Analysis and Design of Intelligent Systems Using Soft Computing TechniquesPatricia Melin, Oscar Castillo, Eduardo G. Ramírez, Witold Pedrycz This book comprises a selection of papers from IFSA 2007 on new methods for ana- sis and design of hybrid intelligent systems using soft computing techniques. Soft Computing (SC) consists of several computing paradigms, including fuzzy logic, n- ral networks, and genetic algorithms, which can be used to produce powerful hybrid intelligent systems for solving problems in pattern recognition, time series prediction, intelligent control, robotics and automation. Hybrid intelligent systems that combine several SC techniques are needed due to the complexity and high dimensionality of real-world problems. Hybrid intelligent systems can have different architectures, which have an impact on the efficiency and accuracy of these systems, for this reason it is very important to optimize architecture design. The architectures can combine, in different ways, neural networks, fuzzy logic and genetic algorithms, to achieve the ultimate goal of pattern recognition, time series prediction, intelligent control, or other application areas. This book is intended to be a major reference for scientists and engineers interested in applying new computational and mathematical tools to design hybrid intelligent systems. This book can also be used as a reference for graduate courses like the f- lowing: soft computing, intelligent pattern recognition, computer vision, applied ar- ficial intelligence, and similar ones. The book is divided in to twelve main parts. Each part contains a set of papers on a common subject, so that the reader can find similar papers grouped together. |
Contents
2 | |
4 | |
5 | |
16 | |
26 | |
36 | |
45 | |
53 | |
An Ant Colony Optimization plugin to Enhance the Interpretability of Fuzzy Rule Bases with Exceptions | 436 |
Performance Improvement of the Attitude Estimation System Using Fuzzy Inference and Genetic Algorithms | 445 |
Multi Objective Optimization in Machining Operations | 455 |
Evolutionary Computing for the Optimization of Mathematical Functions | 463 |
Providing Intelligence to Evolutionary Computational Methods | 473 |
Part VII Fuzzy Modeling | 482 |
Representing Fuzzy Numbers for Fuzzy Calculus | 483 |
Fuzzy Parallel Processing of Hydro Power Plants Why Not? | 495 |
63 | |
Theory and Applications | 76 |
A Case Study | 79 |
MFCM for Nonlinear Blind Channel Equalization | 88 |
Fuzzy Rules Extraction from Support Vector Machines for Multiclass Classification | 99 |
Density Based Fuzzy Support Vector Machines for Multicategory Pattern Classification | 109 |
A Modified FCM Algorithm for Fast Segmentation of Brain MR Images | 119 |
Incorporation of Noneuclidean Distance Metrics into Fuzzy Clustering on Graphics Processing Units | 128 |
A Comparative Study | 140 |
Improved Fuzzy CMeans Segmentation Algorithm for Images with Intensity Inhomogeneity | 150 |
Part III Intelligent Identification and Control | 160 |
A FuzzyNeural Hierarchical Multimodel for Systems Identification and Direct Adaptive Control | 163 |
Robust Speed Controller Design Method Based on Fuzzy Control for Torsional Vibration Suppression in TwoMass System | 173 |
Selforganizing Fuzzy Controller Based on Fuzzy Neural Network | 185 |
Decision Making Strategies for RealTime Train Dispatch and Control | 195 |
Soft Margin Training for Associative Memories Implemented by Recurrent Neural Networks | 205 |
Part IV Time Series Prediction | 215 |
Modular Neural Networks with Fuzzy Integration Applied for Time Series Forecasting | 216 |
Predicting Job Completion Time in a Wafer Fab with a Recurrent Hybrid Neural Network | 226 |
A Hybrid ANNFIR System for Lot Output Time Prediction and Achievability Evaluation in a Wafer Fab | 236 |
MFactor High Order Fuzzy Time Series Forecasting for Road Accident Data | 246 |
A Realistic Method to Forecast Gross Domestic Capital of India | 255 |
Design of Modular Neural Networks with Fuzzy Integration Applied to Time Series Prediction | 265 |
Part V Pattern Recognition | 274 |
Characterize the Parameters of Genetic Algorithms Based on Zernike Polynomials for Recovery of the Phase of Interferograms of Closed Fringes Usi... | 275 |
Rotated Coin Recognition Using Neural Networks | 290 |
Selected Problems of Intelligent Handwriting Recognition | 298 |
3D Object Recognition Using an Ultrasonic Sensor Array and Neural Networks | 306 |
Soft System for Road Sign Detection | 316 |
Nonlinear Neurofuzzy Network for Channel Equalization | 327 |
On the Possibility of Reliably Constructing a Decision Support System for the Cytodiagnosis of Breast Cancer | 337 |
Spatial Heart Simulation and Analysis Using Unified Neural Network | 346 |
A Method for Creating Ensemble Neural Networks Using a Sampling Data Approach | 355 |
Pattern Recognition Using Modular Neural Networks and Fuzzy Integral as Method for Response Integration | 365 |
Part VI Evolutionary Computation | 374 |
A Differential Evolution Algorithm for Fuzzy Extension of Functions | 375 |
Use of ParetoOptimal and Near ParetoOptimal Candidate Rules in Genetic Fuzzy Rule Selection | 387 |
A Dissimilation Particle Swarm OptimizationBased Elman Network and Applications for Identifying and Controlling Ultrasonic Motors | 397 |
A Cultural Algorithm for Solving the Set Covering Problem | 408 |
Integration of Production and Distribution Planning Using a Genetic Algorithm in Supply Chain Management | 416 |
Bacteria Swarm Foraging Optimization for Dynamical Resource Allocation in a Multizone Temperature Experimentation Platform | 427 |
A Dynamic Method of Experiment Design of Computer Aided Sensory Evaluation | 504 |
Measure of Uncertainty in Regional Grade Variability | 511 |
PCTOPSIS Method for the Selection of a Cleaning System for Engine Maintenance | 519 |
Coordination Uncertainty of Belief Measures in Information Fusion | 530 |
TwoInput Fuzzy TPE Systems | 539 |
Intelligent Decision Support System | 549 |
An Adaptive Location Service on the Basis of Fuzzy Logic for MANETs | 558 |
Part VIII Intelligent Manufacturing and Scheduling | 566 |
Fuzzy Logic Based Replica Management Infrastructure for Balanced Resource Allocation and Efficient Overload Control of the Complex ServiceOrie... | 567 |
A FuzzyNeural Approach with BPN Postclassification for Job Completion Time Prediction in a Semiconductor Fabrication Plant | 580 |
Enhanced Genetic AlgorithmBased Fuzzy Multiobjective Strategy to Multiproduct Batch Plant Design | 590 |
A Novel Approach for Reasoning in Possibilistic Logic | 600 |
Applying GeneticFuzzy Approach to Model Polyester Dyeing | 608 |
Gear Fault Diagnosis in Time Domains by Using Bayesian Networks | 618 |
An Intelligent Hybrid Algorithm for JobShop Scheduling Based on Particle Swarm Optimization and Artificial Immune System | 628 |
Fuzzy Multicriteria Decision Making Method for Machine Selection | 638 |
Fuzzy Goal Programming and an Application of Production Process | 649 |
The Usage of Fuzzy Quality Control Charts to Evaluate Product Quality and an Application | 660 |
Part IX Intelligent Agents | 674 |
An Intelligent BeliefDesireIntention Agent for Digital GameBased Learning | 675 |
Improved Scheme for Telematics Fault Tolerance with Agents | 686 |
Multiagent Based Integration of Production and Distribution Planning Using Genetic Algorithm in the Supply Chain Management | 696 |
Modeling and Simulation by Petri Networks of a Fault Tolerant Agent Node | 707 |
Part X Neural Networks Theory | 717 |
The Game of Life Using Polynomial Discrete Time Cellular Neural Networks | 719 |
Wavelet Networks Approach | 727 |
Support Vector MachineBased ECG Compression | 737 |
Tuning FCMP to Elicit Novel Time Course Signatures in fMRI Neural Activation Studies | 746 |
Part XI Robotics | 756 |
Moving Object Tracking Using the Particle Filter and SOM in Robotic Space with Network Sensors | 757 |
Robust Stability Analysis of a Fuzzy Vehicle Lateral Control System Using Describing Function Method | 769 |
A Comparative Study for a Drone | 780 |
Optimal Path Planning for Autonomous Mobile Robot Navigation Using Ant Colony Optimization and a Fuzzy Cost Function Evaluation | 790 |
Intelligent Control and Planning of Autonomous Mobile Robots Using Fuzzy Logic and Multiple Objective Genetic Algorithms | 799 |
Part XII Fuzzy Logic Applications | 808 |
Generalized Reinforcement Learning Fuzzy Control with Vague States | 809 |
New Cluster Validity Index with Fuzzy Functions | 821 |
A Fuzzy Model for Supplier Selection and Development | 831 |
A Neurofuzzy Multiobjective Design of Shewhart Control Charts | 842 |
Author Index | 853 |
Other editions - View all
Common terms and phrases
adaptive agent algorithm applied approach average calculated channel classification clustering complex Computer considered cost decision defined described determined developed distance distribution dynamic effect equal error estimation evaluation example experiments fault Figure fuzzy logic fuzzy rules fuzzy sets fuzzy system genetic algorithm given IEEE improve initial input integrated Intelligent interval layer learning linguistic machine manufacturer means measure membership functions method modular neural network node objective obtained operation optimal output parameters pattern performance period planning population position possibilistic prediction presented problem production programming proposed recognition References represented respectively robot rules samples selection shown signal simulation solution space speed step structure Table theory tion type-2 fuzzy uncertainty University variables vector weights
Popular passages
Page 69 - A higher-type number just indicates a higher "degree of fuzziness". Since a higher type changes the nature of the membership functions, the operations that depend on the membership functions change; however, the basic principles of fuzzy logic are independent of the nature of membership functions and hence, do not change. Rules of inference like Generalized Modus Ponens or Generalized Modus Tollens continue to apply.
Page 218 - The neural network generally consists of at least three layers: one input layer, one output layer, and one or more hidden layers. Figure...
Page 69 - ... the membership grade is a crisp number in [0,1]. Such sets can be used in situations where there is uncertainty about the membership grades themselves, eg, an uncertainty in the shape of the membership function or in some of its parameters. Consider the transition from ordinary sets to fuzzy sets. When we cannot determine the membership of an element in a set as 0 or 1 , we use fuzzy sets of type-1. Similarly, when the situation is so fuzzy that we have trouble determining the membership grade...
Page 221 - X be a finite set and h:X— >[0,1] be a fuzzy subset of X, the fuzzy integral over X of function h with respect to the fuzzy measure g is defined in the following way...
Page 69 - ... type reduction" and call the type-1 fuzzy set so obtained a "type-reduced set". The typereduced fuzzy set may then be defuzzified to obtain a single crisp number; however, in many applications, the type-reduced set may be more important than a single crisp number. Type-2 sets can be used to convey the uncertainties in membership functions of type-1 fuzzy sets, due to the dependence of the membership functions on available linguistic and numerical information. Linguistic information (eg rules...
Page 446 - ... solution. At each generation, a new set of approximations is created by the process of selecting individuals according to their level of fitness in the problem domain and breeding them together using operators borrowed from natural genetics. This...
Page 108 - Knowledge-based analysis of microarray gene expression data by using support vector machines.
Page 64 - The HGA approach has a number of advantages: 1) An optimal and the least number of membership functions and rules are obtained 2) No pre-fixed fuzzy structure is necessary, and 3) Simpler implementing procedures and less cost are involved. We consider in this paper the case of automatic anesthesia control in human patients for testing the optimized fuzzy controller. We did have, as a reference, the best fuzzy controller that was developed for the automatic anesthesia control [10, 11], and we consider...
Page 31 - ... gives a crisp number at the output of the fuzzy system, the extended defuzzification operation in the type-2 case gives a type-1 fuzzy set at the output. Since this operation takes us from the type-2 output sets of the fuzzy system to a type-1 set, we can call this operation "type reduction" and call the type-1 fuzzy set so obtained a "type-reduced set".