of Automated Guided Vehicles;783
24.4.1;1 Introduction;783
24.4.2;2 AGV Dispatching;784
24.4.3;3 Fuzzy Dispatching of AGV;785
24.4.4;4 Simulation Analysis;786
24.4.5;5 Results;788
24.4.6;6 Conclusion;792
24.4.7;References;793
25;Part XVIII Soft Computing and Hybrid Intelligent Systems in Product Design and Development;796
25.1;Application of Evolutionary Algorithms to the Design of Barrier Screws for Single Screw Extruders;797
25.1.1;1.1 Introduction;797
25.1.2;1.2 Process Modeling;799
25.1.3;1.3 Design Approach;800
25.1.3.1;1.3.1 Multi-Objective Optimization Algorithm;800
25.1.3.2;1.3.2 Methodology for Screw Design;802
25.1.4;1.4 Optimization Example;803
25.1.5;1.5 Conclusions;806
25.1.6;Acknowledgments;807
25.1.7;References;808
25.2;Soft Computing in Engineering Design: A Fuzzy Neural Network for Virtual Product Design;809
25.2.1;1. Introduction;809
25.2.2;2. Soft Computing Framework for Engineering Design;810
25.2.3;3. Fuzzy Neural Network Model;811
25.2.3.1;3.1 The FNN Architecture;812
25.2.3.2;3.2 Parameter Learning Algorithms;813
25.2.3.2.1;3.2.1 The Supervised Learning;813
25.2.3.2.2;3.2.2 Self-Organized Learning;814
25.2.4;4. System Implementation;815
25.2.5;5. Case Study;816
25.2.6;6. Conclusions;817
25.2.7;References;817
25.3;Internet Server Controller Based Intelligent Maintenance System for Products;819
25.3.1;1. Introduction;819
25.3.2;2. Intelligent Maintenance Systems;820
25.3.3;3. Internet-based Server Controller;822
25.3.3.1;3.1. Structure of the Embedded Network Model;822
25.3.3.2;3.2. Software Agent for Embedded Network Model;823
25.3.4;4. Watchdog Agent;825
25.3.5;5. Tele-Service Engineering System for Information Appliance and Testbed;826
25.3.5.1;5.1. Structure of the Remote Engineering System Testbed;826
25.3.5.2;5.2. Main Interfaces of the Remote Engineering System Testbed;827
25.3.5.3;5.3. The Development Toolkit;827
25.3.6;6. Conclusions;827
25.3.7;Acknowledgement and Disclaimer;828
25.3.8;References;828
25.4;A Novel Genetic Fuzzy/Knowledge Petri Net Model and Its Applications;829
25.4.1;1. Introduction;829
25.4.2;2. Knowledge-Based Petri Net Models;830
25.4.2.1;2.1 Knowledge Petri Net;830
25.4.2.2;2.2 Fuzzy Knowledge Petri net;831
25.4.2.3;2.3 FKPN-based Expert System;832
25.4.2.3.1;2.3.1 Knowledge Representation;832
25.4.2.3.2;2.3.2 Reasoning;833
25.4.3;3. Genetic Knowledge Petri Net Models;834
25.4.3.1;3.1 Genetic Models for KPN and FKPN;834
25.4.3.2;3.2 Evolutionary Design for Petri Nets;834
25.4.3.3;3.3 Genetic Rule-Finding and -Tuning for FKPN;835
25.4.4;4. Applications in Engineering Design;836
25.4.5;5. Conclusions;837
25.4.6;References;837
25.5;Individual Product Customization Based On Multi-agent Technology*;839
25.5.1;1 Introduction;839
25.5.2;2 Customization Principles of Individual Product;841
25.5.2.1;2.1 Module of Individual Product Customization;841
25.5.2.2;2.2 Content Matching of Individual Product Customization;841
25.5.2.3;2.3 Interesting Value Counting of Individual Products;843
25.5.3;3 The Customization System of Individual Product;843
25.5.4;4. Case Study: Individual Motorcycle Customization;844
25.5.4.1;4.1 Individual Motorcycle Customization Characteristics;844
25.5.4.2;4.2 Requirement Quantity Determination of Individual Motorcycle Customization;845
25.5.4.3;4.3 A Process of Individual Motorcycle Customization Based on Multi-agent Technology;845
25.5.4.4;4.4 An Individual Motorcycle Customization Calculation;846
25.5.5;5 Conclusions;848
25.5.6;References;848
25.6;An Intelligent Design Method of Product Scheme Innovation*;849
25.6.1;1 Introduction;849
25.6.2;2 Intelligent Design Principle of Product Scheme Innovation;852
25.6.2.1;2.1 Intelligent Design Model of Product Scheme Innovation;852
25.6.2.2;2.2 Function Cell Classes of a Product;853
25.6.2.3;2.3 Structure Cell Classes of a Product;853
25.6.2.4;2.4 Knowledge Acquiring, Expression and Reasoning of Product Scheme Intelligent Design;854
25.6.2.5;2.5 Intelligent Design of Motorcycle Innovation;855
25.6.3;3 Conclusions;858
25.6.4;References;858
25.7;Communication Method for Chaotic Encryption in Remote Monitoring Systems for Product e-Manufacturing and e-Maintenance;859
25.7.1;1. Introduction;859
25.7.2;2. Nonlinear Test Based on the VWK Method;861
25.7.2.1;2.1 The Theory;861
25.7.2.2;2.2 The Effect of Sampling Interval;862
25.7.2.3;2.3 Application;863
25.7.3;3. The Cryptanalysis;864
25.7.4;4. Nonlinear Test Study Based on the Surrogate Data;865
25.7.5;5. Conclusion;866
25.7.6;Acknowledgement and Disclaimer;867
25.7.7;References;867
26;Subject Index;869
27;Index of Contributors;873mehr
Leseprobe
Applying Fuzzy Sets to the SemanticWeb: The Problem of Retranslation (p. 3)

Ronald R. Yager
Machine Intelligence Institute, Iona College
New Rochelle, NY 10801

Abstract: We discuss the role of Zadeh's paradigmof computing with words on the semantic web We describe thethree important steps in using computing with words. We focuson the retranslation step, selecting a term from our prescribedvocabulary to express information represented using fuzzy sets. A number of criteria of concern in this retranslation processare introduced. Some of these criteria can be seen to correspondto a desire to accurately reflect the given information. Othercriteria may correspond to a desire, on the part provider ofthe information, to give a particular perception or "spin."We discuss some methods for combining these criteria to evaluatepotential retranslations.

Keywords: Computing with Words, Fuzzy Sets, Linguistic Approximation

1. Computing with Words and the Semantic Web

The Semantic Web is invisioned as an extension of the currentweb in which information is given well-defined meaning and semantics,better enabling computers and people to work in cooperation. Among its goals is a humanlike automated manipulation of theknowledge contained on the web. While computers are good atprocessing information, they have no understanding of the meaningand semantics of the content which greatly hinders human likemanipulation. The fulfillment of the vision of the SemanticWeb requires tools that enable the computational representationof knowledge that emulates human deep understanding. Hence enablingintelligent information processing. Fuzzy subset theory andthe related paradigm of computing with words [1-3] providetools of this nature and hence will help to enable the automatedmanipulation of human knowledge.mehr

Autor