Bayesian Networks - A Practial Guide toApplications
Buy Rights Online Buy Rights

Rights Contact Login For More Details

More About This Title Bayesian Networks - A Practial Guide toApplications

English

Bayesian Networks, the result of the convergence of artificial intelligence with statistics, are growing in popularity. Their versatility and modelling power is now employed across a variety of fields for the purposes of analysis, simulation, prediction and diagnosis.

This book provides a general introduction to Bayesian networks, defining and illustrating the basic concepts with pedagogical examples and twenty real-life case studies drawn from a range of fields including medicine, computing, natural sciences and engineering.

Designed to help analysts, engineers, scientists and professionals taking part in complex decision processes to successfully implement Bayesian networks, this book equips readers with proven methods to generate, calibrate, evaluate and validate Bayesian networks.

The book:

  • Provides the tools to overcome common practical challenges such as the treatment of missing input data, interaction with experts and decision makers, determination of the optimal granularity and size of the model. 
  • Highlights the strengths of Bayesian networks whilst also presenting a discussion of their limitations.
  • Compares Bayesian networks with other modelling techniques such as neural networks, fuzzy logic and fault trees.
  • Describes, for ease of comparison, the main features of the major Bayesian network software packages: Netica, Hugin, Elvira and Discoverer, from the point of view of the user.
  • Offers a historical perspective on the subject and analyses future directions for research.

Written by leading experts with practical experience of applying Bayesian networks in finance, banking, medicine, robotics, civil engineering, geology, geography, genetics, forensic science, ecology, and industry, the book has much to offer both practitioners and researchers involved in statistical analysis or modelling in any of these fields.

English

Editors

OLIVIER POURRET, Electricité de France

PATRICK NAÏM, ELSEWARE, France

BRUCE MARCOT, USDA Forest Service, Oregon, USA

English

Foreword ix

Preface xi

1 Introduction to Bayesian networks 1

1.1 Models 1

1.2 Probabilistic vs. deterministic models 5

1.3 Unconditional and conditional independence 9

1.4 Bayesian networks 11

2 Medical diagnosis 15

2.1 Bayesian networks in medicine 15

2.2 Context and history 17

2.3 Model construction 19

2.4 Inference 26

2.5 Model validation 28

2.6 Model use 30

2.7 Comparison to other approaches 31

2.8 Conclusions and perspectives 32

3 Clinical decision support 33

3.1 Introduction 33

3.2 Models and methodology 34

3.3 The Busselton network 35

3.4 The PROCAM network 40

3.5 The PROCAM Busselton network 44

3.6 Evaluation 46

3.7 The clinical support tool: TakeHeartII 47

3.8 Conclusion 51

4 Complex genetic models 53

4.1 Introduction 53

4.2 Historical perspectives 54

4.3 Complex traits 56

4.4 Bayesian networks to dissect complex traits 59

4.5 Applications 64

4.6 Future challenges 71

5 Crime risk factors analysis 73

5.1 Introduction 73

5.2 Analysis of the factors affecting crime risk 74

5.3 Expert probabilities elicitation 75

5.4 Data preprocessing 76

5.5 A Bayesian network model 78

5.6 Results 80

5.7 Accuracy assessment 83

5.8 Conclusions 84

6 Spatial dynamics in France 87

6.1 Introduction 87

6.2 An indicator-based analysis 89

6.3 The Bayesian network model 97

6.4 Conclusions 109

7 Inference problems in forensic science 113

7.1 Introduction 113

7.2 Building Bayesian networks for inference 116

7.3 Applications of Bayesian networks in forensic science 120

7.4 Conclusions 126

8 Conservation of marbled murrelets in British Columbia 127

8.1 Context/history 127

8.2 Model construction 129

8.3 Model calibration, validation and use 136

8.4 Conclusions/perspectives 147

9 Classifiers for modeling of mineral potential 149

9.1 Mineral potential mapping 149

9.2 Classifiers for mineral potential mapping 151

9.3 Bayesian network mapping of base metal deposit 157

9.4 Discussion 166

9.5 Conclusions 171

10 Student modeling 173

10.1 Introduction 173

10.2 Probabilistic relational models 175

10.3 Probabilistic relational student model 176

10.4 Case study 180

10.5 Experimental evaluation 182

10.6 Conclusions and future directions 185

11 Sensor validation 187

11.1 Introduction 187

11.2 The problem of sensor validation 188

11.3 Sensor validation algorithm 191

11.4 Gas turbines 197

11.5 Models learned and experimentation 198

11.6 Discussion and conclusion 202

12 An information retrieval system 203

12.1 Introduction 203

12.2 Overview 205

12.3 Bayesian networks and information retrieval 206

12.4 Theoretical foundations 207

12.5 Building the information retrieval system 215

12.6 Conclusion 223

13 Reliability analysis of systems 225

13.1 Introduction 225

13.2 Dynamic fault trees 227

13.3 Dynamic Bayesian networks 228

13.4 A case study: The Hypothetical Sprinkler System 230

13.5 Conclusions 237

14 Terrorism risk management 239

14.1 Introduction 240

14.2 The Risk Influence Network 250

14.3 Software implementation 254

14.4 Site Profiler deployment 259

14.5 Conclusion 261

15 Credit-rating of companies 263

15.1 Introduction 263

15.2 Naive Bayesian classifiers 264

15.3 Example of actual credit-ratings systems 264

15.4 Credit-rating data of Japanese companies 266

15.5 Numerical experiments 267

15.6 Performance comparison of classifiers 273

15.7 Conclusion 276

16 Classification of Chilean wines 279

16.1 Introduction 279

16.2 Experimental setup 281

16.3 Feature extraction methods 285

16.4 Classification results 288

16.5 Conclusions 298

17 Pavement and bridge management 301

17.1 Introduction 301

17.2 Pavement management decisions 302

17.3 Bridge management 307

17.4 Bridge approach embankment – case study 308

17.5 Conclusion 312

18 Complex industrial process operation 313

18.1 Introduction 313

18.2 A methodology for Root Cause Analysis 314

18.3 Pulp and paper application 321

18.4 The ABB Industrial IT platform 325

18.5 Conclusion 326

19 Probability of default for large corporates 329

19.1 Introduction 329

19.2 Model construction 332

19.3 BayesCredit 335

19.4 Model benchmarking 341

19.5 Benefits from technology and software 342

19.6 Conclusion 343

20 Risk management in robotics 345

20.1 Introduction 345

20.2 DeepC 346

20.3 The ADVOCATE II architecture 352

20.4 Model development 354

20.5 Model usage and examples 360

20.6 Benefits from using probabilistic graphical models 361

20.7 Conclusion 362

21 Enhancing Human Cognition 365

21.1 Introduction 365

21.2 Human foreknowledge in everyday settings 366

21.3 Machine foreknowledge 369

21.4 Current application and future research needs 373

21.5 Conclusion 375

22 Conclusion 377

22.1 An artificial intelligence perspective 377

22.2 A rational approach of knowledge 379

22.3 Future challenges 384

Bibliography 385

Index 427

loading