Neural Networks and Artificial Intelligence for Biomedical Engineering

, by Hudson, Donna L.; Cohen, Maurice E.

Note: Supplemental materials are not guaranteed with Rental or Used book purchases.

ISBN: 9780780334045 | 0780334043
Cover: Hardcover
Copyright: 10/8/1999

Buy New

Print on Demand: 2-4 Weeks. This item cannot be cancelled or returned.

$247.86

"Using examples drawn from biomedicine and biomedical engineering, this essential reference book brings you comprehensive coverage of all the major techniques currently available to build computer-assisted decision support systems. You will find practical solutions for biomedicine based on current theory and applications of neural networks, artificial intelligence, and other methods for the development of decision aids, including hybrid systems. NEURAL NETWORKS AND ARTIFICIAL INTELLIGENCE FOR BIOMEDICAL ENGINEERING offers students and scientists of biomedical engineering, biomedical informatics, and medical artificial intelligence a deeper understanding of the powerful techniques now in use with a wide range of biomedical applications. Highlighted topics include:Types of neural networks and neural network algorithmsKnowledge representation, knowledge acquisition, and reasoning methodologiesChaotic analysis of biomedical time series Genetic algorithms Probability-based systems and fuzzy systemsEvaluation and validation of decision support aids. For more information on the IEEE Press Series in Biomedical Engineering edited by Metin Akay, go to " Sponsored by: IEEE Engineering in Medicine and Biology Society.

PREFACE

xxi

(2)

ACKNOWLEDGMENTS

xxiii

Overview

(12)

0.1 Early Biomedical Systems

(2)

0.1.1 History

(1)

0.1.2 Medical Records

(1)

0.1.3 Drawbacks of Traditional Approaches

(1)

0.1.4 Numerical versus Symbolic Approaches

(1)

0.2 Medical and Biological Data

(5)

0.2.1 Binary Data

(1)

0.2.2 Categorical data

(1)

0.2.3 Integer Data

(1)

0.2.4 Continuous Data

(1)

0.2.5 Fuzzy Data

(1)

0.2.6 Temporal Data

(1)

0.2.7 Time Series Data

(2)

0.2.8 Image Data

(1)

0.3 Organization of the Book

(1)

References

(4)

PART I NEURAL NETWORKS

(118)

CHAPTER 1 Foundations of Neural Networks

(16)

1.1 Objectives of Neural Networks

(1)

1.1.1 Modeling Biomedical Systems

(1)

1.1.2 Establishment of Decision-Making Systems

(1)

1.2 Biological Foundations of Neural Networks

(2)

1.2.1 Structure of the Neuron

(2)

1.2.2 Structure of the Central Nervous System

(1)

1.3 Early Neural Models

(3)

1.3.1 McCulloch and Pitts Neuron

(1)

1.3.2 Hebbian Learning

(1)

1.3.3 ADALINE

(1)

1.3.4 Rosenblatt Perceptron

(1)

1.3.5 Problems with Early Systems

(1)

1.4 Precursor to Current Models: Pattern Classification

(5)

1.4.1 Feature Extraction

(2)

1.4.2 Supervised Learning

(1)

1.4.3 Unsupervised Learning

(1)

1.4.4 Learning Algorithms

(2)

1.5 Resurgence of the Neural Network Approach

(1)

1.6 Basic Concepts

(1)

1.6.1 Artificial Neurons

(1)

1.6.2 Selection of Input Nodes

(1)

1.6.3 Network Structure

(1)

1.6.3.1 Feed-Forward Networks

(1)

1.6.3.2 Feed-Backward Networks

(1)

1.6.4 Learning Mechanism

(1)

1.6.5 Output

(1)

1.7 Summary

(1)

References

(2)

CHAPTER 2 Classes of Neural Networks

(16)

2.1 Basic Network Properties

(3)

2.1.1 Terminology

(1)

2.1.2 Structure of Networks

(1)

2.1.3 Computational Properties of Nodes

(1)

2.1.4 Algorithm Design

(1)

2.2 Classification Models

(1)

2.3 Association Models

(6)

2.3.1 Hopfield Nets

(1)

2.3.1.1 Theoretical Basis

(1)

2.3.2 Other Associative Memory Approaches

(1)

2.3.2.1 Theoretical Basis of Bidirectional Associative Memory (BAM)

(2)

2.3.3 Hamming Net

(1)

2.3.3.1 Theoretical Basis

(1)

2.3.4 Applications of Association Models

(1)

2.4 Optimization Models

(2)

2.4.1 Hopfield Net

(1)

2.4.2 Boltzmann Machines

(1)

2.4.2.1 Theoretical Basis

(1)

2.4.3 Applications of Optimization Models

(1)

2.5 Self-Organization Models

(1)

2.6 Radial Basis Functions (RBFs)

(2)

2.6.1 Theoretical Basis

(1)

2.6.2 Applications of Radial Basis Functions

(1)

2.7 Summary

(1)

References

(2)

CHAPTER 3 Classification Networks and Learning

(14)

3.1 Network Structure

(1)

3.1.1 Layer Definition

(1)

3.1.2 Input Layer

(1)

3.1.3 Hidden Layer

(1)

3.1.4 Output Layer

(1)

3.2 Feature Selection

(5)

3.2.1 Types of Variables

(1)

3.2.2 Feature Vectors

(1)

3.2.3 Image Data

(1)

3.2.4 Time Series Data

(1)

3.2.4.1 Chaotic Analysis of Time Series

(1)

3.2.4.2 Graphical Measures of Chaos

(1)

3.2.4.3 Numerical Measures of Chaos

(1)

3.2.5 Issues of Dimensionality

(1)

3.3 Types of Learning

(4)

3.3.1 Supervised Learning

(1)

3.3.1.1 Selection of Training and Test Sets

(1)

3.3.1.2 Selection of Learning Algorithm

(1)

3.3.2 Unsupervised Learning

(3)

3.3.3 Causal Models

(1)

3.4 Interpretation of Output

(1)

3.5 Summary

(1)

References

(3)

CHAPTER 4 Supervised Learning

(20)

4.1 Decision Surfaces

(1)

4.2 Two-Category Separation, Linearly Separable Sets

(4)

4.2.1 Fisher's Linear Discriminant

(1)

4.2.2 Gradient Descent Procedures

(1)

4.2.3 Perceptron Algorithm

(1)

4.2.4 Relaxation Procedures

(1)

4.2.5 Potential Functions

(1)

4.3 Nonlinearly Separable Sets

(2)

4.3.1 Nonlinear Discriminant Functions

(1)

4.3.2 Hypernet, A Nonlinear Potential Function Algorithm

(1)

4.3.3 Categorization of Nonlinearly Separable Sets

(1)

4.3.3.1 Minimum Squared Error Procedures (MSEs)

(1)

4.3.3.2 Ho-Kashyap Procedure

(1)

4.4 Multiple Category Classification Problems

(3)

4.4.1 Extension of Fisher Discriminant

(1)

4.4.2 Kesler Construction

(1)

4.4.3 Backpropagation

(1)

4.5 Relationship to Neural Network Models

(1)

4.6 Comparison of Methods

(1)

4.6.1 Convergence and Stability

(1)

4.6.2 Training Time

(1)

4.6.3 Predictive Power

(1)

4.7 Applications

(3)

4.7.1 Single-Category Classification

(1)

4.7.2 Multicategory Classification

(2)

4.7.3 Reduction of Nodes

(1)

4.8 Summary

(2)

References

(3)

CHAPTER 5 Unsupervised Learning

(16)

5.1 Background

(1)

5.2 Clustering

(4)

5.2.1 Basic Isodata

(1)

5.2.2 Similarity Measures

(1)

5.2.3 Criterion Functions

(1)

5.2.3.1 Sum of Squared Error Criteria

(1)

5.2.3.2 Minimum Error Criteria

(1)

5.2.3.3 Scattering Criteria

(1)

5.2.3.4 Iterative Optimization

(1)

5.2.4 Hierarchical Clustering

(1)

5.2.5 Metrics

(1)

5.3 Kohonen Networks and Competitive Learning

(2)

5.4 Hebbian Learning

(1)

5.5 Adaptive Resonance Theory (ART)

(2)

5.6 Applications

(3)

5.6.1 Dimensionality Reduction

(1)

5.6.1.1 Minimization of Criteria Functions

(1)

5.6.1.2 Clustering and Dimensionality Reduction

(1)

5.6.2 Biomedical Applications

(1)

5.6.3 Diagnosis of CAD as a Clustering Problem

(1)

5.6.4 Other Biomedical Applications

(1)

5.7 Summary

(1)

References

(3)

CHAPTER 6 Design Issues

(14)

6.1 Introduction

(1)

6.1.1 Objective of the Model

(1)

6.1.2 Information Sources

(1)

6.2 Input Data Types

(5)

6.2.1 Extracting Information from the Medical Record

(1)

6.2.2 Using Information from Data Collection Sheets

(1)

6.2.2.1 Coding Multiple Responses

(1)

6.2.2.2 Ordering Categorical Data

(1)

6.2.2.3 Changing Categorical Data into Binary Data

(1)

6.2.2.4 Considering the Use of Fuzzy Input Data

(1)

6.2.2.5 Missing Data

100

(1)

6.2.3 Time Series Data

100

(1)

6.2.4 Image Data

101

(1)

6.3 Structure of Networks

101

(1)

6.3.1 Number of Layers

101

(1)

6.3.2 Connectivity

101

(1)

6.4 Implications of Network Structures

101

(4)

6.4.1 Classification Potential

101

(2)

6.4.2 Training

103

(1)

6.4.2.1 Number of Cases Required

103

(1)

6.4.3 Reduction in Number of Nodes

104

(1)

6.4.3.1 Expert Intervention

104

(1)

6.4.3.2 Statistical Significance

104

(1)

6.4.3.3 Threshold Pruning

104

(1)

6.4.3.4 Other Techniques

105

(1)

6.4.4 Output

105

(1)

6.5 Choice of Learning Algorithm

105

(1)

6.6 Summary

106

(1)

References

106

(3)

CHAPTER 7 Comparative Analysis

109

(12)

7.1 Introduction

109

(1)

7.2 Input Data Considerations

109

(1)

7.3 Supervised Learning Algorithms

110

(4)

7.3.1 Gradient Descent Procedures

111

(1)

7.3.2 Extensions to Nonlinear Decision Functions

111

(2)

7.3.3 Extensions to Multiple Categories

113

(1)

7.4 Unsupervised Learning

114

(1)

7.4.1 Clustering Methods

114

(1)

7.4.1.1 Choice of Method

114

(1)

7.4.1.2 Choice of Distance Measure

114

(1)

7.4.1.3 Limitations

115

(1)

7.4.2 Self-Organization Networks

115

(1)

7.4.2.1 Kohonen Networks

115

(1)

7.4.2.2 ART Networks

115

(1)

7.5 Network Structures

115

(1)

7.5.1 Number of Categories

115

(1)

7.5.2 Connectivity

115

(1)

7.6 Interpretation of Results

116

(2)

7.6.1 Supervised Learning

116

(1)

7.6.1.1 Training

116

(1)

7.6.1.2 Evaluation

116

(1)

7.6.1.3 Classification

117

(1)

7.6.2 Unsupervised Learning

117

(1)

7.6.2.1 Training

117

(1)

7.6.2.2 Evaluation

118

(1)

7.6.2.3 Classification

118

(1)

7.6.3 Data Scaling and Normalization

118

(1)

7.6.4 Dependence on Training Data

118

(1)

7.7 Summary

118

(1)

References

119

(2)

CHAPTER 8 Validation and Evaluation

121

(10)

8.1 Introduction

121

(1)

8.2 Data Checking

121

(2)

8.2.1 Verification of Accuracy of Data for Training

121

(1)

8.2.1.1 Chart Review

121

(1)

8.2.1.2 Databases

122

(1)

8.2.1.3 Prospective Studies

122

(1)

8.2.2 Appropriateness of Data for Training

122

(1)

8.2.3 Use of Gold Standards in Supervised Learning

123

(1)

8.3 Validation of Learning Algorithm

123

(1)

8.3.1 Technical Integrity of Algorithm

123

(1)

8.3.2 Appropriateness of Algorithm for Given Application

123

(1)

8.3.2.1 Theoretical Considerations

123

(1)

8.3.2.2 Practical Considerations

123

(1)

8.3.2.3 Comparison to Other Approaches

123

(1)

8.4 Evaluation of Performance

124

(2)

8.4.1 Supervised Learning Algorithms

124

(1)

8.4.1.1 Performance of Algorithm on Test Set

124

(1)

8.4.1.2 Relevance of Contributing Parameters

124

(1)

8.4.1.3 Comparison to Other Methods

124

(1)

8.4.2 Unsupervised Learning

124

(1)

8.4.2.1 Applicability to Other Data Sets

125

(1)

8.5 Summary

126

(1)

References

127

(4)

PART II ARTIFICIAL INTELLIGENCE

131

(86)

CHAPTER 9 Foundations of Computer-Assisted Decision Making

131

(20)

9.1 Motivation for Computer-Assisted Decision Making

131

(1)

9.2 Databases and Medical Records

131

(4)

9.2.1 The First Decade (1970-1980)

131

(3)

9.2.2 The Second Decade (1980-1990)

134

(1)

9.2.3 Current Approaches to Medical Databases

134

(1)

9.3 Mathematical Modeling and Simulation

135

(1)

9.4 Pattern Recognition

136

(1)

9.5 Bayesian Analysis

137

(1)

9.5.1 Early Bayesian Systems

137

(1)

9.5.2 Bayesian Belief Networks

138

(1)

9.6 Decision Theory

138

(1)

9.7 Symbolic Reasoning Techniques

139

(5)

9.7.1 Early Expert Systems

139

(3)

9.7.2 Second-Generation Expert Systems

142

(1)

9.7.2.1 Causal Systems

143

(1)

9.7.2.2 Reasoning with Uncertainty

143

(1)

9.7.2.3 Hybrid Systems

144

(1)

9.8 Summary

144

(1)

References

145

(6)

CHAPTER 10 Knowledge Representation

151

(22)

10.1 Production Rules

151

(9)

10.1.1 General Structure

151

(1)

10.1.2 Methods of Confirming Conditions

152

(1)

10.1.2.1 Matching

152

(1)

10.1.2.1.1 Natural Language Processing

152

(1)

10.1.2.1.2 Partial Matching

152

(1)

10.1.2.1.3 Data-Driven Approaches

153

(1)

10.1.2.2 Conflict Resolution

153

(1)

10.1.3 Rule Searching Strategies

153

(2)

10.1.4 Expanded Production Rule Systems

155

(1)

10.1.5 Certainty Factors

156

(2)

10.1.6 Advantages of Production Systems

158

(1)

10.1.7 Disadvantages of Production Systems

158

(2)

10.1.8 Areas of Applications of Production Rule Systems

160

(1)

10.2 Frames

160

(2)

10.2.1 General Structure

160

(1)

10.2.2 Inheritance

161

(1)

10.2.3 Example of a Frame-Based Decision-Support System

161

(1)

10.3 Databases

162

(4)

10.3.1 Relational Databases

163

(2)

10.3.2 Query Languages

165

(1)

10.3.3 Object-Oriented Databases

165

(1)

10.4 Predicate Calculus and Semantic Nets

166

(2)

10.4.1 Syntax

166

(1)

10.4.2 Method of Proof

167

(1)

10.4.3 Semantic Trees

167

(1)

10.4.4 Semantic Interpretation

167

(1)

10.4.5 Applications

167

(1)

10.5 Temporal Data Representations

168

(1)

10.5.1 Knowledge-Based Systems

168

(1)

10.5.2 Data-Based Systems

169

(1)

10.6 Summary

169

(2)

References

171

(2)

CHAPTER 11 Knowledge Acquisition

173

(12)

11.1 Introduction

173

(1)

11.2 Expert Input

173

(5)

11.2.1 Acquisition for a New System

173

(1)

11.2.1.1 Use of Existing Material

173

(2)

11.2.1.2 Techniques for Knowledge Elicitation

175

(1)

11.2.1.3 Dealing with Multiple Experts

176

(1)

11.2.1.4 Consistency

177

(1)

11.2.1.5 Completeness

177

(1)

11.2.2 Updating of Information

177

(1)

11.3 Learned Knowledge

178

(3)

11.3.1 Rote Learning

178

(1)

11.3.2 Learning by Being Told

178

(1)

11.3.3 Learning from Examples

178

(1)

11.3.3.1 Pattern Classification and Neural Networks

178

(1)

11.3.3.2 Learning Single Concepts

178

(1)

11.3.3.3 Learning Multiple Concepts

179

(2)

11.4 Meta-Knowledge

181

(1)

11.5 Knowledge Base Maintenance

182

(1)

11.5.1 Assuring Accuracy

182

(1)

11.5.1.1 Permission to Change Knowledge Base

182

(1)

11.5.1.2 Verifying Sources of Information

182

(1)

11.5.2 Maintaining Consistency

183

(1)

11.6 Summary

183

(1)

References

183

(2)

CHAPTER 12 Reasoning Methodologies

185

(20)

12.1 Introduction

185

(1)

12.2 Problem Representations

185

(5)

12.2.1 Graphs and Trees

185

(2)

12.2.2 Binary Trees

187

(1)

12.2.3 State-Space Representations

188

(1)

12.2.4 Problem Reduction Representations

189

(1)

12.2.5 Game Trees

190

(1)

12.3 Blind Searching

190

(1)

12.3.1 Depth-First Search

190

(1)

12.3.2 Breadth-First Search

191

(1)

12.4 Ordered Search

191

(2)

12.4.1 Uniform Cost Method

192

(1)

12.4.2 Using Heuristic Information

192

(1)

12.5 AND/OR Trees

193

(3)

12.5.1 Breadth-First Search and Depth-First of AND/OR Tree

194

(1)

12.5.2 Costs of Solution Trees

194

(1)

12.5.3 Ordered Searching of AND/OR Trees

195

(1)

12.6 Searching Game Trees

196

(1)

12.6.1 Minimax

196

(1)

12.6.2 Alpha-Beta

196

(1)

12.7 Searching Graphs

196

(1)

12.7.1 Breadth-First Graph Searching

197

(1)

12.7.2 Uniform Cost Algorithm

197

(1)

12.7.3 AND/OR Graphs

197

(1)

12.8 Rule Base Searching

197

(1)

12.8.1 Backward-Chaining

197

(1)

12.8.2 Forward-Chaining

198

(1)

12.9 Higher-Level Reasoning Methodologies

198

(3)

12.9.1 Inference Engines

198

(1)

12.9.1.1 Binary Logic Engines

198

(1)

12.9.1.2 Approximate Reasoning Engines

199

(1)

12.9.1.3 Fuzzy Logic Engines

199

(1)

12.9.1.4 Probability-Based Engines

199

(1)

12.9.2 Cognitive Models

200

(1)

12.9.3 Automatic Deduction

200

(1)

12.9.4 Natural Language Processing

200

(1)

12.10 Examples in Biomedical Expert Systems

201

(1)

12.11 Summary

201

(2)

References

203

(2)

CHAPTER 13 Validation and Evaluation

205

(12)

13.1 Introduction

205

(1)

13.2 Algorithmic Evaluation

205

(2)

13.2.1 Searching Algorithm

205

(1)

13.2.1.1 AND/OR Trees

205

(1)

13.2.1.2 Control by Meta Rules

206

(1)

13.2.1.3 Data-Driven Search

206

(1)

13.2.1.4 Hierarchical Search

206

(1)

13.2.2 Inference Engine

206

(1)

13.2.2.1 Binary Engines

206

(1)

13.2.2.2 Complex Engines

207

(1)

13.2.3 Aggregation of Evidence

207

(1)

13.2.4 Use of Meta Knowledge

207

(1)

13.3 Knowledge Base Evaluation

207

(1)

13.3.1 Expert-Derived Information

207

(1)

13.3.1.1 Individual Units of Knowledge

208

(1)

13.3.1.2 Combination of Knowledge

208

(1)

13.3.2 Learned Information

208

(1)

13.3.3 Meta Knowledge

208

(1)

13.4 System Evaluation

208

(4)

13.4.1 Evaluation with Original Knowledge Base

209

(1)

13.4.2 Evaluation with Updated Knowledge Base

209

(1)

13.4.3 Evaluation of User Interaction Parameters

209

(1)

13.4.3.1 Interpretation of Input

209

(1)

13.4.3.2 Explanation Capabilities

210

(1)

13.4.4 Validation with Clinical Data

210

(1)

13.4.4.1 Sources of Clinical Data

210

(1)

13.4.4.1.1 Retrospective Studies

210

(1)

13.4.4.2 Selection of Cases

210

(1)

13.4.4.3 Actual Outcome

211

(1)

13.4.4.4 Results from Clinical Decision-Support System

211

(1)

13.5 Summary

212

(1)

References

213

(4)

PART III ALTERNATIVE APPROACHES

217

(80)

CHAPTER 14 Genetic Algorithms

217

(8)

14.1 Foundations

217

(1)

14.2 Representation Schemes

218

(1)

14.3 Evaluation Functions

218

(1)

14.4 Genetic Operators

218

(1)

14.4.1 Mutation

218

(1)

14.4.2 Crossover

218

(1)

14.5 Evolution Strategies

219

(2)

14.5.1 Genetic Algorithms

219

(1)

14.5.2 Optimization Strategies

219

(1)

14.5.2.1 Hill Climbing

219

(1)

14.5.2.2 Simulated Annealing

219

(1)

14.5.3 Genetic Search

220

(1)

14.6 Biomedical Examples

221

(1)

14.6.1 Literature References

221

(1)

14.7 Summary

222

(1)

References

223

(2)

CHAPTER 15 Probabilistic Systems

225

(18)

15.1 Introduction

225

(1)

15.2 Bayesian Approaches

225

(6)

15.2.1 Bayes' Rule

225

(1)

15.2.2 Bayes' Decision Theory

226

(1)

15.2.3 Risk Analysis

226

(2)

15.2.4 Supervised Bayesian Learning

228

(1)

15.2.5 Decision Trees

229

(2)

15.3 Parameter Estimation

231

(2)

15.3.1 Maximum Likelihood Estimation

231

(1)

15.3.2 Bayesian Estimation

232

(1)

15.4 Discriminant Analysis

233

(1)

15.5 Statistical Pattern Classification

234

(1)

15.6 Unsupervised Learning

235

(3)

15.6.1 Parzen Windows

235

(1)

15.6.2 Nearest Neighbor Algorithms

236

(1)

15.6.3 Mixture Densities and Maximum Likelihood Estimates

236

(1)

15.6.4 Unsupervised Bayesian Learning

237

(1)

15.7 Regression Analysis

238

(2)

15.8 Biomedical Applications

240

(1)

15.9 Summary

240

(1)

References

241

(2)

CHAPTER 16 Fuzzy Systems

243

(18)

16.1 Introduction

243

(1)

16.2 Fuzzy Information

243

(2)

16.2.1 Input Data

243

(1)

16.2.2 Fuzzy Logic and Fuzzy Set Theory

244

(1)

16.2.3 Representation of Fuzzy Variables

244

(1)

16.2.4 Membership Functions

245

(1)

16.3 Fuzzy Neural Networks

245

(1)

16.4 Fuzzy Approaches for Supervised Learning Networks

246

(2)

16.4.1 Pre-Processing of Fuzzy Input

246

(1)

16.4.2 Propagation of Results

247

(1)

16.4.2.1 Max-Min Networks

247

(1)

16.4.2.2 Learning Algorithms for Interval Data

247

(1)

16.4.2.3 Analogue Models

248

(1)

16.5 Fuzzy Generalizations of Unsupervised Learning Methods

248

(1)

16.5.1 Fuzzy Associative Memories

248

(1)

16.5.2 Fuzzy Clustering

248

(1)

16.6 Reasoning with Uncertain Information

249

(7)

16.6.1 Uncertainty in Input Data

250

(1)

16.6.1.1 Degree of Presence Input

250

(1)

16.6.1.2 Linguistic Input

250

(1)

16.6.2 Uncertainty in Knowledge Base

250

(1)

16.6.3 Inference Engines for Uncertain Information

251

(1)

16.6.3.1 Binary Logic Engines

251

(1)

16.6.3.2 Fuzzy Logic Engines

252

(1)

16.6.4 Evidential Reasoning

252

(1)

16.6.4.1 Possibility Theory

252

(1)

16.6.4.2 Probabilistic Approaches

253

(1)

16.6.4.3 Dempster-Shafer Belief Theory

253

(1)

16.6.5 Compatibility Indices

254

(1)

16.6.6 Approximate Reasoning

255

(1)

16.7 Pre-Processing and Post-Processing Using Fuzzy Techniques

256

(1)

16.8 Applications in Biomedical Engineering

257

(1)

16.9 Summary

258

(1)

References

259

(2)

CHAPTER 17 Hybrid Systems

261

(12)

17.1 Hybrid Systems Approaches

261

(1)

17.2 Components of Hybrid Systems

261

(6)

17.2.1 Knowledge-Based Approaches

262

(1)

17.2.1.1 Knowledge Base

262

(1)

17.2.1.2 Input Data

263

(1)

17.2.1.3 Decision-Making Algorithm

264

(1)

17.2.1.4 Output Data

264

(1)

17.2.2 Data-Based Approaches

264

(1)

17.2.2.1 Neural Networks

265

(1)

17.2.2.2 Genetic Algorithms

266

(1)

17.2.3 General Methodologies

266

(1)

17.2.3.1 Fuzzy Logic

266

(1)

17.2.3.2 Statistical Approaches

267

(1)

17.3 Use of Complex Data Structures

267

(1)

17.3.1 Time Series Data

267

(1)

17.3.1.1 Automatic ECG Analyzers

267

(1)

17.3.1.2 Summary Methods

268

(1)

17.3.2 Image Data

268

(1)

17.4 Design Methodologies

268

(2)

17.4.1 System Structure

268

(1)

17.4.2 User Interfaces

269

(1)

17.4.3 Pre-Processing

269

(1)

17.4.4 Post-Processing

269

(1)

17.4.5 Presentation of Results

270

(1)

17.5 Summary

270

(1)

References

270

(3)

CHAPTER 18 HyperMerge, a Hybrid Expert System

273

(18)

18.1 Introduction

273

(1)

18.2 Knowledge-Based Component

273

(3)

18.2.1 Crisp Implementation

273

(1)

18.2.2 Partial Substantiation of Antecedents

274

(1)

18.2.3 Weighted Antecedents and Partial Substantiation of Rules

275

(1)

18.2.4 Handling of Temporal Data

276

(1)

18.3 Neural Network Component

276

(2)

18.3.1 Learning Algorithm

276

(1)

18.3.2 Special Data Types

277

(1)

18.3.2.1 Temporal Data

277

(1)

18.3.2.2 Crisp versus Fuzzy Temporal Data

277

(1)

18.3.2.3 Time Series Data

278

(1)

18.4 Analysis of Time Series Data

278

(4)

18.4.1 Chaos Theory

278

(1)

18.4.2 Continuous versus Discrete Chaotic Modeling

279

(1)

18.4.3 Difference Equations and Graphs

280

(1)

18.4.4 Central Tendency Measure

281

(1)

18.5 Combined System

282

(2)

18.5.1 Weighting of Antecedents

282

(1)

18.5.2 Determination of Thresholds

282

(1)

18.5.3 Neural Network with Symbolic Layer

283

(1)

18.6 Application: Diagnosis of Heart Disease

284

(5)

18.6.1 Categories of Heart Disease

284

(1)

18.6.2 Knowledge-Based Information

285

(1)

18.6.3 Data-Based Information

285

(1)

18.6.4 Chaotic Data

285

(3)

18.6.5 Sample System

288

(1)

18.7 Summary

289

(1)

References

289

(2)

CHAPTER 19 Future Perspectives

291

(6)

19.1 Introduction

291

(1)

19.2 Effects of Hardware Advances

291

(2)

19.2.1 Faster Computing Speeds

291

(1)

19.2.2 Increased Memory

292

(1)

19.2.3 Parallel Machines

292

(1)

19.2.4 Miniaturization

292

(1)

19.2.5 Organic Semiconductors

292

(1)

19.3 Effects of Increase in Knowledge

293

(1)

19.3.1 Information Explosion

293

(1)

19.3.2 Human Genome Project

293

(1)

19.3.3 Proliferation of Databases

293

(1)

19.3.4 Communication of Information

294

(1)

19.4 The Future of Software

294

(1)

19.4.1 Hybrid Systems

294

(1)

19.4.2 Parallel Systems

294

(1)

19.4.3 Nontextual Data

295

(1)

19.4.4 Neural Network Models

295

(1)

19.4.5 Artificial Intelligence Approaches

295

(1)

References

295

(2)

INDEX

297

(8)

ABOUT THE AUTHORS

305

Please wait while the item is added to your bag...

FREE SHIPPING

Rent More, Save More! Use code: BBRENTAL

5% off 1 book, 7% off 2 books, 10% off 3+ books

Neural Networks and Artificial Intelligence for Biomedical Engineering

Summary

Author Biography

Table of Contents

Supplemental Materials

FREE SHIPPING

Rent More, Save More! Use code: BBRENTAL

5% off 1 book, 7% off 2 books, 10% off 3+ books

Neural Networks and Artificial Intelligence for Biomedical Engineering

Summary

Author Biography

Table of Contents

Supplemental Materials

Digital License