Nature-inspired methods in chemometrics: genetic algorithms and artificial neural networks: genetic algorithms and artificial neural networks
Regular price
101.750 KD
inc. VAT
Couldn't load pickup availability
Table of contents
- Cover
- CONTENTSix
- PREFACEvii
- LIST OF CONTRIBUTORSxvii
- PART I: GENETIC ALGORITHMS1
- CHAPTER 1. Genetic Algorithms and Beyond3
- 1 Introduction3
- 2 Biological systems and the simple genetic algorithm (SGA)5
- 3 Why do GAs work?6
- 4 Creating a genetic algorithm7
- 5 Exploration versus exploitation28
- 6 Other population-based methods40
- 7 Conclusions48
- CHAPTER 2. Hybrid Genetic Algorithms55
- 1 Introduction55
- 2 The approach to hybridization55
- 3 Why hybridize?57
- 4 Detailed examples59
- 5 Conclusion66
- CHAPTER 3. Robust Soft Sensor Development Using Genetic Programming69
- 1 Introduction69
- 2 Soft sensors in industry71
- 3 Requirements for robust soft sensors76
- 4 Selected approaches for effective soft sensors development80
- 5 Genetic programming in soft sensors development90
- 6 Integrated methodology99
- 7 Soft sensor for emission estimation: a case study103
- 8 Conclusions105
- CHAPTER 4. Genetic Algorithms in Molecular Modelling: A Review109
- 1 Introduction109
- 2 Molecular modelling and genetic algorithms110
- 3 Small and medium-sized molecule conformational search114
- 4 Constrained conformational space searches119
- 5 The protein-ligand docking problem124
- 6 Protein structure prediction with genetic algorithms131
- 7 Conclusions134
- CHAPTER 5. Mobydigs: Software for Regression and Classification Models by Genetic Algorithms141
- 1 Introduction141
- 2 Population definition143
- 3 Tabu list143
- 4 Random variables144
- 5 Parent selection145
- 6 Crossover/mutation trade-off145
- 7 Selection pressure and crossover/mutation trade-off influence148
- 8 RQK fitness functions151
- 9 Evolution of the populations154
- 10 Model distance155
- 11 The software MobyDigs158
- CHAPTER 6. Genetic Algorithm-PLS as a Tool for Wavelength Selection in Spectral Data Sets169
- 1 Introduction169
- 2 The problem of variable selection170
- 3 GA applied to variable selection172
- 4 Evolution of the genetic algorithm176
- 5 Pretreatment and scaling181
- 6 Maximum number of variables182
- 7 Examples183
- 8 Conclusions194
- PART II: ARTIFICIAL NEURAL NETWORKS197
- CHAPTER 7. Basics of Artificial Neural Networks199
- 1 Introduction199
- 2 Basic concepts200
- 3 Error backpropagation ANNs204
- 4 Kohonen ANNs206
- 5 Counterpropagation ANNs213
- 6 Radial basis function (RBF) networks216
- 7 Learning by ANNs220
- 8 Applications223
- 9 Conclusions226
- CHAPTER 8. Artificial Neural Networks in Molecular StructuresŒProperty Studies231
- 1 Introduction231
- 2 Molecular descriptors231
- 3 Counter propagation neural network233
- 4 Application in toxicology and drug design237
- 5 Conclusions252
- CHAPTER 9. Neural Networks for the Calibration of Voltammetric Data257
- 1 Introduction257
- 2 Electroanalytical data257
- 3 Application of artificial neural networks to voltammetric data261
- 4 Genetic algorithms for optimisation of feed forward neural networks269
- 5 Conclusions278
- CHAPTER 10. Neural Networks and Genetic Algorithms Applications in Nuclear Magnetic Resonance (NMR)281
- 1 Introduction281
- 2 NMR spectroscopy283
- 3 Neural networks applications285
- 4 Genetic algorithms303
- 5 Biomedical NMR spectroscopy309
- 6 Conclusion315
- CHAPTER 11. A Qsar Model for Predicting the Acute Toxicity of Pesticides to Gammarids323
- 1 Introduction323
- 2 Materials and methods324
- 3 Results and discussion330
- 4 Conclusions338
- CONCLUSION341
- CHAPTER 12. Applying Genetic Algorithms and Neural Networks to Chemometric Problems343
- 1 Introduction343
- 2 Structure of the genetic algorithm345
- 3 Results for the genetic algorithms350
- 4 Structure of the neural network362
- 5 Results for the neural network365
- 6 Conclusions373
- INDEX377
In recent years Genetic Algorithms (GA) and Artificial Neural Networks (ANN) have progressively increased in importance amongst the techniques routinely used in chemometrics. This book contains contributions from experts in the field is divided in two sections (GA and ANN). In each part, tutorial chapters are included in which the theoretical bases of each technique are expertly (but simply) described. These are followed by application chapters in which special emphasis will be given to the advantages of the application of GA or ANN to that specific problem, compared to classical techniques, and to the risks connected with its misuse.
This book is of use to all those who are using or are interested in GA and ANN. Beginners can focus their attentions on the tutorials, whilst the most advanced readers will be more interested in looking at the applications of the techniques. It is also suitable as a reference book for students.
- Subject matter is steadily increasing in importance
- Comparison of Genetic Algorithms (GA) and Artificial Neural Networks (ANN) with the classical techniques
- Suitable for both beginners and advanced researchers
This book is of use to all those who are using or are interested in GA and ANN. Beginners can focus their attentions on the tutorials, whilst the most advanced readers will be more interested in looking at the applications of the techniques. It is also suitable as a reference book for students.
- Subject matter is steadily increasing in importance
- Comparison of Genetic Algorithms (GA) and Artificial Neural Networks (ANN) with the classical techniques
- Suitable for both beginners and advanced researchers