Atnaujinkite slapukų nuostatas

El. knyga: Real Life Applications of Soft Computing

, ,
  • Formatas: 686 pages
  • Išleidimo metai: 21-May-2010
  • Leidėjas: CRC Press Inc
  • Kalba: eng
  • ISBN-13: 9781439822890
Kitos knygos pagal šią temą:
Real Life Applications of Soft ComputingDidesnis paveikslėlis
  • Formatas: 686 pages
  • Išleidimo metai: 21-May-2010
  • Leidėjas: CRC Press Inc
  • Kalba: eng
  • ISBN-13: 9781439822890
Kitos knygos pagal šią temą:

DRM apribojimai

  • Kopijuoti:

    neleidžiama

  • Spausdinti:

    neleidžiama

  • El. knygos naudojimas:

    Skaitmeninių teisių valdymas (DRM)
    Leidykla pateikė šią knygą šifruota forma, o tai reiškia, kad norint ją atrakinti ir perskaityti reikia įdiegti nemokamą programinę įrangą. Norint skaityti šią el. knygą, turite susikurti Adobe ID . Daugiau informacijos  čia. El. knygą galima atsisiųsti į 6 įrenginius (vienas vartotojas su tuo pačiu Adobe ID).

    Reikalinga programinė įranga
    Norint skaityti šią el. knygą mobiliajame įrenginyje (telefone ar planšetiniame kompiuteryje), turite įdiegti šią nemokamą programėlę: PocketBook Reader (iOS / Android)

    Norint skaityti šią el. knygą asmeniniame arba „Mac“ kompiuteryje, Jums reikalinga  Adobe Digital Editions “ (tai nemokama programa, specialiai sukurta el. knygoms. Tai nėra tas pats, kas „Adobe Reader“, kurią tikriausiai jau turite savo kompiuteryje.)

    Negalite skaityti šios el. knygos naudodami „Amazon Kindle“.

Rapid advancements in the application of soft computing tools and techniques have proven valuable in the development of highly scalable systems and resulted in brilliant applications, including those in biometric identification, interactive voice response systems, and data mining. Although many resources on the subject adequately cover the theoretic concepts, few provide clear insight into practical application.





Filling this need, Real Life Applications of Soft Computing explains such applications, including the underlying technology and its implementation. While these systems initially seem complex, the authors clearly demonstrate how they can be modeled, designed, and implemented. Written in a manner that makes it accessible to novices, the book begins by covering the theoretical foundations of soft computing. It supplies a concise explanation of various models, principles, algorithms, tools, and techniques, including artificial neural networks, fuzzy systems, evolutionary algorithms, and hybrid algorithms.





Supplying in-depth exposure to real life systems, the text provides:



















Multi-dimensional coverage supported by references, figures, and tables













Warnings about common pitfalls in the implementation process, as well as detailed examinations of possible solutions













A timely account of developments in various areas of application













Solved examples and exercises in each chapter











Detailing a wide range of contemporary applications, the text includes coverage of those in biometric systems, including physiological and behavioral biometrics. It also examines applications in legal threat assessment, robotic path planning, and navigation control. The authors consider fusion methods in biometrics and bioinformatics and also provide effective disease identification techniques.





Co
Foreword xxv
Preface xxvii
Acknowledgments xxix
Authors xxxi
SECTION I Soft-Computing Concepts
Chapter 1 Introduction
3(38)
1.1 Soft Computing
3(5)
1.1.1 What is Soft Computing?
4(1)
1.1.2 Soft Computing versus Hard Computing
5(2)
1.1.3 Soft-Computing Systems
7(1)
1.2 Artificial Intelligence
8(7)
1.2.1 What is Artificial Intelligence?
9(1)
1.2.2 Problem Solving in AI
10(4)
1.2.3 Logic in Artificial Intelligence
14(1)
1.3 Soft-Computing Techniques
15(4)
1.3.1 Artificial Neural Networks
15(1)
1.3.2 Fuzzy Systems
16(1)
1.3.3 Evolutionary Algorithm
17(1)
1.3.4 Hybrid Systems
18(1)
1.4 Expert Systems
19(4)
1.4.1 What are Expert Systems?
20(1)
1.4.2 Expert System Design
21(1)
1.4.3 High-End Planning and Autonomous Systems
22(1)
1.5 Types of Problems
23(1)
1.5.1 Classification
23(1)
1.5.2 Functional Approximation
24(1)
1.5.3 Optimizations
24(1)
1.6 Modeling the Problem
24(4)
1.6.1 Input
25(2)
1.6.2 Ouputs
27(1)
1.6.3 System
27(1)
1.7 Machine Learning
28(2)
1.7.1 What is Machine Learning?
28(1)
1.7.2 Historical Database
28(1)
1.7.3 Data Acquisition
29(1)
1.7.4 Pattern Matching
29(1)
1.8 Handling Impreciseness
30(1)
1.8.1 Uncertainties in Data
30(1)
1.8.2 Noise
30(1)
1.9 Clustering
31(3)
1.9.1 K-Means Clustering
31(1)
1.9.2 Fuzzy C-Means Clustering
32(1)
1.9.3 Subtractive Clustering
33(1)
1.10 Hazards of Soft Computing
34(1)
1.11 Road Map for the Future
34(2)
1.11.1 Accuracy
34(1)
1.11.2 Input Limitations
35(1)
1.11.3 Computational Constraints
35(1)
1.11.4 Analogy with the Human Brain
35(1)
1.11.5 What to Expect in the Future
35(1)
1.12 Conclusions
36(5)
Chapter Summary
36(1)
Solved Examples
37(1)
Rule-Based Approach
38(1)
Soft-Computing Approach
38(1)
Exercises
39(1)
General Questions
39(1)
Programming and Practical Questions
40(1)
Chapter 2 Artificial Neural Networks I
41(34)
2.1 Artificial Neural Networks
41(2)
2.1.1 Historical Note
41(2)
2.2 The Biological Neuron
43(1)
2.3 The Artificial Neuron
44(2)
2.3.1 Structure
44(1)
2.3.2 The Processing of the Neuron
45(1)
2.3.3 The Perceptron
46(1)
2.4 Multilayer Perceptron
46(5)
2.4.1 Layers
47(1)
2.4.2 Weights
47(1)
2.4.3 Activation Functions
48(2)
2.4.4 Feed-Forward Neural Network
50(1)
2.5 Modeling the Problem
51(4)
2.5.1 Functional Prediction
51(1)
2.5.2 Classification
52(1)
2.5.3 Normalization
53(1)
2.5.4 The Problem of Nonlinear Separability
53(1)
2.5.5 Bias
54(1)
2.6 Types of Data Involved
55(1)
2.7 Training
55(9)
2.7.1 Types of Learning
56(1)
2.7.2 The Stages of Supervised Learning
57(1)
2.7.3 Error Function
57(1)
2.7.4 Epoch
58(1)
2.7.5 Learning Rate
59(1)
2.7.6 Variable Learning Rate
60(1)
2.7.7 Momentum
60(1)
2.7.8 Stopping Condition
61(1)
2.7.9 Back Propagation Algorithm
61(1)
2.7.10 Steepest Descent Approach
61(1)
2.7.11 Mathematical Analysis of the BPA Expression
62(2)
2.8 Issues in ANN
64(2)
2.8.1 Convergence
64(1)
2.8.2 Generalization
65(1)
2.8.3 Overgeneralization
65(1)
2.8.4 Complexity
66(1)
2.9 Example of Time Series Forecasting
66(3)
2.9.1 Problem Description
66(1)
2.9.2 Inputs
67(1)
2.9.3 Outputs
67(1)
2.9.4 Network
68(1)
2.9.5 Results
68(1)
2.10 Conclusions
69(6)
Chapter Summary
69(1)
Solved Examples
70(2)
Exercises
72(1)
General Questions
72(1)
Practical Questions
73(2)
Chapter 3 Artificial Neural Networks II
75(28)
3.1 Types of Artificial Neural Networks
75(2)
3.1.1 Unsupervised Learning
75(1)
3.1.2 Reinforcement Learning
76(1)
3.2 Radial Basis Function Network
77(3)
3.2.1 Concept
77(1)
3.2.2 Network Architecture
78(1)
3.2.3 Mathematical Analysis
78(1)
3.2.4 Training
79(1)
3.3 Learning Vector Quantization
80(4)
3.3.1 Concept
80(1)
3.3.2 Architecture
81(1)
3.3.3 Mathematical Modeling
81(1)
3.3.4 Training
82(1)
3.3.4.1 LVQ 1 Algorithm
82(1)
3.3.4.2 LVQ 2.1 Algorithm
83(1)
3.4 Self-Organizing Maps
84(2)
3.4.1 Concept
84(1)
3.4.2 Architecture
84(1)
3.4.3 Mathematical Analysis
85(1)
3.4.4 Training
85(1)
3.5 Recurrent Neural Network
86(1)
3.5.1 Concept
86(1)
3.5.2 Architecture
86(1)
3.5.3 Training
87(1)
3.6 Hopfield Neural Network
87(3)
3.6.1 Concept
88(1)
3.6.2 Architecture
88(1)
3.6.3 Mathematical Modeling
88(1)
3.6.4 Training
89(1)
3.7 Adaptive Resonance Theory
90(2)
3.7.1 Concept
90(1)
3.7.2 Architecture
90(1)
3.7.3 Training
91(1)
3.8 Character Recognition by Commonly Used ANNs
92(11)
3.8.1 Problem Description
92(1)
3.8.2 Inputs
93(1)
3.8.3 Outputs
93(1)
3.8.4 Solution by Radial Basis Function Network
93(1)
3.8.5 Solution by Learning Vector Quantization
93(1)
3.8.6 Solution by Self-Organizing Map
94(1)
3.8.7 Solution by Recurrent Neural Network
95(1)
3.8.8 Solution by Hopfield Neural Network
96(1)
Chapter Summary
97(1)
Solved Examples
97(3)
Exercises
100(1)
General Questions
100(1)
Practical Questions
101(2)
Chapter 4 Fuzzy Inference Systems
103(44)
4.1 Fuzzy Systems
103(1)
4.2 Historical Note
104(1)
4.3 Fuzzy Logic
104(4)
4.3.1 Logic
104(1)
4.3.2 Problems with Nonfuzzy Logic
105(2)
4.3.3 Fuzzy Logic
107(1)
4.3.4 When Not to Use Fuzzy
107(1)
4.3.4 Fuzzy Sets
108(1)
4.4 Membership Functions
108(4)
4.4.1 Gaussian Membership Functions
109(1)
4.4.2 Triangular Membership Function
110(1)
4.4.3 Sigmoidal Membership Function
110(1)
4.4.4 Other Membership Functions
111(1)
4.5 Fuzzy Logical Operators
112(8)
4.5.1 And Operator
113(1)
4.5.1.1 Realization of Min and Product
113(2)
4.5.2 Or Operator
115(1)
4.5.2.1 Realization of Max
115(2)
4.5.3 Not Operator
117(1)
4.5.4 Implication
118(2)
4.6 More Operations
120(4)
4.6.1 Aggregation
120(1)
4.6.1.1 Realization of Sum and Max
120(1)
4.6.2 Defuzzification
121(3)
4.7 Fuzzy Inference Systems
124(6)
4.7.1 Fuzzy Inference System Design
124(1)
4.7.2 The Fuzzy Process
125(1)
4.7.3 Illustrative Example
126(3)
4.7.4 Surface Diagrams
129(1)
4.8 Type-2 Fuzzy Systems
130(4)
4.8.1 T2 Fuzzy Sets
130(2)
4.8.2 Representations of T2 FS
132(1)
4.8.3 Solving a T2 Fuzzy System
132(2)
4.9 Other Sets
134(2)
4.9.1 Rough Sets
134(1)
4.9.2 Vague Sets
135(1)
4.9.3 Intuitionistic Fuzzy Sets
135(1)
4.10 Sugeno Fuzzy Systems
136(1)
4.11 Example: Fuzzy Controller
136(11)
4.11.1 Problem Description
136(1)
4.11.2 Inputs and Outputs
137(1)
4.11.3 Membership Functions
138(2)
4.11.4 Rules
140(1)
4.11.5 Results and Simulation
140(2)
Chapter Summary
142(1)
Solved Examples
142(3)
Exercise
145(1)
General Questions
145(1)
Practical Questions
146(1)
Chapter 5 Evolutionary Algorithms
147(34)
5.1 Evolutionary Algorithms
147(1)
5.2 Historical Note
148(1)
5.3 Biological Inspiration
148(1)
5.4 Genetic Algorithms
149(8)
5.4.1 Concept
149(1)
5.4.2 Solution
150(2)
5.4.3 Initial Population
152(1)
5.4.4 Genetic Operators
153(3)
5.4.5 Fitness Function
156(1)
5.4.6 Stopping Condition
156(1)
5.5 Fitness Scaling
157(1)
5.5.1 Rank Scaling
157(1)
5.5.2 Proportional Scaling
158(1)
5.5.3 Top Scaling
158(1)
5.6 Selection
158(2)
5.6.1 Roulette Wheel Selection
158(1)
5.6.2 Stochastic Universal Sampling
159(1)
5.6.3 Rank Selection
159(1)
5.6.4 Tournament Selection
159(1)
5.6.5 Other Selection Methods
160(1)
5.7 Mutation
160(1)
5.7.1 Uniform Mutation
160(1)
5.7.2 Gaussian Mutation
161(1)
5.7.3 Variable Mutation Rate
161(1)
5.8 Crossover
161(1)
5.8.1 One-Point Crossover
161(1)
5.8.2 Two-Point Crossover
161(1)
5.8.3 Scattered Crossover
162(1)
5.8.4 Intermediate Crossover
162(1)
5.8.5 Heuristic Crossover
162(1)
5.9 Other Genetic Operators
162(1)
5.9.1 Eliticism
163(1)
5.9.2 Insert and Delete
163(1)
5.9.3 Hard and Soft Mutation
163(1)
5.9.4 Repair
163(1)
5.10 Algorithm Working
163(4)
5.10.1 Convergence
165(2)
5.11 Diversity
167(1)
5.12 Grammatical Evolution
168(2)
5.13 Other Optimization Techniques
170(3)
5.13.1 Particle Swarm Optimization
170(1)
5.13.2 Ant Colony Optimizations
171(2)
5.14 Metaheuristic Search
173(1)
5.15 Traveling Salesman Problem
173(8)
5.15.1 Problem Description
173(1)
5.15.2 Crossover
174(1)
5.15.3 Mutation
174(1)
5.15.4 Fitness Function
174(1)
5.15.5 Results
175(1)
Chapter Summary
176(1)
Solved Examples
176(3)
Questions
179(1)
General Questions
179(1)
Practical Questions
179(2)
Chapter 6 Hybrid Systems
181(34)
6.1 Introduction
181(1)
6.2 Key Takeaways from Individual Systems
182(1)
6.2.1 Artificial Neural Networks
182(1)
6.2.2 Fuzzy Systems
182(1)
6.2.3 Genetic Algorithms
182(1)
6.2.4 Logic and AI-Based Systems
182(1)
6.3 Adaptive Neuro-Fuzzy Inference Systems
182(6)
6.3.1 General Architecture
183(1)
6.3.1.1 Layer 0
183(1)
6.3.1.2 Layer 1
183(1)
6.3.1.3 Layer 2
184(1)
6.3.1.4 Layer 3
184(1)
6.3.1.5 Layer 4
184(1)
6.3.1.6 Layer 5
184(1)
6.3.2 Problem Solving in ANFIS
184(1)
6.3.2.1 Initial FIS
185(1)
6.3.2.2 Clustering Training Data
185(1)
6.3.2.3 Parameterization of the FIS
185(1)
6.3.2.4 Training
185(1)
6.3.2.5 Testing
185(1)
6.3.3 Training
185(1)
6.3.3.1 Back Propagation Algoritm
185(1)
6.3.3.2 Hybrid Training
186(1)
6.3.4 Types of ANFIS
186(1)
6.3.5 Convergence in ANFIS
186(1)
6.3.6 Application in a Real Life Problem
186(2)
6.4 Evolutionary Neural Networks
188(4)
6.4.1 Evolving a Fixed-Structure ANN
188(1)
6.4.1.1 Problem Encoding
189(1)
6.4.1.2 Genetic Operators
189(1)
6.4.1.3 Fitness Function
189(1)
6.4.1.4 Testing
190(1)
6.4.2 Evolving-Variable Structure ANN
191(1)
6.4.2.1 Direct Encoding
191(1)
6.4.2.2 Grammatical Encoding
192(1)
6.4.2.3 Fitness Function
192(1)
6.4.3 Evolving Learning Rule
192(1)
6.5 Evolving Fuzzy Logic
192(8)
6.5.1 Evolving a Fixed-Structure FIS
193(1)
6.5.1.1 Experimental Verification
194(3)
6.5.2 Evolving-a Variable-Structured FIS
197(3)
6.6 Fuzzy Artificial Neural Networks with Fuzzy Inputs
200(3)
6.6.1 Basic Conecpts
200(1)
6.6.2 Fuzzy Arithmetic Operations
200(2)
6.6.3 ALPHA Cut
202(1)
6.6.4 Modified BPA
202(1)
6.7 Rule Extraction from ANN
203(2)
6.7.1 Need of Rule Extraction
203(1)
6.7.2 System Inputs Outputs, and Performance
204(1)
6.7.3 Extraction Algorithms
204(1)
6.8 Modular Neural Network
205(10)
6.8.1 Need for MNNs
205(1)
6.8.2 Biological Inspiration
205(1)
6.8.3 Modularity in ANN
205(1)
6.8.4 Working of the MNNs
206(1)
6.8.4.1 ART-BP Network
206(1)
6.8.4.2 Hierarchical Network
207(1)
6.8.4.3 Multiple-Experts Network
207(1)
6.8.4.4 Ensemble Networks
207(1)
6.8.4.5 Hierarchical Competitive Modular Neural Network
208(1)
6.8.4.6 Merge-and-Glue Network
208(1)
Chapter Summary
209(1)
Solved Examples
210(1)
Questions
211(1)
General Questions
211(1)
Practical Questions
212(3)
SECTION II Soft Computing in Biosystems
Chapter 7 Physiological Biometrics
215(32)
7.1 Introduction
215(1)
7.1.1 What Is a Biometric System?
215(1)
7.1.2 Need for Biometric Systems
215(1)
7.2 Types of Biometric Systems
216(1)
7.2.1 Physiological Biometric Systems
216(1)
7.2.2 Behavioral Biometric Systems
217(1)
7.2.3 Fused Biometric Systems
217(1)
7.3 Recognition Systems
217(1)
7.4 Face Recognition
218(17)
7.4.1 Dimensionality Reduction with PCA
219(1)
7.4.1.1 Standard Deviation
220(1)
7.4.1.2 Covariance
221(1)
7.4.1.3 Covariance Matrix
221(1)
7.4.1.4 Eigen Vectors
221(2)
7.4.2 Dimensionality Reduction by R-LDA
223(1)
7.4.3 Morphological Methods
224(5)
7.4.4 Classification with ANNs
229(1)
7.4.4.1 The ANN with BPA
230(1)
7.4.4.2 RBFN
230(1)
7.4.5 Results
231(1)
7.4.5.1 PCA, R-LDA, and MA with ANN and BPA
231(2)
7.4.5.2 PCA and R-LDA with RBFN
233(1)
7.4.6 Concluding Remarks for Face as a Biometric
234(1)
7.5 Hand Geometry
235(6)
7.5.1 Image Acquisition
236(1)
7.5.2 Image Preprocessing
237(1)
7.5.2.1 Filtering
237(1)
7.5.2.2 Binarization
237(1)
7.5.2.3 Contour Detection
237(1)
7.5.3 Feature Extraction
238(1)
7.5.3.1 Finger Baselines
238(1)
7.5.3.2 Finger Lengths
239(1)
7.5.3.3 Finger Widths
239(1)
7.5.4 Classification by ANN
239(1)
7.5.5 Results
239(2)
7.5.6 Concluding Remarks for Hand as a Biometric
241(1)
7.6 Iris
241(6)
7.6.1 Human Iris
242(1)
7.6.2 Image Acquisition
243(1)
7.6.3 Preprocessing
243(1)
7.6.4 Feature Extraction
243(2)
7.6.5 Results
245(1)
7.6.6 Concluding Remarks for Iris as a Biometric
245(2)
Chapter 8 Behavioral Biometrices
247(28)
8.1 Introduction
247(1)
8.2 Speech
248(21)
8.2.1 Speech Input
248(2)
8.2.2 Speech Features
250(1)
8.2.2.1 Cepstral Analysis
250(1)
8.2.2.2 Power Spectral Density
250(1)
8.2.2.3 Spectrogram Analysis
251(1)
8.2.2.4 Number of Zero Crossings
252(1)
8.2.2.5 Formant Frequencies
252(1)
8.2.2.6 Time
252(1)
8.2.2.7 Pitch and Amplitude
252(1)
8.2.3 Wavelet Analysis
252(1)
8.2.3.1 Fourier Analysis
252(1)
8.2.3.2 Short-Time Fourier Analysis
253(1)
8.2.3.3 Wavelet Analysis
253(1)
8.2.4 ANN with BPA
254(1)
8.2.5 ANFIS
255(1)
8.2.6 Modular Neural Network
256(1)
8.2.7 Systems and Results
257(1)
8.2.7.1 ANN with BPA
257(3)
8.2.7.2 Neuro-Fuzzy System
260(3)
8.2.7.3 Modular Neural Networks
263(1)
8.2.7.4 Wavelet Coefficients with ANN and BPA
264(4)
8.2.8 Concluding Remarks for the Speech Biometric
268(1)
8.3 Signature Classification
269(6)
8.3.1 Preprocessing
270(1)
8.3.2 Feature Extraction
271(1)
8.3.3 Artificial Neural Network
271(1)
8.3.4 Results
271(2)
8.3.5 Concluding Remarks for the Signature Biometric
273(2)
Chapter 9 Fusion Methods in Biometrics
275(16)
9.1 Introduction
275(3)
9.1.1 Problems with Unimodal Systems
275(1)
9.1.2 Motivation for Fusion Methods
275(1)
9.1.3 Workings of Fusion Methods
276(1)
9.1.4 What Can Be Fused?
276(1)
9.1.5 Unimodal or Bimodal?
277(1)
9.1.6 Note for Functional Prediction Problems
278(1)
9.2 Fusion of Face and Speech
278(3)
9.2.1 Working
279(1)
9.2.2 Results
280(1)
9.2.3 Concluding Remarks for the Fusion of Face and Speech
280(1)
9.3 Fusion of Face and Ear
281(5)
9.3.1 Haar Transform
282(1)
9.3.2 Feature Extraction
283(1)
9.3.2.1 Face
284(1)
9.3.2.2 Ear Feature Extraction
284(1)
9.3.3 Classification
285(1)
9.3.4 Results
285(1)
9.3.5 Concluding Remarks for the Fusion of Face and Ear
286(1)
9.4 Recognition with Modular ANN
286(5)
9.4.1 Problem of High Dimensionality
286(1)
9.4.2 Modular Neural Networks
287(1)
9.4.3 Modules
288(1)
9.4.4 Artificial neural Networks
288(1)
9.4.5 Integrator
289(1)
9.4.6 Results
289(1)
9.4.7 Concluding Remarks for Modular neural network Approach
290(1)
Chapter 10 Bioinformatics
291(18)
10.1 About Protein
291(1)
10.2 Protein Structure
291(4)
10.2.1 Four Distinct Aspects of a Protein's Structure
293(1)
10.2.2 Protein Folding
293(1)
10.2.3 Protein Secondary Structure Theory
293(1)
10.2.4 Characteristics of Alpha Helices
294(1)
10.2.5 Characteristics of Beta Sheets
294(1)
10.2.6 Characteristics of Loops
294(1)
10.3 Problem of Protein Structure Determination
295(6)
10.3.1 Application of Artificial Neural Networks
296(2)
10.3.2 System Analysis
298(1)
10.3.3 Approach
298(1)
10.3.4 Encoding Scheme
299(2)
10.3.5 Architecture of the Artificial Neural Network
301(1)
10.4 Procedure
301(5)
10.4.1 Data Source and Description
302(1)
10.4.2 Formation of Inputs and Outputs
303(1)
10.4.3 Training
304(1)
10.4.4 Testing
305(1)
10.5 Results
306(1)
10.6 Conclusions
307(2)
Chapter 11 Biomedical Systems-I
309(38)
11.1 Introduction
309(3)
11.1.1 Need and Issues
310(1)
11.1.2 Machine Learning Perspective
310(1)
11.1.3 Diseases
311(1)
11.1.4 Methodology
312(1)
11.2 ANN Classifiers
312(3)
11.2.1 ANN with BPA
313(1)
11.2.2 Radial Basis Function Networks
314(1)
11.2.3 Learning Vector Quantization
314(1)
11.2.4 Data Sets
315(1)
11.3 Breast Cancer
315(6)
11.3.1 Data Set of Breast Cancer
316(1)
11.3.2 Results
316(1)
11.3.2.1 ANN with BPA
316(1)
11.3.2.2 Radial Basis Function Networks (RBFN)
317(1)
11.3.2.3 LVQ Network
318(1)
11.3.2.4 Performance Comparison
319(2)
11.4 Epilepsy
321(5)
11.4.1 Data Set for Epilepsy
321(1)
11.4.2 Results
321(1)
11.4.2.1 ANN with BPA
321(2)
11.4.2.2 RBFN
323(1)
11.4.2.3 LVQ Network
324(1)
11.4.2.4 Performance Comparison
324(2)
11.5 Thyroid
326(5)
11.5.1 Data Set for Thyroid Disorders
326(1)
11.5.2 Results
326(1)
11.5.2.1 ANN with BPA
326(2)
11.5.2.2 RBFN
328(1)
11.5.2.3 LVQ Network
328(1)
11.5.2.4 Performance Comparison
329(2)
11.6 Skin Diseases
331(3)
11.6.1 Data set for Skin Diseases
331(1)
11.6.2 Results
331(1)
11.6.2.1 ANN with BPA
331(1)
11.6.2.2 RBFN
332(1)
11.6.2.3 Diagnosis Using LVQ Network
333(1)
11.6.2.4 Performance Comparison
333(1)
11.7 Diabetes
334(4)
11.7.1 Data Set for Diabetes
336(1)
11.7.2 Results
336(1)
11.7.2.1 ANN with BPA
336(1)
11.7.2.2 RBFN
336(1)
11.7.2.3 LVQ Network
337(1)
11.7.2.4 Performance Comparison
338(1)
11.8 Heart Disease
338(5)
11.8.1 Data Set for Heart Diseases
341(1)
11.8.2 Results
341(1)
11.8.2.1 ANN with BPA
341(1)
11.8.2.2 RBFN
341(1)
11.8.2.3 LVQ Network
342(1)
11.8.2.4 Performance Comparison
343(1)
11.9 Cumulative Results
343(1)
11.10 Conclusions
344(3)
Chapter 12 Biomedical Systems-II
347(28)
12.1 Introduction
347(1)
12.2 Hybrid Systems as Classifiers
348(6)
12.2.1 ANFIS
349(2)
12.2.2 Ensemble
351(1)
12.2.3 Evolutionary ANN
352(2)
12.3 Fetal Delivery
354(4)
12.3.1 Description of Data Set
355(1)
12.3.2 ANN with BPA
355(1)
12.3.3 RBFN
355(1)
12.3.4 LVQ Networks
355(1)
12.3.5 ANFIS
356(1)
12.3.6 Comparison of Results
357(1)
12.4 Pima Indian Diabetes
358(4)
12.4.1 Data Set Description
358(1)
12.4.2 ANN with BPA
359(1)
12.4.3 Ensemble
359(1)
12.4.4 ANFIS
359(1)
12.4.5 Evolutionary ANN
360(1)
12.4.6 Concluding Remarks for Pima Indian Diabetes
361(1)
12.5 Fetal Heart Sound De-Noising Techniques
362(13)
12.5.1 Signal Detection and Recording
363(1)
12.5.2 Signal De-noising
363(1)
12.5.2.1 Band-Pass Filtering Method
364(1)
12.5.2.2 Signal Difference Method
364(1)
12.5.2.3 Blind Separation of Source Method
364(1)
12.5.2.4 Adaptive Noise Cancellation Method
364(1)
12.5.3 Adaptive Noise Cancellation
364(2)
12.5.4 System Simulation
366(1)
12.5.5 Results
367(3)
12.5.6 Concluding Remarks for Fetal Heart Sound De-Noising Techniques
370(5)
SECTION III Soft Computing in Other Application Areas
Chapter 13 Legal Threat Assessment
375(30)
13.1 Introduction
375(4)
13.1.1 Threat, Judiciary, and Justice
375(1)
13.1.2 Role of Time in Threat
376(1)
13.1.3 Key Outcomes
377(1)
13.1.4 Motivation
377(1)
13.1.5 Literature Review
378(1)
13.1.6 Approach and Objectives
378(1)
13.2 Expert System
379(11)
13.2.1 Expert System Architecture
379(1)
13.2.2 Threat Capture System
380(1)
13.2.3 Input Modeling
381(1)
13.2.3.1 Input Quantization
382(1)
13.2.4 Source Input
382(1)
13.2.4.1 Source Type
382(1)
13.2.4.2 Past Experience
383(1)
13.2.4.3 Desperation Rating
383(1)
13.2.4.4 Financial Capability
383(1)
13.2.4.5 Social Capability
383(1)
13.2.5 Target Input
383(1)
13.2.5.1 Target Type
383(1)
13.2.5.2 Target Past Exprience
383(1)
13.2.6 Vulnerability Input
383(1)
13.2.6.1 Threat Type
384(1)
13.2.6.2 Content Type
384(1)
13.2.6.3 Court Type
384(1)
13.2.6.4 Publication Media
385(1)
13.2.7 Fuzzification of Input
385(5)
13.3 Fuzzy Inference System
390(3)
13.3.1 Source System
390(1)
13.3.2 Target System
391(1)
13.3.3 Vulnerability System
392(1)
13.3.4 Threat Management System
392(1)
13.4 Analysis of Rules and Inference Engine
393(5)
13.4.1 Source System
393(2)
13.4.2 Target System
395(1)
13.4.3 Vulnerability System
395(2)
13.4.4 Threat Management System
397(1)
13.5 Evaluation of the Expert System
398(5)
13.5.1 Aim of Testing
398(1)
13.5.2 Performance Benchmark
398(1)
13.5.2.1 Validity
399(1)
13.5.2.2 Correctness
399(1)
13.5.2.3 Effectiveness
399(1)
13.5.2.4 Competence
399(1)
13.5.2 Test Pack
399(2)
13.5.4 Performance of the Expert System
401(1)
13.5.5 Results
401(1)
13.5.5.1 Correctness
401(1)
13.5.5.2 Validity
401(1)
13.5.5.3 Effectiveness
401(1)
13.5.5.4 Competence
401(2)
13.6 Conclusions
403(2)
13.6.1 Implication of the Results
403(1)
13.6.2 Key Outcomes
403(1)
13.6.3 Future Work
403(2)
Chapter 14 Robotic Path Planning and Navigation Control
405(30)
14.1 Introduction
405(2)
14.2 Robotics and Simulation Model
407(4)
14.2.1 Robotic Hardware
407(1)
14.2.2 Robotic Sensors
408(1)
14.2.3 Robotic Map
408(1)
14.2.4 Path Planning and Control
408(1)
14.2.5 AI Robotics and Applications
409(1)
14.2.6 General Assumptions
409(2)
14.3 Genetic Algorithm
411(6)
14.3.1 Representation
411(1)
14.3.2 Evaluations of Fitness
412(1)
14.3.3 Initial Solutions
413(1)
14.3.3.1 Find a Straight Path Solution Between Source and Destination
413(1)
14.3.3.2 Find Random Left Solution Between Source and Destination
414(1)
14.3.3.3 Find Random Right Solution Between Source and Destination
414(1)
14.3.3.4 Find Full Solutions
414(1)
14.3.4 Crossover
415(1)
14.3.5 Mutation
416(1)
14.4 Artificial Neural Network with Back Propagation Algorithm
417(2)
14.4.1 Inputs
417(1)
14.4.2 Explanation of the Outputs
418(1)
14.3.3 Special Constraints Put in the Algorithm
418(1)
14.4.4 Procedure
418(1)
14.5 A Algorithm
419(1)
14.6 Comparisons
420(1)
14.7 Robotic Controller
421(3)
14.7.1 Inputs and Outputs
421(1)
14.7.2 Rules
422(2)
14.8 Results
424(6)
14.8.1 Genetic Algorithm
425(1)
14.8.2 Artificial Neural Networks
425(1)
14.8.3 A Algorithm
425(3)
14.8.4 Robotic Controller
428(2)
14.9 Conclusions
430(5)
Chapter 15 Character Recognition
435(30)
15.1 Introduction
435(2)
15.2 General Algorithm Architecture for Character Recognition
437(5)
15.2.1 Binarization
438(1)
15.2.2 Preprocessing
438(1)
15.2.2.1 Filters
438(1)
15.2.2.2 Smoothing
438(1)
15.2.2.3 Skew Detection and Correction
439(1)
15.2.2.4 Slant Correction
439(1)
15.2.2.5 Character Normalization
439(2)
15.2.2.6 Thinning
441(1)
15.2.3 Segmentation
441(1)
15.3 Multilingual OCR by Rule-Based Approach and ANN
442(3)
15.4 Rule-Based Approach
445(5)
15.4.1 Classification
445(1)
15.4.2 Tests
446(2)
15.4.2.1 Class C Test
448(1)
15.4.2.2 Class A-3 Test
448(51)
15.4.2.3 Class A-6 Test
499(1)
15.4.2.4 Class B-1 Test
449(1)
15.4.2.5 Class A-4 Test
449(1)
15.4.2.6 Class A-1 Test
449(1)
15.4.2.7 Class A-5 Test
449(1)
15.4.3 Rules
449(1)
15.5 Artificial Neural Network
450(1)
15.5.1 Inputs
450(1)
15.5.2 Outputs
450(1)
15.5.3 Identification
451(1)
15.6 Results of Multilingual OCR
451(1)
15.7 Algorithm for Handwriting Recognition Using GA
451(10)
15.7.1 Generation of Graph
452(1)
15.7.2 Fitness Function of GA
453(1)
15.7.2.1 Deviation Between Two Edges
453(3)
15.7.2.2 Deviation of a Graph
456(1)
15.7.3 Crossover
457(1)
15.7.3.1 Matching of Points
458(1)
15.7.3.2 Generate Adjacency Matrix
459(1)
15.7.3.3 Find Paths
459(1)
15.7.3.4 Removing and Adding Edges
460(1)
15.7.3.5 Generation of Graph
460(1)
15.8 Results of Handwriting Recognition
461(3)
15.8.1 Effect of Genetic Algorithms
461(1)
15.8.1.1 Distance Optimization
461(1)
15.8.1.2 Style Optimization
462(2)
15.9 Conclusions
464(1)
Chapter 16 Picture Learning
465(22)
16.1 Introduction
465(1)
16.2 Picture Learning
466(4)
16.2.1 Coding Techniques
467(2)
16.2.2 JPEG Compression
469(1)
16.2.3 Soft-Computing Approaches
470(1)
16.3 Hybrid Classifier Based on Neuro-Fuzzy System
470(6)
16.3.1 Clustering
471(1)
16.3.2 Fuzzy Logic
472(1)
16.3.3 Network Training
473(3)
16.3.4 Genetic Algorithms
476(1)
16.4 Picture Learning Using the Algorithm
476(2)
16.5 Instantaneously Learning Neural Network
478(7)
16.5.1 CC4 Algorithm
479(1)
16.5.1.1 Corners Algorithm
480(1)
16.5.1.2 Learning
480(1)
16.5.2 Input Encoding
481(1)
16.5.3 Modifications for Complex Inputs
482(1)
16.5.4 Restrictions on Inputs
483(1)
16.5.5 ACC Algorithm
484(1)
16.6 Picture Learning
485(1)
16.7 Conclusions
485(2)
Chapter 17 Other Real Life Applications
487(20)
17.1 Introduction
487(1)
17.2 Automatic Document Classification
487(6)
17.2.1 About the Problem
488(1)
17.2.1.1 Information Access and Retrieval
488(1)
17.2.1.2 Document Classification
488(1)
17.2.1.3 Automatic Document Classification
489(1)
17.2.2 Architecture of a Classifier
489(1)
17.2.2.1 Preprocessing
489(1)
17.2.2.2 Learning
490(1)
17.2.2.3 Outputs
490(1)
17.2.3 Naive Bayes Model
490(1)
17.2.3.1 Bayes' Theorem
490(1)
17.2.3.2 Classification Algorithm
490(1)
17.2.3.3 Implementation Procedure
491(1)
17.2.4 Artificial Neural Network Model
491(1)
17.2.4.1 Concept Extraction and Classification
492(1)
17.2.5 Experiments and Results
492(1)
17.3 Negative Association Rule Mining
493(4)
17.3.1 Association Rules
494(1)
17.3.1.1 Formal Definition of Negative Association Rule
495(1)
17.3.2 Application of Genetic Algorithms
495(1)
17.3.2.1 Individual Representation
495(1)
17.3.2.2 Genetic Operators
496(1)
17.3.2.3 Fitness Function
496(1)
17.4 Genre Classification Using Modular Artificial Neural Networks
497(4)
17.4.1 Genre Identification
498(1)
17.4.1.1 Feature Extraction
499(1)
17.4.1.2 Aggregation
499(1)
17.4.1.3 Classification
499(1)
17.4.2 Extracted Features
500(1)
17.4.3 Classifier
500(1)
17.5 Credit Ratings
501(2)
17.5.1 Credit Rating
501(1)
17.5.2 Methodology
502(1)
17.5.2.1 Inputs
502(1)
17.5.2.2 Evolutionary ANN
502(1)
17.6 Conclusions
503(4)
SECTION IV Soft Computing Implementation Issues
Chapter 18 Parallel Implementation of Artificial Neural Networks
507(16)
18.1 Introduction
507(1)
18.2 Back Propagation Algorithm
508(1)
18.3 Data Set Partitioning
509(2)
18.4 Layer Partitioning
511(2)
18.5 Node Partitioning
513(1)
18.6 Hierarchical Partitioning
514(5)
18.6.1 Self-Adaptive Approach
515(2)
18.6.2 Connections
517(1)
18.6.3 Working
518(1)
18.7 Results
519(3)
18.8 Conclusions
522(1)
Chapter 19 A Guide to Problem Solving Using Soft Computing
523(48)
19.1 Introduction
523(2)
19.2 ANN with BPA
525(21)
19.2.1 Number of Hidden Layers
525(1)
19.2.2 Number of Neurons
526(1)
19.2.3 Learning Rate
526(5)
19.2.4 Variable Learning Rate
531(1)
19.2.5 Momentum
531(3)
19.2.6 Training Time, Epochs, and Overlearning
534(2)
19.2.7 Validation Data and Early Stopping
536(1)
19.2.8 Goal
536(1)
19.2.9 Input Distribution
536(1)
19.2.10 Randomness
537(1)
19.2.11 Generalization
537(1)
19.2.12 Global and Local Optima
538(1)
19.2.13 Noise
539(1)
19.2.14 Classificatory Inputs
540(3)
19.2.15 Not All ANNs Get Trained
543(1)
19.2.16 ANN with BPA as Classifier
544(1)
19.2.17 ANN with BPA as Functional Predictor
545(1)
19.3 Other ANN Models
546(3)
19.3.1 Radial Basis Function Networks
546(1)
19.3.1.1 RBFNs as Classifiers
546(1)
19.3.1.2 RBFNs as Functional Predictors
547(1)
19.3.1.3 Role of Radius of RBFNs in Generalization
547(1)
19.3.2 Self-Organizing Maps
548(1)
19.3.3 Learning Vector Quantization
549(1)
19.4 Fuzzy Inference Systems
549(7)
19.4.1 Number of Rules
550(1)
19.4.2 Number of Membership Functions
551(1)
19.4.3 Weights of Rules
551(1)
19.4.4 Input/Output Distribution Between MFs
552(1)
19.4.5 Shape of the MFs
553(2)
19.4.6 Manual Modify and Test
555(1)
19.4.7 Generalization
555(1)
19.4.8 Can FIS Solve Every Problem?
556(1)
19.5 Evolutionary Algorithms
556(6)
19.5.1 Crossover Rate
557(1)
19.5.2 Mutation Rate
557(3)
19.5.3 Individual Representation
560(1)
19.5.4 Infeasible Solutions
561(1)
19.5.5 Local and Global Minima
561(1)
19.5.6 Optimization Time
562(1)
19.6 Hybrid Algorithms
562(9)
19.6.1 ANFIS
563(1)
19.6.2 Ensemble
564(1)
19.6.3 Evolutionary ANN
565(6)
APPENDICES
Appendix A Matlab® GUIs for Soft Computing
571(14)
A.1 Introduction
571(1)
A.2 Artificial Neural Networks
571(7)
A.3 Fuzzy Inference System
578(3)
A.4 Genetic Algorithms
581(2)
A.5 Adaptive Neuro-Fuzzy Inference Systems
583(2)
Appendix B Matlab® Source Codes for Soft Computing
585(8)
B.1 Introduction
585(1)
B.2 Artificial Neural Network
585(1)
B.2.1 ANN with BPA
586(1)
B.2.2 Radial Basis Function Network
587(1)
B.2.3 Learning Vector Quantization
587(1)
B.2.4 Self-Organizing Map
587(1)
B.2.5 Recurrent Neural Network
588(3)
B.3 Fuzzy Inference Systems
591(1)
B.4 Genetic Algorithm
591(2)
Appendix C Book Website
593(4)
REFERENCES
References 597(44)
Standard Data Sets Used 641(2)
Registered Trademarks 643(2)
Index 645
Dr. Anupam Shukla is an associate professor in the IT Department of the Indian Institute of Information Technology and Management Gwalior. He has 22 years of teaching experience. His research interest includes speech processing, artificial intelligence, soft computing and bioinformatics. He has published over 120 papers in various national and international journals/conferences. He is referee for 10 international journals including Elsevier, IEEE, and ACM computing and in the editorial board of International Journal of AI and Soft Computing. He also received Gold Medal from Jadavpur University during his postgraduate studies.





Dr. Ritu Tiwari is an assistant professor in the IT Department of Indian Institute of Information Technology and Management Gwalior. Her field of research includes biometrics, artificial neural networks, signal processing, robotics and soft computing. She has published around 50 papers in various national and international journals/conferences. She has received Young Scientist Award from Chhattisgarh Council of Science & Technology in the year 2006. She also received Gold Medal in her post graduation from NIT, Raipur.





Rahul Kala is a student at the Indian Institute of Information Technology and Management Gwalior. His areas of research are hybrid soft computing, robotic planning, biometrics, artificial intelligence, and soft computing. He has published over 25 papers in various international and national journals/conferences. He also takes a keen interest toward free/open source software. He secured All India 8th position in Graduates Aptitude Test in Engineeging-2008 with a percentile of 99.84. Rahul is the winner of Lord of the Code Scholarship Contest organized by KReSIT, IIT Bombay and Red Hat. He also secured seventh position in ACM-International Collegiate Programming Contest Kanpur Regional 2007.
Daugiau apie elektronines knygas Daugiau apie elektronines knygas
Pastovi nuoroda: https://www.kriso.lt/db/97814398228902e.html
Raktažodžiai: