## Recent Advances in Intelligent Paradigms and ApplicationsDigital systems that bring together the computing capacity for processing large bodies of information with the human cognitive capability are called intelligent systems. Building these systems has become one of the great goals of modem technology. This goal has both intellectual and economic incentives. The need for such intelligent systems has become more intense in the face of the global connectivity of the internet. There has become an almost insatiable requirement for instantaneous information and decision brought about by this confluence of computing and communication. This requirement can only be satisfied by the construction of innovative intelligent systems. A second and perhaps an even more significant development is the great advances being made in genetics and related areas of biotechnology. Future developments in biotechnology may open the possibility for the development of a true human-silicon interaction at the micro level, neural and cellular, bringing about a need for "intelligent" systems. What is needed to further the development of intelligent systems are tools to enable the representation of human cognition in a manner that allows formal manipulation. The idea of developing such an algebra goes back to Leibniz in the 17th century with his dream of a calculus ratiocinator. It wasn't until two hundred years later beginning with the work of Boole, Cantor and Frege that a formal mathematical logic for modeling human reasoning was developed. The introduction of the modem digital computer during the Second World War by von Neumann and others was a culmination of this intellectual trend. |

### What people are saying - Write a review

We haven't found any reviews in the usual places.

### Contents

Architectures and Perspectives | 1 |

2 Models Of Hybrid Soft Computing Architectures | 4 |

22 Transformational Hybrid Intelligent System | 5 |

24 Integrated Intelligent System | 6 |

31 Meta Learning Evolutionary Artificial Neural Networks | 8 |

4 Adaptation of Fuzzy Inference Systems | 12 |

5 Evolutionary Fuzzy Systems | 14 |

6 Cooperative NeuroFuzzy Systems | 15 |

7 Conclusions | 154 |

References | 156 |

NeuroFuzzy Methods for Modeling and Identification | 161 |

21 Nonlinear System Identification | 162 |

23 Artificial Neural Networks | 166 |

3 NeuroFuzzy Modeling | 172 |

31 Constructing NeuroFuzzy Networks | 174 |

33 GradientBased Learning | 175 |

61 Fuzzy Associative Memories | 16 |

62 Fuzzy Rule Extraction Using Self Organizing Maps | 17 |

63 Systems Capable of Learning Fuzzy Set Parameters | 18 |

7 Integrated NeuroFuzzy Systems | 19 |

71 Integrated NeuroFuzzy System Mamdani FIS | 20 |

72 Integrated Neurofuzzy system TakagiSugeno FIS | 21 |

8 NeuroFuzzyEvolutionary EvoNF Systems | 24 |

9 Fuzzy Evolutionary Algorithms | 26 |

1O Soft Computing and Probabilistic Reasoning | 27 |

Acknowledgements | 28 |

Hybrid Architecture for Autonomous Robots Based on Representation Perception and Intelligent Control | 37 |

11 Autonomy in robotic systems | 38 |

12 Robot control architectures | 39 |

2 HARPIC | 40 |

22 Management of perception resources | 42 |

23 Assessment mechanisms within the control architecture | 43 |

24 Comparison with other architectures | 47 |

25 Implementation and experiments | 49 |

3 Computational intelligence and controlled autonomy | 53 |

4 Computational intelligence and learning | 54 |

5 Conclusion | 55 |

An Application to Medical Diagnosis | 57 |

2 Brief Introduction to Intuitionistic Fuzzy Sets | 59 |

2 1 Distances Between Intuitionistic Fuzzy Sets | 61 |

3 An Intuitionistic Fuzzy Sets Approach to Medical Diagnosis due to De Biswas and Roy | 64 |

4 Medical Diagnosis via Distances for Intuitionistic Fuzzy Sets | 67 |

5 Conclusions | 69 |

References | 70 |

A Fuzzy Inference Methodology Based on the Fuzzification of Set Inclusion | 71 |

2 Classical Inference Strategies | 73 |

3 InclusionBased Approach | 79 |

32 InclusionBased Reasoning with One Fuzzy Rule | 82 |

33 InclusionBased Reasoning with Parallel Fuzzy Rules | 83 |

4 Conclusion | 87 |

5 Acknowledgements | 88 |

A Fuzzy Approach to JobShop Scheduling Problem Based on Imprecise Processing Times | 91 |

2 The JobShop Scheduling Problem | 93 |

22 Fuzzy Job Processing Times | 94 |

3 Preliminaries | 95 |

4 Fuzzy Job Shop Scheduling Model Based on Imprecise Processing Times | 98 |

5 Computational Results | 101 |

6 Concluding Remarks | 104 |

References | 105 |

Towards an Optimal Combination of Granularity and HigherOrder Approaches | 107 |

Case Study | 111 |

3 Selecting Operations that Are in Optimal Agreement with Granularity | 116 |

4 Optimal Selection of HigherOrder Approach | 122 |

Preliminary Results | 126 |

6 Conclusions | 128 |

Acknowledgments | 129 |

Discovering Efficient Learning Rules for Feedforward Neural Networks Using Genetic Programming | 133 |

2 Standard Backpropagation Algorithm and Recent Improvements | 135 |

22 Improvements to SBP | 136 |

3 Previous Work on the Evolution of Neural Network Learning Rules | 138 |

4 Our Approach to Evolving Learning Rules with GP | 140 |

Learning Rules for Output Layers | 141 |

Learning Rules for Hidden Layers | 143 |

6 Discussion | 151 |

35 Initialization of Antecedent Membership Functions | 179 |

4 Simulation Examples | 181 |

42 pH Neutralization Process | 183 |

5 Concluding Remarks | 185 |

References | 186 |

Constrained Two Dimensional Bin Packing Using a Genetic Algorithm | 187 |

2 Some Industrial Applications of 2Dimensional Bin Packing | 189 |

23 Packing | 190 |

3 A Brief Description of Genetic Algorithm | 191 |

33 Selection | 192 |

34 Crossover | 193 |

35 Mutation | 194 |

4 Proposed Genetic Algorithm for TwoDimensional Packing | 195 |

41 Model Representation | 196 |

42 Objective Function | 197 |

45 Mutation | 198 |

452 Orientation | 199 |

47 Constraint Handling | 200 |

5 Performance Evaluation of TwoDimensional Genetic Algorithm | 201 |

52 Comparison With Another Genetic Algorithm | 205 |

6 Conclusion | 208 |

Cargo Details | 210 |

Sequential and Distributed Evolutionary Algorithms for Combinatorial Optimization Problems | 211 |

2 The Evolutionary Algorithms | 212 |

21 Sequential Evolutionary Algorithms | 214 |

22 Distributed Evolutionary Algorithms | 215 |

3 Combinatorial Optimization Problems | 216 |

31 The Maximum Cut Problem | 217 |

32 The Error Correcting Code Design Problem | 219 |

33 The Minimum Tardy Task Problem | 221 |

4 Experimental Runs | 224 |

41 Results for the Maximum Cut Problem | 225 |

42 Results for the ECC Problem | 226 |

43 Results for the Minimum Tardy Task Problem | 228 |

5 Conclusion | 230 |

References | 232 |

Embodied Emotional Agent in Intelligent Training System | 235 |

2 The problem of emotion generation | 237 |

23 Models of architecture for emotion generation | 239 |

3 Producing emotions by qualitative reasoning | 240 |

31 Qualitative reasoning | 241 |

33 Emotion generation based on a qualitative reasoning system | 243 |

41 Operational context | 244 |

42 Architecture overview | 245 |

43 Choosing and treating the input | 246 |

44 Generating emotions | 248 |

45 Providing visual feedback from emotions | 249 |

5 Discussions and conclusion | 250 |

251 | |

Optimizing Intelligent Agents Constraint Satisfaction with Neural Networks | 255 |

2 Preparing the Input for the Neural Networks | 257 |

3 Design of Neural Network | 259 |

32 Neural Network Selection and Criteria | 260 |

33 Learning Algorithms for FFNN | 261 |

4 Data Analysis and Results | 262 |

5 Conclusion | 270 |

### Other editions - View all

### Common terms and phrases

adaptation agent antecedent applications approach approximately architecture Artiﬁcial Neural Networks attention manager backpropagation behavior binary cargos classiﬁcation coefﬁcients conﬁdence constraints crossover deﬁned Deﬁnition degree describe difﬁcult efﬁcient embodied agent emotions environment error evolutionary algorithms Evolutionary Computation example expert ﬁnd ﬁrst ﬁtness ﬁxed fuzzy inference system fuzzy logic fuzzy model fuzzy number fuzzy rules Fuzzy Systems genetic algorithm genGA global granularity Hamming distance heuristic hidden layer hybrid identiﬁcation input intelligent systems interval intuitionistic fuzzy relation intuitionistic fuzzy sets job-shop scheduling problem Kreinovich learning algorithms learning rules machine membership functions method modiﬁcation mutation neuro-fuzzy neuro-fuzzy models neuro-fuzzy systems neurons NLRO number of hidden objective function operations packing problems parameters perception processes performance problem instance proposed real number reasoning represent representation robot Rprop satisﬁed selection Soft Computing solution speciﬁc string supervised learning Support Vector Machine T-norm Table techniques Theorem variables vector weights