CHAPTER 16 Neural Computing Applications, and Advanced Artificial Intelligent Systems and Applications.

Slides:



Advertisements
Similar presentations
Approaches, Tools, and Applications Islam A. El-Shaarawy Shoubra Faculty of Eng.
Advertisements

© Negnevitsky, Pearson Education, Lecture 12 Hybrid intelligent systems: Evolutionary neural networks and fuzzy evolutionary systems Introduction.
Decision Support and Artificial Intelligence Jack G. Zheng May 21 st 2008 MIS Chapter 4.
Decision Support and Artificial Intelligence Jack G. Zheng July 11 th 2005 MIS Chapter 4.
Neural Networks in Financial Analysis
11-1 Intelligent Support Systems Copied from:
Expert Systems Expert Systems are computerized advisory programs that imitate the reasoning process of experts. They consist of a knowledge base and a.
An Introduction to Artificial Intelligence By Dr Brad Morantz Viral Immunology Center Georgia State University.
TECHNOLOGY GUIDE 4: Intelligent Systems
4 Intelligent Systems.
SBSE Course 3. EA applications to SE Analysis Design Implementation Testing Reference: Evolutionary Computing in Search-Based Software Engineering Leo.
Decision Support Systems
The Decision-Making Process IT Brainpower
Chapter 11 Artificial Intelligence and Expert Systems.
Artificial Intelligence
Genetic Algorithms Learning Machines for knowledge discovery.
Marakas: Decision Support Systems, 2nd Edition © 2003, Prentice-Hall Chapter Chapter 7: Expert Systems and Artificial Intelligence Decision Support.
Basic concepts of Data Mining, Clustering and Genetic Algorithms Tsai-Yang Jea Department of Computer Science and Engineering SUNY at Buffalo.
CHAPTER 16 Neural Computing Applications, and Advanced Artificial Intelligent Systems and Applications.
Data Mining By Andrie Suherman. Agenda Introduction Major Elements Steps/ Processes Tools used for data mining Advantages and Disadvantages.
Chapter 11 Managing Knowledge. Dimensions of Knowledge.
Intelligent Support Systems
Revision Michael J. Watts
CHAPTER 12 ADVANCED INTELLIGENT SYSTEMS © 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition, Turban, Aronson, and Liang.
0AI-based Information Technology  Information Technology Based on AI ● What is Artificial Intelligence? ● Artificial Intelligence vs. Natural Intelligence.
Chapter 18: Neural Computing Applications, Genetic Algorithms, Fuzzy Logic and Hybrid Intelligent Systems Several Real-world Applications of ANN Technology.
Slides are based on Negnevitsky, Pearson Education, Lecture 12 Hybrid intelligent systems: Evolutionary neural networks and fuzzy evolutionary systems.
Using Neural Networks in Database Mining Tino Jimenez CS157B MW 9-10:15 February 19, 2009.
© 2003, Prentice-Hall Chapter Chapter 4: Machines Than Can Learn Modern Data Warehousing, Mining, and Visualization: Core Concepts by George M. Marakas.
Soft Computing Lecture 18 Foundations of genetic algorithms (GA). Using of GA.
Marakas: Decision Support Systems, 2nd Edition © 2003, Prentice-Hall Chapter Chapter 9: Machines Than Can Learn Decision Support Systems in the 21.
PLUG IT IN 5 Intelligent Systems. 1.Introduction to intelligent systems 2.Expert Systems 3.Neural Networks 4.Fuzzy Logic 5.Genetic Algorithms 6.Intelligent.
An Introduction to Artificial Intelligence and Knowledge Engineering N. Kasabov, Foundations of Neural Networks, Fuzzy Systems, and Knowledge Engineering,
11 C H A P T E R Artificial Intelligence and Expert Systems.
Neural Networks & Cases
Chapter 7 Neural Networks in Data Mining Automatic Model Building (Machine Learning) Artificial Intelligence.
1 Integration of Neural Network and Fuzzy system for Stock Price Prediction Student : Dah-Sheng Lee Professor: Hahn-Ming Lee Date:5 December 2003.
Aspects of Artificial Intelligence Himadri Barman.
1 Introduction to Neural Networks And Their Applications.
Fuzzy Genetic Algorithm
Neural Networks II By Jinhwa Kim. 2 Neural Computing is a problem solving methodology that attempts to mimic how human brain function Artificial Neural.
I Robot.
Chapter 5: Business Intelligence: Data Warehousing, Data Acquisition, Data Mining, Business Analytics, and Visualization DECISION SUPPORT SYSTEMS AND BUSINESS.
© 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition, Turban, Aronson, and Liang 12-1 Chapter 12 Advanced Intelligent Systems.
G ENETIC A LGORITHM. S IMULATED E VOLUTION We need the following Representation of an individual Fitness Function Reproduction Method Selection Criteria.
Chapter 4 Decision Support System & Artificial Intelligence.
PLUG IT IN 5 Intelligent Systems. 1.Introduction to intelligent systems 2.Expert Systems 3.Neural Networks 4.Fuzzy Logic 5.Genetic Algorithms 6.Intelligent.
 Based on observed functioning of human brain.  (Artificial Neural Networks (ANN)  Our view of neural networks is very simplistic.  We view a neural.
Artificial Intelligence, Expert Systems, and Neural Networks Group 10 Cameron Kinard Leaundre Zeno Heath Carley Megan Wiedmaier.
A field of study that encompasses computational techniques for performing tasks that require intelligence when performed by humans. Simulation of human.
ITEC 1010 Information and Organizations Chapter V Expert Systems.
Copyright © 2011 Pearson Education, Inc. Publishing as Pearson Addison-Wesley Chapter 28 Data Mining Concepts.
Business Intelligence and Decision Support Systems (9 th Ed., Prentice Hall) Chapter 6: Artificial Neural Networks for Data Mining.
An Evolutionary Algorithm for Neural Network Learning using Direct Encoding Paul Batchis Department of Computer Science Rutgers University.
A Presentation on Adaptive Neuro-Fuzzy Inference System using Particle Swarm Optimization and it’s Application By Sumanta Kundu (En.R.No.
A case in Neural Network - A Nerual Network for Bankruptcy Prediction.
George Yauneridge.  Machine learning basics  Types of learning algorithms  Genetic algorithm basics  Applications and the future of genetic algorithms.
 Negnevitsky, Pearson Education, Lecture 12 Hybrid intelligent systems: Evolutionary neural networks and fuzzy evolutionary systems n Introduction.
CHAPTER 16 Neural Computing Applications, and Advanced Artificial Intelligent Systems and Applications.
CHAPTER 1 Introduction BIC 3337 EXPERT SYSTEM.
Organization and Knowledge Management
Introduction Characteristics Advantages Limitations
과제 3: 인공신경망.
MANAGING KNOWLEDGE FOR THE DIGITAL FIRM
Chapter 12 Advanced Intelligent Systems
Neural Networks & a case with bankruptcy prediction
Intelligent Systems and
A case in Neural Network - A Nerual Network for Bankruptcy Prediction
A case in Neural Network - A Nerual Network for Bankruptcy Prediction
Presentation transcript:

CHAPTER 16 Neural Computing Applications, and Advanced Artificial Intelligent Systems and Applications

n Several Real-World Applications of ANN Technology n Advanced AI Systems –Genetic Algorithms –Fuzzy Logic –Qualitative Reasoning n Integration (Hybrids)

Areas of ANN Applications: An Overview Representative Business ANN Applications n Accounting n Finance n Human Resources n Management n Marketing n Operations

Credit Approval with Neural Networks n Increases loan processor productivity by 25 to 35 % over other computerized tools n Also detects credit card fraud

The ANN Method n Data from the application and into a database n Preprocess applications manually n Neural network trained in advance with many good and bad risk cases

Neural Network Credit Authorizer Construction Process n Step 1: Collect data n Step 2: Separate data into training and test sets n Step 3: Transform data into network inputs n Step 4: Select, train, and test network n Step 5: Deploy developed network application

Bankruptcy Prediction with Neural Networks Concept Phase n Paradigm: Three-layer network, back-propagation n Training data: Small set of well-known financial ratios n Data available on bankruptcy outcomes n Supervised network n Training time not to be a problem

Application Design n Five Input Nodes X1: Working capital/total assets X2: Retained earnings/total assets X3: Earnings before interest and taxes/total assets X4: Market value of equity/total debt X5: Sales/total assets n Single Output Node: Final classification for each firm –Bankruptcy or –Nonbankruptcy n Development Tool: NeuroShell

Architecture of the Bankruptcy Prediction Neural Network (Figure 16.3) X4 X3 X5 X1 X2 Bankrupt 0 Not bankrupt 1

n ANN did better predicting 22 out of the 27 actual cases n Discriminant analysis predicted only 16 correctly n Error Analysis –Five bankrupt firms misclassified by both methods –Similar for nonbankrupt firms n Neural network at least as good as conventional n Accuracy of about 80 percent is usually acceptable for neural network applications

Stock Market Prediction System with Modular Neural Networks n Accurate Stock Market Prediction - Complex Problem n Several Mathematical Models - Disappointing Results n Fujitsu and Nikko Securities: TOPIX Buying and Selling Prediction System

n Input: Several technical and economic indexes n Several modular neural networks relate past indexes, and buy/sell timing n Prediction system –Modular neural networks –Very accurate

Integrated ANNs and Expert Systems 1. Resource Requirements Advisor 2. Personnel Resource Requirements Advisor 3. Diagnostic System for an Airline 4. Manufacturing Product Liability 5. Oil Refinery Production Scheduling and Environmental Control

Genetic Algorithms n Goal (evolutionary algorithms): Demonstrate self- organization and adaptation by exposure to the environment n System learns to adapt to changes. n Example 1: Vector Game –Random trial and error –Genetic algorithm solution n Process (Figure 16.9) n Example: the game of MasterMind

Genetic Algorithm Definition and Process Genetic algorithm: "an iterative procedure maintaining a population of structures that are candidate solutions to specific domain challenges (Grefenstette, 1982) n Each candidate solution is called a chromosome n Chromosomes can copy themselves, mate, and mutate n Use specific genetic operators - reproduction, crossover and mutation

Primary Operators of Most Genetic Algorithms n Reproduction n Crossover n Mutation

Genetic Algorithm Operators Parent 1 Parent Child 1 Child 2 Mutation

GA Example: The Knapsack Problem n Item: n Benefit: n Weight: n Knapsack holds a maximum of 22 pounds n Fill it to get the maximum benefit n Solutions take the form of a string of 1s n Solution: n Means choose items 1, 2, 5. Weight = 21, Benefit = 20 n Evolver solution in Figure 16.10

Genetic Algorithm Application Areas n Dynamic process control n Induction of rule optimization n Discovering new connectivity topologies n Simulating biological models of behavior and evolution n Complex design of engineering structures n Pattern recognition n Scheduling n Transportation n Layout and circuit design n Telecommunication n Graph-based problems

Business Applications n Channel 4 Television (England) to schedule commercials n Driver scheduling in a public transportation system n Jobshop scheduling n Assignment of destinations to sources n Trading stocks n Productivity in whisky making is increased n Often genetic algorithm hybrids with other AI methods

Representative Commercial Packages n Evolver (Excel spreadsheet add-in) n Genetic Algorithm User Interface (GAUI) n OOGA (Object-Oriented GA for industrial use) n XperRule Genasys (ES shell with an embedded genetic algorithm) n Sugal Genetic Algorithm Simulator

Fuzzy Logic n Fuzzy logic deals with uncertainty n Uses the mathematical theory of fuzzy sets n Simulates the process of normal human reasoning n Allows the computer to behave less precisely and logically Decision making involves gray areas and the term maybe

Membership Functions in Fuzzy Sets (Figure 16.11) Membership ShortMediumTall Height in inches (1 inch = 2.54 cm)

Fuzzy Logic Applications and Software n Difficult to apply when people provide evidence n Used in consumer products that have sensors –Air conditioners –Cameras –Dishwashers –Microwaves –Toasters n Special software packages n Controls applications

Examples of Fuzzy Logic Example 1: Strategic planning –STRATASSIST - fuzzy expert system that helps small- to medium-sized firms plan strategically for a single product Example 2: Fuzziness in real estate Example 3: A fuzzy bond evaluation system

Fuzzy Logic Software n Fuzzy Inference Development Environment (FIDE) n Z Search n HyperLogic Corporation demos n Others

Qualitative Reasoning (QR) –Means of representing and making inferences using general, physical knowledge about the world –QR is a model-based procedure that consequently incorporates deep knowledge about a problem domain –Typical QR Logic If you touch a kettle full of boiling water on a stove, you will burn yourself If you throw an object off a building, it will go down

n But n No specific knowledge about boiling temperature, just that it is really hot! n No specific information about the building or object, unless you are the object, or you are trying to catch it

Some Real-World QR Applications n Nuclear plant fault diagnoses n Business processes n Financial markets n Economic systems

Intelligent Systems Integration n Combine –Neural Computing –Expert Systems –Genetic Algorithms –Fuzzy Logic n Example: International investment management-- stock selection n Fuzzy Logic and ANN (FuzzyNet) to forecast the expected returns from stocks, cash, bonds, and other assets to determine the optimal allocation of assets

Data Mining and Knowledge Discovery in Databases (KDD) n Hidden value in data n Knowledge Discovery in Databases (KDD)