Front Cover -- Pattern Recognition in Industry -- Copyright Page -- Contents -- Preface -- Acknowledgments -- About the Author -- Part I: Philosophy -- Chapter 1. Introduction -- 1.1. Distinguishing Knowledge and Information from Data -- 1.2. Whence Pattern Recognition Technology -- 1.3. Thermodynamic Concept of Order Leading to Information Theory -- 1.4. Modeling Informed by Observation -- 1.5. Pattern Recognition Technology Triad -- References -- Chapter 2. Patterns Within Data -- 2.1. Types of Data -- 2.2. Characterizing Data -- 2.3. Distance Between Data -- 2.4. Organizing Data-Clustering / Auto-Classification -- 2.5. Organizing Data-Data Series Resonance -- 2.6. Organizing Data-Correlative Modeling -- References -- Chapter 3. Adapting Biological Principles for Deployment in Computational Science -- 3.1. Learning Organisms-An Introduction to Neural Nets -- 3.2. Supervised Learning -- 3.3. Unsupervised Learning -- 3.4. Models that Self-Organize Data (Unsupervised Learning) as well as Correlate them with Dependent Outcomes (Supervised Learning) -- 3.5. Genetic Algorithms -- References -- Chapter 4. Issues in Predictive Empirical Modeling -- 4.1. Pre-Conditioning Data: Pre- and Post-Processing -- 4.2. Detecting Extrapolative Conditions -- 4.3. Embedding Mechanistic Understanding / Experiential Judgment to Enhance Extrapolative Robustness -- 4.4. Insight into Model Behavior -- Part II: Technology -- Chapter 5. Supervised Learning-Correlative Neural Nets -- 5.1. Supervised Learning with Back-Propagation Neural Nets -- 5.2. Feedforward-Exercising the BP Net in Predictive Mode-Neuron Transformation Function -- 5.3. BP Training-Connection Weights Adjusted by the "Delta Rule" to Minimize Learning Errors -- 5.4. Back-Propagation Equations for General Transformation Functions -- 5.5. Back-Propagation Equations for Sigmoidal Transformation Functions.

5.6. Conjugate Gradient Methodology for Rapid and Robust Convergence -- 5.7. Separating Signal from Noise in Training -- 5.8. Pre-Conditioning Data for BP Nets -- 5.9. Supervised Learning with Radial Basis Function Neural Nets -- 5.10. Seeding the Input Data Space with RBF Cluster Centers -- 5.11. Assigning Spheres of Influence to each Cluster -- 5.12. Activating Clusters from a Point in the Data Space -- 5.13. Developing RBF Correlation Models-Assigning Weights to Map Outcome -- 5.14. Pre-Conditioning Data for RBF Nets -- 5.15. Neural Net Correlation Models -- References -- Chapter 6. Unsupervised Learning: Auto-Clustering and Self-Organizing Data -- 6.1. Unsupervised Learning-Value to Industry -- 6.2. Auto-Clustering Using Radial Basis Functions -- 6.3. RBF Cluster Radius -- 6.4. Competitive Learning -- 6.5. Data Pre-Conditioning for Competitive Learning -- References -- Chapter 7. Customizing for Industrial Strength Applications -- 7.1. Modeling: The Quest for Explaining and Predicting Processes -- 7.2. Combining Empiricism with Mechanistic Understanding -- 7.3. Embedding an Idealized (Partially Correct) Model -- 7.4. Embedding A Priori Understanding in the Form of Constraints -- 7.5. Incorporating Mixed Data Types -- 7.6. Confidence Measure for Characterizing Predictions -- 7.7. Interpreting Trained Neural Net Structures -- 7.8. Graphical Interpretation of Trained Neural Net Structures -- References -- Chapter 8. Characterizing and Classifying Textual Material -- 8.1. Capturing a Document's Essential Features through Fingerprinting -- 8.2. Similar Documents Auto-Classified into Distinct Clusters -- 8.3. Activity Profiles of Authors Provide Competitive Insight -- 8.4. Visualizing a Document's Contents -- 8.5. Identifying Keywords through Entropic Analysis of Text Documents.

8.6. Automation Shrinks Time and Resources Required to Keep up with the World -- References -- Chapter 9. Pattern Recognition in Time Series Analysis -- 9.1. Leading Indices as Drivers -- 9.2. Concept of Resonance in Quantifying Similarities between Time Series -- 9.3. Identifying Leading Indicators -- 9.4. Forecasting -- Reference -- Chapter 10. Genetic Algorithms -- 10.1. Background -- 10.2. Definitions -- 10.3. Setting the Stage -- 10.4. Selection -- 10.5. Mating -- 10.6. Mutation -- 10.7. "Breeding" Fit Solutions -- 10.8. Discovering Profitable Operating Strategies -- 10.9. Product Formulation -- References -- Part III: Case Studies -- Chapter 11. Harnessing the Technology for Profitability -- 11.1. Process Industry Application Modes -- 11.2. Business Applications -- 11.3. Case Studies that Follow -- Chapter 12. Reactor Modeling Through in Situ Adaptive Learning -- 12.1. Background -- 12.2. Reactor Catalyst Deactivation -- 12.3. Model Configuration -- 12.4. In Situ Modeling Scheme -- 12.5. Validation Procedure -- 12.6. Validation Results -- 12.7. Roles Played by Modeling and Plant Operational Teams -- 12.8. Competitive Advantage Derived through this Approach -- Reference -- Chapter 13. Predicting Plant Stack Emissions to Meet Environmental Limits -- 13.1. Background -- 13.2. Reactor Flow and Model Configuration -- 13.3. Model Training and Results -- 13.4. Identifying Optimal Operating Windows for Enhancing Profits -- Chapter 14. Predicting Fouling/Coking in Fired Heaters -- 14.1. Background -- 14.2. Model Configuration -- 14.3. Model Results -- 14.4. Conclusions -- Chapter 15. Predicting Operational Credits -- 15.1. Background -- 15.2. Issues -- 15.3. Model Configuration -- 15.4. Model Results -- 15.5. Plant Follow-Up -- Chapter 16. Pilot Plant Scale-up by Interpreting Tracer Diagnostics -- 16.1. Background -- 16.2. Issue.

16.3. Genetic Algorithm-Simulation Model Coupling -- 16.4. Results and Conclusion -- Chapter 17. Predicting Distillation Tower Temperatures: Mining Data for Capturing Distinct Operational Variability -- 17.1. Background -- 17.2. Issue -- 17.3. Model Configuration -- 17.4. Identifying Distinctly Different Operating Conditions -- 17.5. Results -- Chapter 18. Enabling New Process Design Based on Laboratory Data -- 18.1. Background -- 18.2. Model Configuration-Bi-Level Focus for "Spot-Lighting" Region of Interest -- 18.3. Model Results -- 18.4. Conclusion -- Chapter 19. Forecasting Price Changes of a Composite Basket of Commodities -- 19.1. Background -- 19.2. Approach and Model Configuration -- 19.3. Model Results -- 19.4. Conclusions -- Chapter 20. Corporate Demographic Trend Analysis -- 20.1. Background -- 20.2. Issues -- 20.3. Approach and Model Configuration -- 20.4. Model Results and Conclusions -- Epilogue -- Appendices -- Appendix A1. Thermodynamics and Information Theory -- A1.1. Thermodynamic Concepts Set the Stage for Quantifying Information -- A1.2. Equilibrium as a State of Disorder-Organization as a Value-Adding Process -- A1.3. Entropy, Disorder, and Uncertainty -- A1.4. Opportunities Found in Imbalances -- A1.5. Appreciation through Quantification -- A1.6. Quantifying Information Transfer -- A1.7. Information Content in a System -- References -- Appendix A2. Modeling -- A2.1. What Are Models -- A2.2. Mechanistic Modeling-General Laws -- A2.3. Particular Laws and Constitutive Relations -- A2.4. Combining General Laws and Constitutive Relations -- A2.5. Modeling Directly from Data -- Reference -- Index.