Hybrid Artificial Intelligence Systems: 4th International Conference, HAIS 2009, Salamanca, Spain, June 10-12, 2009, Proceedings (Lecture Notes in Computer Science, 5572)

This volume constitutes the refereed proceedings of the 4th International Workshop on Hybrid Artificial Intelligence Systems, HAIS 2009, held in Salamanca, Spain, in June 2009. The 85 papers presented, were carefully reviewed and selected from 206 submissions. The topics covered are agents and multi agents systems, HAIS applications, cluster analysis, data mining and knowledge discovery, evolutionary computation, learning algorithms, real world HAIS applications and data uncertainty, hybrid artificial intelligence in bioinformatics, evolutionary multiobjective machine learning, hybrid reasoning and coordination methods on multi-agent systems, methods of classifiers fusion, knowledge extraction based on evolutionary learning, hybrid systems based on bioinspired algorithms and argumentation methods, hybrid evolutionry intelligence in financial engineering. Hybrid Artificial Intelligence Systems, 4th International Conference, HAIS 2009, Salamanca, Spain, June 10-12, 2009, Proceedings......Page 3 ISBN 9783642023187......Page 4 Preface ......Page 5 Organization......Page 7 Table of Contents......Page 14 Introduction......Page 22 Agent Types in HoCa......Page 23 Using HoCa to Development a Hybrid Multi-Agent System for Dependent Environment......Page 25 Results and Conclusions......Page 27 References......Page 28 Motivation and Related Work......Page 30 General Description......Page 31 The Inter-agents Communication Protocol......Page 32 Implementation and Evaluation......Page 34 Conclusions and Future Work......Page 37 References......Page 38 Introduction......Page 39 Hybrid and Deliberative Structure......Page 40 Reactive Structure......Page 42 Properties of Intention......Page 43 Demonstrations and Experiments......Page 44 Discussion and Conclusions......Page 45 References......Page 46 Introduction......Page 47 Multi-agent Based Personal File Management System......Page 48 Case Representation......Page 49 Case Retrieval......Page 50 Case Reuse and Revision......Page 51 Performance Validation......Page 52 Conclusions......Page 53 References......Page 54 Introduction......Page 55 Agent-Based Evolutionary System for Solving TSP......Page 56 Experimental Results......Page 58 References......Page 62 Introduction......Page 63 Evolutionary Algorithm: Memetic Algorithm......Page 65 The Vehicle Routing Problem. Public Transport Routes......Page 66 Solving the Problem Using a Memetic Algorithm......Page 67 Conclusions and Future Lines......Page 69 References......Page 70 Introduction......Page 71 Combining a Multi-agent Architecture and Case-Based Reasoning Systems......Page 72 Presenting a New Multi-agent Contingency Response System for Dynamic Environments......Page 73 Data Input Service......Page 75 Revision Service......Page 76 Results......Page 77 Conclusions and Future Work......Page 78 References......Page 79 Introduction......Page 81 Measuring Similarities between Customer Satisfaction Profiles......Page 82 Visualisation......Page 84 Results......Page 85 References......Page 88 Introduction......Page 89 An Overview of the System......Page 90 Development of a Decision-Maker......Page 91 Development of a Prototype of the Decision-Maker......Page 94 Experiments......Page 95 References......Page 96 Introduction......Page 98 Earthquakes and Data......Page 99 Wavelet Transformation......Page 100 Calculating Singularities......Page 101 Experimental Procedure......Page 102 Wenchuan Earthquake......Page 103 Puer Earthquake......Page 105 Conclusion......Page 107 References......Page 108 Introduction......Page 109 Evolutionary Based Automatic Design System......Page 110 Hydrodynamic Simulator......Page 111 Experiments......Page 113 Conclusions......Page 115 References......Page 116 Introduction......Page 117 The Automatic Design Procedure......Page 118 Hydrodynamic Simulation Model......Page 119 Neuronal Correction......Page 120 Design Example......Page 121 Conclusions......Page 123 References......Page 124 Introduction......Page 125 Itemsets, Supports of Itemsets, Frequent Itemsets, Downward Closed Sets......Page 126 Closures, Closed Itemsets......Page 127 Representing Patterns with Closures of Downward Closed Sets......Page 128 Summary and Conclusions......Page 131 References......Page 132 Introduction......Page 134 Transductive-Weighted Neuro-Fuzzy Inference System......Page 136 Tool Wear Model in Turning Process......Page 137 Results......Page 138 Discussion......Page 140 References......Page 141 Introduction......Page 142 Kalman Filters and Non-linear Variants......Page 143 Non-linear Enhancement of KF......Page 145 Information Fusion......Page 146 Conclusions......Page 147 References......Page 148 Introduction......Page 150 Coarse Candidate Selection Module......Page 151 Experimental Results......Page 152 Fine Module Performance......Page 153 HBHS Performance......Page 154 HBHS against Other Methods......Page 155 Conclusions and Future Work......Page 156 References......Page 157 Introduction......Page 158 Unsupervised Methods......Page 159 Derived Variables......Page 160 Results......Page 161 Conclusions......Page 164 References......Page 165 Introduction......Page 166 Format of the Generic Software Architecture......Page 168 Knowledge Representation – The Whiteboard......Page 170 Reasoning and Planning......Page 171 Modeling Behaviors......Page 172 Illustration and Conclusions......Page 174 References......Page 176 Introduction......Page 178 Connectionist Projection Model......Page 179 CBR Paradigm......Page 180 A Hybrid Advising Solution......Page 181 Proposal Generation......Page 182 A Real-Life Case Study......Page 184 Enhancing DIPKIP......Page 186 References......Page 188 Introduction......Page 190 Related Work......Page 191 Simplified Silhouette Filter (SSF)......Page 192 Empirical Evaluation......Page 193 Conclusions......Page 196 References......Page 197 Introduction......Page 198 The Multi-objective Variant of DE......Page 199 Search-Variable Representation and Description of the New algorithm......Page 200 Selecting the Objective Functions......Page 201 Evaluating the Clustering Quality......Page 202 Presentation of Results......Page 203 References......Page 205 Introduction......Page 208 ARES System......Page 209 Characteristics of Credibility Coefficient......Page 210 Ordinal Credibility Coefficient......Page 212 Multi Credibility Coefficient Method......Page 213 References......Page 215 Introduction......Page 216 EAC-I: Evolutionary Algorithm for Clustering Based Imputation......Page 217 Bias in Classification......Page 219 Illustrative Experimental Results......Page 221 References......Page 223 Motivation and Goals......Page 224 System Architecture......Page 225 Data Wrappers......Page 227 Meta ARM (Association Rule Mining) Scenario......Page 228 Classifier Generation Scenario......Page 229 Conclusions......Page 230 References......Page 231 Introduction......Page 232 Evolutionary Techniques......Page 233 Modules......Page 234 MDDSS......Page 235 Evolution of FS1 and Its Links......Page 236 Conclusions and Expected Outcomes......Page 238 References......Page 239 Introduction......Page 240 Capability Maturity Model Integrated (CMMI)......Page 241 Fuzzy Set Theory......Page 242 Algorithm of FQIMM......Page 243 Conclusions......Page 246 References......Page 247 Introduction......Page 248 Related Work......Page 249 C2D: Confidence-Based Concept Discovery Method......Page 250 Transitive Rules in C2D......Page 251 Experimental Results......Page 253 Conclusion......Page 254 References......Page 255 Introduction......Page 256 Business Intelligence and Energy Markets Related Work......Page 257 Prediction......Page 258 Modeling......Page 259 Conclusions and Future Work......Page 260 References......Page 261 Introduction......Page 265 LIRBF Model......Page 267 Learning the LIRBF Model Coefficients......Page 269 Experiments......Page 270 References......Page 272 Introduction......Page 273 ELD Problem Formulation......Page 274 The Hybrid Algorithm......Page 276 Six-Unit System......Page 278 Thirteen-Unit System......Page 279 References......Page 280 Introduction......Page 282 The Density Classification Task and Related Work......Page 283 The Space Dimension......Page 284 Circular Evolutionary Approach to the Density Classification Task......Page 285 Numerical Experiments......Page 286 Conclusions and Future Work......Page 288 References......Page 289 Introduction......Page 290 University Course Timetabling......Page 291 The Hybrid Strategy......Page 292 Initialisation Heuristic......Page 293 Non-linear Great Deluge......Page 294 Experiments and Results......Page 295 References......Page 296 Introduction......Page 298 Agent-Based Co-operative Co-evolutionary System for Multi-objective Optimization......Page 299 The Experiments......Page 302 Summary and Conclusions......Page 304 References......Page 305 Introduction......Page 306 Scheduling of Independent Tasks in Computational Grids......Page 308 The Proposed GA(TS) Hybrid Approach......Page 309 Tabu Search for the Scheduling Problem in Grids......Page 310 Experimental Study......Page 311 Conclusions......Page 312 Introduction......Page 314 Background......Page 315 Understanding Model–Building......Page 316 Improved Fitness Assignment......Page 318 Competent Model Builders......Page 319 References......Page 320 Introduction......Page 322 Background......Page 323 Local Search......Page 325 HJMA......Page 326 Varying the Number of Peaks......Page 327 References......Page 328 Introduction......Page 331 Evolutionary Programming......Page 333 Proposed MDE Algorithm: A Hybridized Version of DE and EP......Page 334 Numerical Results......Page 335 Conclusions......Page 337 References......Page 338 Introduction......Page 340 Oscillatory Clusters and Input Dataset......Page 341 CNN Modeling......Page 343 Proposed Method to Detect Fragmentary Synchronization......Page 345 References......Page 347 Introduction......Page 348 The Ensemble of Neural Predictors......Page 349 Final Predictor......Page 351 Numerical Results......Page 352 References......Page 355 Introduction......Page 357 TERSQ Algorithm......Page 358 Hybrid Evolutionary Algorithm......Page 360 Videogame Characters......Page 361 Conclusions......Page 363 References......Page 364 Introduction......Page 365 GTM and Geodesic Metric......Page 366 Geo-GTM......Page 367 A Semi-supervised Extension of Geo-GTM......Page 368 Experimental Results and Discussion......Page 369 References......Page 372 Introduction......Page 373 The Hot Strip Mill Process......Page 374 IT2 Design......Page 375 Experimental Results......Page 378 References......Page 379 Introduction......Page 381 Design Engineering......Page 382 Process Planning......Page 383 The Assembly Line Balancing Problem......Page 384 The Dynamic Scheduling Problem......Page 385 References......Page 386 Introduction......Page 389 Signal Data Analysis......Page 390 Confidence Estimation......Page 391 Network Output Analysis......Page 392 Expert Pooling......Page 394 References......Page 396 Introduction......Page 397 The Proposed Hybrid Ant-Based Model......Page 398 Solution Construction and Pheromone Update......Page 399 Insertion-Based Local Search......Page 400 Numerical Results......Page 401 Conclusions and Future Work......Page 403 References......Page 404 Motivation......Page 405 The Design Stage......Page 406 Definition of the Thermal Dynamics......Page 407 Experiments and Commented Results......Page 408 Conclusions and Future work......Page 410 References......Page 411 Introduction......Page 412 Self-Organizing Maps (SOM)......Page 413 Fuzzy Interpretation of the Topographical Map......Page 414 Biomedical Signals - Patients with Diabetes......Page 416 Sampling of Data from Diabetes......Page 417 Implementations and Results......Page 418 References......Page 420 Unearth the Hidden Supportive Information for an Intelligent Medical Diagnostic System......Page 422 Nature of Medical Data......Page 423 MIDCA......Page 424 Intelligence of MIDCA......Page 425 LSIA Discovery......Page 426 Experimental Results......Page 427 References......Page 428 Introduction......Page 430 Incremental Kernel Machines......Page 431 The Spectrum Kernel......Page 432 Experiments......Page 433 Results......Page 434 References......Page 436 Introduction......Page 438 Noise......Page 439 Data Sets......Page 440 Results......Page 441 Conclusion......Page 444 References......Page 445 Introduction......Page 446 Voxel Based Descriptor......Page 448 Supervised Growing Neural Gas (SGNG)......Page 449 Conclusion......Page 452 Introduction......Page 454 Accuracy Versus Sensitivity......Page 455 Base Classifier Framework and Objective Functions......Page 456 MPDE Algorithm......Page 457 Experiments......Page 459 Conclusions......Page 461 References......Page 462 Introduction......Page 463 Related Work......Page 464 Core Algorithm......Page 465 Langley Glide-Back Booster (LGBB)......Page 466 Results......Page 467 Summary......Page 469 References......Page 470 Introduction......Page 471 Using Multi-objective G3P for Classification Rule Generation......Page 472 Genetic Operators......Page 473 Fitness Function......Page 474 Comparison of Multi-objective Strategies......Page 475 References......Page 478 Introduction......Page 480 Formalization of the ASBO Argumentation System......Page 481 The Interaction Protocol......Page 482 The Context and the State of a Conversation......Page 483 Effect Rules......Page 484 Termination and Outcome Conditions......Page 485 An Example......Page 486 Conclusions......Page 487 Motivation......Page 489 Social Structure......Page 490 Protocol Specification......Page 492 Normative Context Definition......Page 493 Application Example......Page 494 Conclusion......Page 495 References......Page 496 Introduction......Page 497 CBR as Deliberative Mechanism for Agents......Page 498 Temporal-Bounded CBR......Page 500 Revise Phase......Page 501 Reuse Phase......Page 502 References......Page 503 Introduction......Page 505 Event Tracing in Multiagent Systems......Page 506 Functional Requirements......Page 508 Efficiency Requirements......Page 509 Security Requirements......Page 510 Conclusions and Future Work......Page 511 Introduction......Page 513 Web Service Security Problem Description......Page 514 Classifier Agent Internal Structure......Page 515 Mechanism for the Classification of SOAP Message Attack......Page 516 References......Page 519 Introduction......Page 521 The AgUser’s Circulation and the Dynamics of Belief Change......Page 522 RecMAS: Prototype and Implementation......Page 524 AgentComs: Trading Knowledge through Links......Page 525 Complex Optimization Problem......Page 526 Optimization Using Wireless Communications......Page 527 Final Results: Strategies for the Adaptation in Real Time and the Dynamic Attraction of Clients......Page 528 Conclusions and Future Work......Page 529 References......Page 530 Introduction......Page 531 Classifier Fusion......Page 532 Dudani's Weighting Function and the Inverse Distance Weight......Page 533 Experiments and Results......Page 534 Concluding Remarks......Page 536 Introduction......Page 538 Machine Learning Ensembles......Page 539 Ensemble of Vector Quantization Neural Networks Using Fusion......Page 540 Networks Fusion Using Boosting......Page 541 Experimental Results......Page 542 Conclusions and Further Works......Page 544 Introduction and Related Works......Page 546 Model of Compound Classifier......Page 547 Learning AdaSS Algorithm......Page 548 Experimental Investigation......Page 550 Conclusions......Page 552 References......Page 553 Bayes Hierarchical Classifier......Page 554 Decision Problem Statement......Page 555 Basic Notions of Intuitionistic Fuzzy Events......Page 557 Global Optimal Strategy......Page 558 Illustrative Example......Page 559 Conclusion......Page 560 References......Page 561 Introduction......Page 562 Classifier Fusion Based on Classifier Response......Page 563 Classifier Fusion Based on Values of Classifiers’ Discrimination Function......Page 564 Example of Classifier Fusion Based on Weights Depended on Classifier and Class Number......Page 565 Experimental Investigation......Page 567 Final Remarks......Page 568 References......Page 569 Introduction......Page 570 Bumble Bees Behavior......Page 571 BBMO for the Feature Selection Problem......Page 572 GRASP for the Clustering Problem......Page 573 Computational Results......Page 574 Conclusions and Future Research......Page 576 Introduction......Page 578 Evolutionary Instance and Feature Selection......Page 579 Cooperative Coevolution......Page 580 Cooperative Coevolutive Model Based on Instance and Feature Selection Using CHC......Page 581 Results......Page 583 Concluding Remarks......Page 584 Introduction......Page 586 Uncertainty and Feature Selection in Unsupervised Problems......Page 587 The Fuzzy Unsupervised Mutual Information Feature Selection Algorithm......Page 588 The Unsupervised Algorithm......Page 589 Experiments and Results......Page 590 Conclusions and Future Works......Page 591 References......Page 592 Introduction......Page 594 Subgroup Discovery......Page 595 NMEF-SD: Non-dominated Multi-objective Evolutionary Algorithm Based on the Extraction of Fuzzy Rules for Subgroup Discovery......Page 596 Re-initialization Based on Coverage......Page 598 Experimentation......Page 599 Conclusions......Page 600 Introduction......Page 602 Imbalanced Data-Sets in Classification......Page 603 IVFSs Model......Page 604 Genetic Tuning of the Amplitude of Upper Bound of the IVFS......Page 605 Experimental Set-Up......Page 606 Conclusions......Page 608 Introduction......Page 610 FS and FC in Presence of Attribute Interaction......Page 611 Data Reduction Using MFE3/GA......Page 612 Empirical Study......Page 614 Conclusion......Page 616 Introduction......Page 618 Related Work......Page 619 Analia......Page 620 Multiobjective Clustering in Analia......Page 621 Experiments......Page 622 Conclusions......Page 624 Introduction......Page 626 Data Complexity......Page 627 Why?......Page 628 How?......Page 629 Process Organization and Genetic Operators......Page 630 Experimental Results......Page 631 Conclusions......Page 633 Introduction......Page 634 Mamdani Fuzzy Rule-Based Systems......Page 635 MF Parameter Learning......Page 636 Interpretability......Page 637 The Three-Objective Evolutionary Approach......Page 638 Experimental Results......Page 639 References......Page 641 Introduction......Page 642 Proposed Algorithm Description......Page 643 Case Study......Page 645 Solution Obtained by the Proposed Algorithm......Page 646 Comparative Analysis of the Obtained Solutions by Other Approaches......Page 648 Conclusions and Future Work......Page 649 Introduction......Page 650 Individual Representation......Page 651 Genetic Operators......Page 652 Evolutionary Algorithm......Page 653 Implementation......Page 655 Results and Discussion......Page 656 Conclusions and Future Work......Page 657 Introduction......Page 659 Genetic Learning......Page 660 Proposed Method......Page 661 Local Nodes......Page 662 Experimental Study......Page 663 Results Analysis......Page 664 Conclusions and Future Work......Page 665 Introduction......Page 667 Preliminaries: Genetic Extraction of Association Rules......Page 668 Association Rules Mining through Evolutionary Algorithms: EARMGA, GAR, and GENAR......Page 669 Experimental Results......Page 671 References......Page 673 Introduction......Page 675 Minimum Risk Genetic Fuzzy Classifiers with Crisp Data......Page 676 Minimum Risk Genetic Fuzzy Classifiers with Low Quality Data......Page 677 Computer Algorithm of the Generalized GFS......Page 678 Synthetic Dataset......Page 679 Concluding Remarks and Future Work......Page 681 Introduction......Page 683 Experiment Strategy: Factorial Design......Page 684 Algorithm Neighboring-Ant Search......Page 685 Characteristics of SQRP......Page 686 Performing the Experiment......Page 687 Analyzing Statistics Results......Page 688 Conclusions and Future Works......Page 689 References......Page 690 Introduction......Page 691 Vehicle Routing Problem (VRP)......Page 692 Ant Colony System Optimization: State of Art......Page 693 Distributed Q-Learning: A Learning-Based Approach......Page 695 Experimentation and Results......Page 696 References......Page 697 Grid Creation and Weighting......Page 699 Creating Preliminary Clusters......Page 700 The Data Table......Page 701 Small Dataset Example......Page 702 Average Error......Page 703 Large Dataset Test......Page 704 Conclusions......Page 705 References......Page 706 Introduction......Page 707 Logistic Function and Adapted Logistic Curve......Page 708 Results and Measurements......Page 709 Available Analogue Implementation......Page 713 References......Page 714 Introduction......Page 715 Particle Swarm Optimisation......Page 716 Forecasting Models......Page 717 Trading-Related Objective Functions......Page 718 Empirical Study......Page 719 Discussion-Further Research......Page 721 Introduction......Page 723 Literature Review......Page 725 Hybrid Ant Colony Optimization Algorithm with a Local Search Technique......Page 727 Computational Study......Page 729 Conclusions and Further Research......Page 732 References......Page 733 Author Index ......Page 734 The 4th International Conference on Hybrid Artificial Intelligence Systems (HAIS 2009), as the name suggests, attracted researchers who are involved in developing and applying symbolic and sub-symbolic techniques aimed at the construction of highly robust and reliable problem-solving techniques, and bringing the most relevant achievements in this field. Hybrid intelligent systems have become increasingly po- lar given their capabilities to handle a broad spectrum of real-world complex problems which come with inherent imprecision, uncertainty and vagueness, hi- dimensionality, and nonstationarity. These systems provide us with the opportunity to exploit existing domain knowledge as well as raw data to come up with promising solutions in an effective manner. Being truly multidisciplinary, the series of HAIS conferences offers an interesting research forum to present and discuss the latest th- retical advances and real-world applications in this exciting research field. This volume of Lecture Notes in Artificial Intelligence (LNAI) includes accepted papers presented at HAIS 2009 held at the University of Salamanca, Salamanca, Spain, June 2009. Since its inception, the main aim of the HAIS conferences has been to establish a broad and interdisciplinary forum for hybrid artificial intelligence systems and asso- ated learning paradigms, which are playing increasingly important roles in a large number of application areas.