book

Intelligent Systems for Engineers and Scientists, 3rd Edition

Name: Intelligent Systems for Engineers and Scientists, 3rd Edition
Author: Adrian A. Hopgood
ISBN: 9781498783798

by Adrian A. Hopgood

April 2016

Intermediate to advanced

451 pages

13h 37m

English

CRC Press

Read now

Unlock full access

Preface
The Author
Chapter 1: Introduction
1.1 Intelligent Systems1.2 A Spectrum of Intelligent Behavior1.3 Knowledge-Based Systems1.4 The Knowledge Base1.4.1 Rules and Facts1.4.2 Inference Networks1.4.3 Semantic Networks1.5 Deduction, Abduction, and Induction1.6 The Inference Engine1.7 Declarative and Procedural Programming1.8 Expert Systems1.9 Knowledge Acquisition1.10 Search1.11 Computational Intelligence1.12 Integration with Other SoftwareFurther Reading
Chapter 2: Rule-Based Systems
2.1 Rules and Facts2.2 A Rule-Based System for Boiler Control2.3 Rule Examination and Rule Firing2.4 Maintaining Consistency2.5 The Closed-World Assumption2.6 Use of Local Variables within Rules2.7 Forward Chaining (a Data-Driven Strategy)2.7.1 Single and Multiple Instantiation of Local Variables2.7.2 Rete Algorithm2.8 Conflict Resolution2.8.1 First Come, First Served2.8.2 Priority Values2.8.3 Metarules2.9 Backward Chaining (a Goal-Driven Strategy)2.9.1 The Backward-Chaining Mechanism2.9.2 Implementation of Backward Chaining2.9.3 Variations of Backward Chaining2.9.4 Format of Backward-Chaining Rules2.10 A Hybrid Strategy2.11 Explanation Facilities2.12 SummaryFurther Reading
Chapter 3: Handling Uncertainty: Probability and Fuzzy Logic
3.1 Sources of Uncertainty3.2 Bayesian Updating3.2.1 Representing Uncertainty by Probability3.2.2 Direct Application of Bayes’ Theorem3.2.3 Likelihood Ratios3.2.4 Using the Likelihood Ratios3.2.5 Dealing with Uncertain Evidence3.2.6 Combining Evidence3.2.7 Combining Bayesian Rules with Production Rules3.2.8 A Worked Example of Bayesian Updating3.2.9 Discussion of the Worked Example3.2.10 Advantages and Disadvantages of Bayesian Updating3.3 Certainty Theory3.3.1 Introduction3.3.2 Making Uncertain Hypotheses3.3.3 Logical Combinations of Evidence3.3.3.1 Conjunction3.3.3.2 Disjunction3.3.3.3 Negation3.3.4 A Worked Example of Certainty Theory3.3.5 Discussion of the Worked Example3.3.6 Relating Certainty Factors to Probabilities3.4 Fuzzy Logic: Type-13.4.1 Crisp Sets and Fuzzy Sets3.4.2 Fuzzy Rules3.4.3 Defuzzification3.4.3.1 Stage 1: Scaling the Membership Functions3.4.3.2 Stage 2: Finding the Centroid3.4.3.3 Defuzzifying at the Extremes3.4.3.4 Sugeno Defuzzification3.4.3.5 A Defuzzification Anomaly3.5 Fuzzy Control Systems3.5.1 Crisp and Fuzzy Control3.5.2 Fuzzy Control Rules3.5.3 Defuzzification in Control Systems3.6 Fuzzy Logic: Type-23.7 Other Techniques3.7.1 Dempster–Shafer Theory of Evidence3.7.2 Inferno3.8 SummaryFurther Reading
Chapter 4: Agents, Objects, and Frames
4.1 Birds of a Feather: Agents, Objects, and Frames4.2 Intelligent Agents4.3 Agent Architectures4.3.1 Logic-Based Architectures4.3.2 Emergent Behavior Architectures4.3.3 Knowledge-Level Architectures4.3.4 Layered Architectures4.4 Multiagent Systems4.4.1 Benefits of a Multiagent System4.4.2 Building a Multiagent System4.4.3 Contract Nets4.4.4 Cooperative Problem-Solving (CPS)4.4.5 Shifting Matrix Management (SMM)4.4.6 Comparison of Cooperative Models4.4.7 Communication between Agents4.5 Swarm Intelligence4.6 Object-Oriented Systems4.6.1 Introducing OOP4.6.2 An Illustrative Example4.6.3 Data Abstraction4.6.3.1 Classes4.6.3.2 Instances4.6.3.3 Attributes (or Data Members)4.6.3.4 Operations (or Methods or Member Functions)4.6.3.5 Creation and Deletion of Instances4.6.4 Inheritance4.6.4.1 Single Inheritance4.6.4.2 Multiple and Repeated Inheritance4.6.4.3 Specialization of Methods4.6.4.4 Class Browsers4.6.5 Encapsulation4.6.6 Unified Modeling Language (UML)4.6.7 Dynamic (or Late) Binding4.6.8 Message Passing and Function Calls4.6.9 Metaclasses4.6.10 Type Checking4.6.11 Persistence4.6.12 Concurrency4.6.13 Active Values and Daemons4.6.14 OOP Summary4.7 Objects and Agents4.8 Frame-Based Systems4.9 Summary: Agents, Objects, and FramesFurther Reading
Chapter 5: Symbolic Learning
5.1 Introduction5.2 Learning by Induction5.2.1 Overview5.2.2 Learning Viewed as a Search Problem5.2.3 Techniques for Generalization and Specialization5.2.3.1 Universalization5.2.3.2 Replacing Constants with Variables5.2.3.3 Using Conjunctions and Disjunctions5.2.3.4 Moving up or down a Hierarchy5.2.3.5 Chunking5.3 Case-Based Reasoning (CBR)5.3.1 Storing Cases5.3.1.1 Abstraction Links and Index Links5.3.1.2 Instance-of Links5.3.1.3 Scene Links5.3.1.4 Exemplar Links5.3.1.5 Failure Links5.3.2 Retrieving Cases5.3.3 Adapting Case Histories5.3.3.1 Null Adaptation5.3.3.2 Parameterization5.3.3.3 Reasoning by Analogy5.3.3.4 Critics5.3.3.5 Reinstantiation5.3.4 Dealing with Mistaken Conclusions5.4 SummaryFurther Reading
Chapter 6: Single-Candidate Optimization Algorithms
6.1 Optimization6.2 The Search Space6.3 Searching the Parameter Space6.4 Hill-Climbing and Gradient Descent Algorithms6.4.1 Hill-Climbing6.4.2 Steepest Gradient Descent or Ascent6.4.3 Gradient-Proportional Descent or Ascent6.4.4 Conjugate Gradient Descent or Ascent6.4.5 Tabu Search6.5 Simulated Annealing6.6 SummaryFurther Reading
Chapter 7: Genetic Algorithms for Optimization
7.1 Introduction7.2 The Basic GA7.2.1 Chromosomes7.2.2 Algorithm Outline7.2.3 Crossover7.2.4 Mutation7.2.5 Validity Check7.3 Selection7.3.1 Selection Pitfalls7.3.2 Fitness-Proportionate Selection7.3.3 Fitness Scaling for Improved Selection7.3.3.1 Linear Fitness Scaling7.3.3.2 Sigma Scaling7.3.3.3 Boltzmann Fitness Scaling7.3.3.4 Linear Rank Scaling7.3.3.5 Nonlinear Rank Scaling7.3.3.6 Probabilistic Nonlinear Rank Scaling7.3.3.7 Truncation Selection7.3.3.8 Transform Ranking7.3.4 Tournament Selection7.3.5 Comparison of Selection Methods7.4 Elitism7.5 Multiobjective Optimization7.6 Gray Code7.7 Variable Length Chromosomes7.8 Building Block Hypothesis7.8.1 Schema Theorem7.8.2 Inversion7.9 Selecting GA Parameters7.10 Monitoring Evolution7.11 Finding Multiple Optima7.12 Genetic Programming7.13 Other Forms of Population-Based Optimization7.14 SummaryFurther Reading
Chapter 8: Neural Networks
8.1 Introduction8.2 Neural Network Applications8.2.1 Classification8.2.2 Nonlinear Estimation8.2.3 Clustering8.2.4 Content-Addressable Memory8.3 Nodes and Interconnections8.4 Single and Multilayer Perceptrons8.4.1 Network Topology8.4.2 Perceptrons as Classifiers8.4.3 Training a Perceptron8.4.4 Hierarchical Perceptrons8.4.5 Buffered Perceptrons8.4.6 Some Practical Considerations8.5 Recurrent Networks8.5.1 Simple Recurrent Network (SRN)8.5.2 Hopfield Network8.5.3 MAXNET8.5.4 The Hamming Network8.6 Unsupervised Networks8.6.1 Adaptive Resonance Theory (ART) Networks8.6.2 Kohonen Self-Organizing Networks8.6.3 Radial Basis Function Networks8.7 Spiking Neural Networks8.8 SummaryFurther Reading

Chapter 9: Hybrid Systems
9.1 Convergence of Techniques9.2 Blackboard Systems for Multifaceted Problems9.3 Parameter Setting9.3.1 Genetic–Neural Systems9.3.2 Genetic–Fuzzy Systems9.4 Capability Enhancement9.4.1 Neuro–Fuzzy Systems9.4.2 Baldwinian and Lamarckian Inheritance in Genetic Algorithms9.4.3 Learning Classifier Systems9.5 Clarification and Verification of Neural Network Outputs9.6 SummaryFurther Reading
Chapter 10: Artificial Intelligence Programming Languages
10.1 A Range of Intelligent Systems Tools10.2 Features of AI Languages10.2.1 Lists10.2.2 Other Data Types10.2.3 Programming Environments10.3 Lisp10.3.1 Background10.3.2 Lisp Functions10.3.3 A Worked Example10.4 Prolog10.4.1 Background10.4.2 A Worked Example10.4.3 Backtracking in Prolog10.5 Comparison of AI Languages10.6 SummaryFurther Reading
Chapter 11: Systems for Interpretation and Diagnosis
11.1 Introduction11.2 Deduction and Abduction for Diagnosis11.2.1 Exhaustive Testing11.2.2 Explicit Modeling of Uncertainty11.2.3 Hypothesize-and-Test11.3 Depth of Knowledge11.3.1 Shallow Knowledge11.3.2 Deep Knowledge11.3.3 Combining Shallow and Deep Knowledge11.4 Model-Based Reasoning11.4.1 The Limitations of Rules11.4.2 Modeling Function, Structure, and State11.4.2.1 Function11.4.2.2 Structure11.4.2.3 State11.4.3 Using the Model11.4.4 Monitoring11.4.5 Tentative Diagnosis11.4.5.1 The Shotgun Approach11.4.5.2 Structural Isolation11.4.5.3 The Heuristic Approach11.4.6 Fault Simulation11.4.7 Fault Repair11.4.8 Using Problem Trees11.4.9 Summary of Model-Based Reasoning11.5 Case Study: A Blackboard System for Interpreting Ultrasonic Images11.5.1 Ultrasonic Imaging11.5.2 Agents in DARBS11.5.3 Rules in DARBS11.5.4 The Stages of Image Interpretation11.5.4.1 Arc Detection Using the Hough Transform11.5.4.2 Gathering the Evidence11.5.4.3 Defect Classification11.5.5 The Use of Neural Networks11.5.5.1 Defect Classification Using a Neural Network11.5.5.2 Echodynamic Classification Using a Neural Network11.5.5.3 Combining the Two Applications of Neural Networks11.5.6 Rules for Verifying Neural Networks11.6 SummaryFurther Reading
Chapter 12: Systems for Design and Selection
12.1 The Design Process12.2 Design as a Search Problem12.3 Computer-Aided Design12.4 The Product Design Specification (PDS): A Telecommunications Case Study12.4.1 Background12.4.2 Alternative Views of a Network12.4.3 Implementation12.4.4 The Classes12.4.4.1 Network12.4.4.2 Link12.4.4.3 Site12.4.4.4 Information Stream12.4.4.5 Equipment12.4.5 Summary of PDS Case Study12.5 Conceptual Design12.6 Constraint Propagation and Truth Maintenance12.7 Case Study: Design of a Lightweight Beam12.7.1 Conceptual Design12.7.2 Optimization and Evaluation12.7.3 Detailed Design12.8 Design as a Selection Exercise12.8.1 Overview12.8.2 Merit Indices12.8.3 The Polymer Selection Example12.8.4 Two-Stage Selection12.8.5 Constraint Relaxation12.8.6 A Naive Approach to Scoring12.8.7 A Better Approach to Scoring12.8.8 Case Study: Design of a Kettle12.8.9 Reducing the Search Space by Classification12.9 Failure Mode and Effects Analysis (FMEA)12.10 SummaryFurther Reading
Chapter 13: Systems for Planning
13.1 Introduction13.2 Classical Planning Systems13.3 STRIPS13.3.1 General Description13.3.2 An Example Problem13.3.3 A Simple Planning System in Prolog13.4 Considering the Side Effects of Actions13.4.1 Maintaining a World Model13.4.2 Deductive Rules13.5 Hierarchical Planning13.5.1 Description13.5.2 Benefits of Hierarchical Planning13.5.3 Hierarchical Planning with ABSTRIPS13.6 Postponement of Commitment13.6.1 Partial Ordering of Plans13.6.2 The Use of Planning Variables13.7 Job-Shop Scheduling13.7.1 The Problem13.7.2 Some Approaches to Scheduling13.8 Constraint-Based Analysis13.8.1 Constraints and Preferences13.8.2 Formalizing the Constraints13.8.3 Identifying the Critical Sets of Operations13.8.4 Sequencing in Disjunctive Case13.8.5 Sequencing in Nondisjunctive Case13.8.6 Updating Earliest Start Times and Latest Finish Times13.8.7 Applying Preferences13.8.8 Using Constraints and Preferences13.9 Replanning and Reactive Planning13.10 SummaryFurther Reading
Chapter 14: Systems for Control
14.1 Introduction14.2 Low-Level Control14.2.1 Open-Loop Control14.2.2 Feedforward Control14.2.3 Feedback Control14.2.4 First- and Second-Order Models14.2.5 Algorithmic Control: The PID Controller14.2.6 Bang-Bang Control14.3 Requirements of High-Level (Supervisory) Control14.4 Blackboard Maintenance14.5 Time-Constrained Reasoning14.5.1 Prioritization of Processes14.5.2 Approximation14.5.2.1 Approximate Search14.5.2.2 Data Approximations14.5.2.3 Knowledge Approximations14.5.3 Single and Multiple Instantiation14.6 Fuzzy Control14.7 The BOXES Controller14.7.1 The Conventional BOXES Algorithm14.7.2 Fuzzy BOXES14.8 Neural Network Controllers14.8.1 Direct Association of State Variables with Action Variables14.8.2 Estimation of Critical State Variables14.9 Statistical Process Control (SPC)14.9.1 Applications14.9.2 Collecting the Data14.9.3 Using the Data14.10 SummaryFurther Reading
Chapter 15: The Future of Intelligent Systems
15.1 Benefits15.2 Trends in Implementation15.3 Intelligent Systems and the Internet15.4 Ubiquitous Intelligent Systems15.5 Conclusion
References

Content preview from Intelligent Systems for Engineers and Scientists, 3rd Edition

Chapter 11

Systems for Interpretation and Diagnosis

11.1 Introduction

Diagnosis is the process of determining the nature of a fault or malfunction, based on a set of symptoms. Input data, that is, the symptoms, are interpreted and the underlying cause of these symptoms is the output. Diagnosis is, therefore, a special case of the more general problem of interpretation. There are many circumstances in which we may wish to interpret data, other than diagnosing problems. Examples include the interpretation of images (e.g., optical, x-ray, ultrasonic, electron microscopic), meters, gauges, and statistical data (e.g., from surveys of people or from a radiation counter). This chapter will examine some of the intelligent systems techniques that are ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Discrete Structures, Logic, and Computability, 4th Edition

Publisher Resources

ISBN: 9781439865965

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Intelligent Systems for Engineers and Scientists, 3rd Edition

by Adrian A. Hopgood

Systems for Interpretation and Diagnosis

11.1 Introduction

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.