Artificial intelligence : approaches, tools and applications / Brent M. Gordon, editor.

Format:

Book

Contributor:

Gordon, Brent M.

Series:

Scientific revolutions series.

Computer science, technology and applications.

Scientific revolutions

Computer science, technology and applications

Language:

English

Subjects (All):

Artificial intelligence.

Physical Description:

1 online resource (179 p.)

Edition:

1st ed.

Place of Publication:

New York : Nova Science Publishers, c2011.

Language Note:

English

Summary:

Artificial Intelligence may be defined as a collection of several analytic tools that collectively attempt to imitate life and has matured to a set of analytic tools that facilitate solving problems which were previously difficult or impossible to solve. In this book, the authors present topical research in the study of the tools and applications of artificial intelligence. Topics discussed include the application of artificial intelligence in the oil and gas industry and in metal stamping die design; and using artificial intelligence to predict embryo quality and in biomedical imaging techniques.

Contents:

Intro

ARTIFICIAL INTELLIGENCE: APPROACHES, TOOLS AND APPLICATIONS

Library of Congress Cataloging-in-Publication Data

CONTENTS

PREFACE

Chapter 1 APPLICATION OF ARTIFICIAL INTELLIGENCE IN THE UPSTREAM OIL AND GAS INDUSTRY

ABSTRACT

1. NEURAL NETWORKS AND THEIR BACKGROUND

1.1. A Short History of Neural Networks

1.2. Structure of a Neural Network

1.3. Mechanics of Neural Networks Operation

2. EVOLUTIONARY COMPUTING

2.1. Genetic Algorithms

2.2. Mechanism of a Genetic Algorithm

3. FUZZY LOGIC

3.1. Fuzzy Set Theory

3.2. Approximate Reasoning

3.3. Fuzzy Inference

4. APPLICATIONS IN THE OIL AND GAS INDUSTRY

4.1. Neural Networks Applications

4.1.1. Reservoir Characterization

4.1.2. Virtual Magnetic Resonance Imaging Logs

4.2. Genetic Algorithms Applications

4.3. Fuzzy Logic Applications

4.3.1. Results

REFERENCES

Chapter 2 AN ARTIFICIAL INTELLIGENCE APPROACH FOR MODELING AND OPTIMIZATION OF THE EFFECT OF LASER MARKING PARAMETERS ON GLOSS OF THE LASER MARKED GOLD

1. INTRODUCTION

2. ANFIS, ANNS, GA AND PSO

2.1. Adaptive Neuro-Fuzzy Inference System

2.1.1. Anfis Architecture

2.1.2. ANFIS Learning Algorithm

2.2. Artificial Neural Networks

2.2.1. Network Types

2.2.2. Training Algorithm

2.3. Genetic Algorithm

(a) Population Initialization

(b) Operators

(c) Chromosome Evaluation

2.4. Particle Swarm Optimization

3. INPUT/OUTPUT VARIABLES

4. ANFIS AND ANNSIMPLEMENTATION

4.1.Model Building Methodology

4.2. ANFIS Modeling

4.3. ANNs Modeling

4.4. Results and Discussion

5. GA AND PSO IMPLEMENTATION

5.1. Optimization

5.2. Optimization Using GA

5.3. Optimization Using PSO

5.4. Results and Discussion

6. METHODOLOGY VALIDATION

CONCLUSION.

APPENDIX A. COMPARISONOF SOMEOF ANFIS MODELING AND ANN MODELINGRESULTSBEFORE AND AFTERCLEANING THE DATA

Chapter 3 AI APPLICATIONS TO METAL STAMPING DIE DESIGN

1.1. Sheet Metal Operations and Press Tools

1.2. Design of Press Tools

1.3. Artificial Intelligence (AI)

Knowledge Based System (KBS) /Expert System (ES)

Neural Network (NN)

Case Based Reasoning (CBR)

Hybrid System

2. REVIEW OF APPLICATIONS OF AI TECHNIQUES TO METAL STAMPING DIE DESIGN

2.1. Manufacturability Evaluation of Sheet Metal Parts

2.2. Process Planning and Metal Stamping Die Design

2.3. Comments on Reviewed Literature

3. PROCEDURE FOR DEVELOPMENT OF KNOWLEDGE BASE SYSTEM (KBS) FOR DESIGN OF METAL STAMPING DIE

3.1. Knowledge Acquisition

Literature Reviews

Die Design Experts

Industrial Visits

Industrial Brochures

3.2. Framing of Production Rules

3.3. Verification of Production Rules

3.4. Sequencing of Production Rules

3.5. Identification of Suitable Hardware and a Computer Language

3.6. Construction of Knowledge Base

3.7. Choice of Search Strategy

3.8. Preparation of User Interface

4. AN INTELLIGENT SYSTEM FOR DESIGN OF PROGRESSIVE DIE: INTPDIE

4.1. Organization of the System

4.2. Validation of the Proposed System INTPDIE

4.3. Scope of Further Research Work

CONCLUSION

Chapter 4 STRUCTURAL FEATURES SIMULATION ON MECHANOCHEMICAL SYNTHESIS OF AL2O3-TIB2 NANOCOMPOSITE USING ANN WITH BAYESIAN REGULARIZATION AND ANFIS

2. EXPERIMENTALPROCEDURES

3. MODELING INTENSITYIN XRD

3.1. Pre-Processing of the Data

3.2. ANFIS

3.3. ANN with Bayesian Regularization with Full Sampling

3.4. Optimizing ANN by Taguchi Method

4. RESULTS AND DISCUSSION

4.1. Experimental Data

4.2. Modeling by ANFIS.

4.3. Modeling by ANN

4.3. Simulation of Structural Features

CONCLUSIONS

Chapter 5 AN ARTIFICIAL INTELLIGENCE TOOL FOR PREDICTING EMBRYOS QUALITY

2. PROPOSED SYSTEM

2.1. Segmentation and Pre-Processing

2.2. Feature Extraction

2.3. Classification

3. EMBRYOS DATASET

4. RESULTS

DISCUSSION

Chapter 6 PASSIVE SYSTEM RELIABILITY OF THE NUCLEAR POWER PLANTS (NPPS) USING FUZZY SET THEORY IN ARTIFICIAL INTELLIGENCE

2. METHOD

3. CALCULATION

4. RESULT AND DISCUSSION

ACKNOWLEDGMENTS

Chapter 7 EMERGENT TOOLS IN AI

1. REPRESENTATION PROBLEMS

2. RULES

3. INFERENCE IN SBR

4. FRAMES

5. SCRIPTS

6. SEARCHING METHODS

7. INTRODUCTION TO FUZZINESS

8. ROUGHNESS

9. COMPARISON BETWEEN FUZZINESS AND ROUGHNESS

10. NETWORKS

Chapter 8 NEURAL NETWORKS APPLIED TO MICRO-COMPUTED TOMOGRAPHY

2. SYNCHROTRON RADIATION MICRO-COMPUTED TOMOGRAPHY FOR BIOMEDICAL IMAGING

3. ARTIFICIAL NEURAL NETWORKS TRAINING STRATEGIES

4. VALIDATION METHODOLOGY: THE LEAVE-ONE-OUT CROSS VALIDATION

5. COMPUTATIONAL EXPERIMENTAL RESULTS

6. DISCUSSION

INDEX.

Notes:

Description based upon print version of record.

Includes bibliographical references and index.

Description based on print version record.

ISBN:

1-62081-485-4

OCLC:

781714706