GMDH-methodology and implementation in C / editor, Godfrey Onwubolu.

Format:

Book

Contributor:

Onwubolu, Godfrey C., editor.

Language:

English

Subjects (All):

GMDH algorithms.

Self-organizing systems--Data processing.

Self-organizing systems.

C (Computer program language).

Physical Description:

xix, 283 pages : illustrations ; 24 cm + 1 CD-ROM (4 3/4 in.)

4 3/4 in.

Place of Publication:

Covent Garden, London : Imperial College Press, [2015]

System Details:

text file

Summary:

Accompanying CD-ROM contains ... "source codes in C Language for Chapters 2-7 and 9."--P. vii.

Contents:

1 Introduction / Godfrey C. Onwubolu Onwubolu, Godfrey C. 1

1.1 Historical Background of GMDH 2

1.2 Basic GMDH Algorithm 4

1.2.1 External criteria 4

1.3 GMDH-Type Neural Networks 6

1.4 Classification of GMDH Algorithms 6

1.4.1 Parametric GMDH algorithms 6

1.4.2 Non-parametric GMDH algorithms 15

1.5 Rationale for GMDH in C Language 25

1.6 Available Public Software 26

1.7 Recent Developments 26

1.8 Conclusions 26

References 27

2 GMDH Multilayered Iterative Algorithm (MIA) / Godfrey C. Onwubolu Onwubolu, Godfrey C. 29

2.1 Multilayered Iterative Algorithm (MIA) Networks 29

2.1.1 GMDH layers 30

2.1.2 GMDH nodes 30

2.1.3 GMDH connections 32

2.1.4 GMDH network 32

2.1.5 Regularized model selection 33

2.1.6 GMDH algorithm 34

2.2 Computer Code for GMDH-MIA 35

2.2.1 Compute a tree of quadratic polynomials 35

2.2.2 Evaluate the Ivakhnenko polynomial using the tree of polynomials generated 41

2.2.3 Compute the coefficients in the Ivakhnenko polynomial using the same tree of polynomials generated 50

2.2.4 Main program 51

2.3 Examples 54

2.3.1 Example 1 54

2.3.2 Example 2 61

2.4 Summary 60

References 70

3 GMDH Multilayered Algorithm Using Prior Information / Alexandr Kiryanov Kiryanov, Alexandr 71

3.1 Introduction 71

3.2 Criterion Correction Algorithm 72

3.3 C++ Implementation 74

3.3.1 Building sources 75

3.4 Example 76

3.5 Conclusion 80

References 80

4 Combinatorial (COMBI) Algorithm / Oleksiy Koshulko Koshulko, Oleksiy, Anatoliy Koshulko Koshulko, Anatoliy, Godfrey C. Onwubolu Onwubolu, Godfrey C. 81

4.1 The COMBI Algorithm 81

4.2 Usage of the "Structure of Functions" 82

4.3 Gradual Increase of Complexity 84

4.4 Implementation 85

4.5 Output Post-Processing 86

4.6 Output Interpretation 90

4.7 Predictive Model 90

4.8 Summary 91

References 92

5 GMDH Harmonic Algorithm / Godfrey C. Onwubolu Onwubolu, Godfrey C. 93

5.1 Introduction 93

5.2 Polynomial Harmonic Approximation 94

5.2.1 Polynomial, harmonic and hybrid terms 94

5.2.2 Hybrid function approximation 95

5.2.3 Need for hybrid modelling 95

5.3 GMDH Harmonic 96

5.3.1 Calculation of the non-multiple frequencies 97

5.3.2 Isolation of significant harmonics 98

5.3.3 Computing of the harmonics 98

Appendix A Derivation of the trigonometric equations 98

A.1 System of equations for the weighting coefficients 98

A.2 Algebraic equation for the frequencies 100

A.3 The normal trigonometric equation 100

References 105

6 GMDH-Based Modified Polynomial Neural Network Algorithm / Alexander Tyryshkin Tyryshkin, Alexander, Anatoliy Andrakhanov Andrakhanov, Anatoliy, Audrey Orlou Orlou, Audrey 107

6.1 Modified Polynomial Neural Network 107

6.2 Description of the Program of MPNN Calculation 115

6.2.1 The software framework (GMDH) 115

6.2.2 Object-oriented architecture of the software framework 116

6.2.3 Description of the program graphic interface 124

6.2.4 Description of the basic functions of the data processing interface 125

6.3 The GMDH PNN Application in Solving the Problem of an Autonomous Mobile Robot (AMR) Control 125

6.3.1 The review of GMDH applications in robotics 126

6.3.2 The application of MPNN for controlling the autonomous mobile robot 126

6.4 Application of MPNN for the Control of the Autonomous Cranberry Harvester 135

6.4.1 General project description 135

6.4.2 Formalization of the cranberry harvester control problem 136

6.4.3 Experiment results 140

6.5 Conclusion 151

References 151

7 GMDH-Clustering / Lyudmyla Saryeheva Saryeheva, Lyudmyla, Alexander Sarychev Sarychev, Alexander 157

7.1 Quality Criteria for GMDH-Clustering 157

7.14 Introduction 157

7.1.2 Problem statement 158

7.1.3 Measures of similarity 160

7.1.4 Selection of informative attributes and the search for the best, clusterization: common approach to the classification of methods 163

7.1.5 Criteria, for the evaluation of clusterization quality 167

7.1.6 Objective clusterization 171

7.2 Computer Code for GMDH-Clustering Quality Criteria 174

7.3 Examples 195

7.3.1 Example 1 195

7.3.2 Example 2 195

7.4 Conclusion 201

References 201

8 Multiagent Clustering Algorithm / Oleksii Oliinyk Oliinyk, Oleksii, Sergey Subbotin Subbotin, Sergey, Andrii Oliinyk Oliinyk, Andrii 205

8.1 Introduction 205

8.2 Honey Bee Swarm 205

8.3 Clustering based on the Multiagent Approach 206

8.4 Computer Code for Multiagent Clustering 208

8.4.1 Moving of agents 209

8.4.2 Natural selection 213

8.4.3 Evaluation of the conditions for objects in different cells 214

8.4.4 Main program: beeClustering 216

8.5 Examples 219

8.5.1 Example 1: Synthetic data 220

8.5.2 Example 2: Real-world problem 223

8.6 Conclusion 225

References 226

9 Analogue Completing Algorithm / Dmytro Zubov Zubov, Dmytro 227

9.1 General Introduction to Analogue Usage in Task Solutions 227

9.2 Analogue Complexing 228

9.2.1 First case: The analogue complexing GMDH algorithm 229

9.2.2 Second case: Method of long-range prognosis for the air temperature over a period of ten days using robust inductive models and analogue principle (example) 234

9.3 Summary 264

References 265

10 GMDH-Type Neural Network and Genetic Algorithm / Saeed Fallahi Fallahi, Saeed, Meysam Shaverdi Shaverdi, Meysam, Vahab Bashiri Bashiri, Vahab 267

10.1 Introduction 267

10.2 Background of the GMDH-type Neural Network and Genetic Algorithm 267

10.3 Description of the Genome Representation of the GMDH-GA Procedure 269

10.4 GMDH-GA for Modeling the Tool wear Problem 271

10.5 Stock Price Prediction Using the GMDH-type Neural Network 274

10.6 Summary 279

References 280.

Notes:

Includes bibliographical references and index.

ISBN:

9781848166103

1848166109

OCLC:

607976448