Intelligent computational systems : a multi-disciplinary perspective / Edited by Faria Nassiri-Mofakham.

Format:

Book

Author/Creator:

Mofakham, Faria Nassiri, Author.

Contributor:

Nassiri-Mofakham, Faria, editor.

Series:

Current and future Developments in Artificial Intelligence, 2543-1579 ; Volume 1

Language:

English

Subjects (All):

Artificial intelligence--Congresses.

Artificial intelligence.

Physical Description:

1 online resource (428 pages) : illustrations (some color), tables.

Edition:

1st ed.

Place of Publication:

Sharjah, United Arab Emirates : Bentham Science Publishers, 2017.

Summary:

Intelligent Computational Systems presents current and future developments in intelligent computational systems in a multi-disciplinary context. Readers will learn about the pervasive and ubiquitous roles of artificial intelligence (AI) and gain a perspective about the need for intelligent systems to behave rationally when interacting with humans in complex and realistic domains. This reference covers widespread applications of AI discussed in 11 chapters which cover topics such as AI and behavioral simulations AI schools automated negotiation language analysis and learning financial prediction sensor management Multi-agent systems and much more. This reference work is will assist researchers advanced-level students and practitioners in information technology and computer science fields interested in the broad applications of AI.

Contents:

Intro

CONTENTS

FOREWORD

PREFACE

List of Contributors

PART I: SIMULATION

Simulation, Intelligence and Agents: Exploring the Synergy

Nasser Ghasem-Aghaee1,2,*, Tuncer Ören3 and Levent Yilmaz4

1. INTRODUCTION

2. SIMULATION: HIGHLIGHTS

2.1. Stand-alone Simulation

2.2. Embedded Simulation

2.3. Other Perspectives

3. INTELLIGENCE, INTELLIGENT ENTITIES, AND AGENTS

3.1. Types of Intelligence

3.1.1. Entities

3.1.2. Context

3.3. Components

3.4. Agents

3.5. Software for Agents

4. SYNERGIES OF SIMULATION AND AGENTS

5. AGENT SIMULATION

5.1. Applications

5.2. Methodology

5.3. Software for Agent Simulation

6. AGENT-SUPPORTED SIMULATION

7. AGENT-MONITORED SIMULATION

8. SOME PROMISING RESEARCH AND DEVELOPMENT AREAS

CONCLUSION

NOTES

CONFLICT OF INTEREST

ACKNOWLEDGEMENTS

REFERENCES

Living with Digital Worlds: A Personal View of Artificial Intelligence

Helder Coelho*

2. ROAD MAP: TERRITORIES

3. MODELS

4. HUMAN INGENUITY

5. MECHANISMS

6. MACHINE LEARNING VARIETY

7. AGENT SHAPES

8. PREDICTING THE FUTURE

9. CHALLENGES

A Baseline for Nonlinear Bilateral Negotiations: The full results of the agents competing in ANAC 2014

Reyhan Aydoğan1,2,*, Catholijn M. Jonker2, Katsuhide Fujita3, Tim Baarslag4, Takayuki Ito5, Rafik Hadfi5 and Kohei Hayakawa5

2. ANAC 2014

2.1. ANAC 2014 Rules

2.2. Negotiation Scenarios

2.3. Competition Setup

3. ANAC 2014 AGENTS

3.1. AgentM [41]

3.2. AgentYK [42]

3.3. BraveCat [43]

3.4. DoNA [44]

3.5. E2Agent [45]

3.6. Gangster [46]

3.7. Group2Agent [47]

3.8. k-GAgent [49]

3.9. Sobut

3.10. WhaleAgent [51]

4. RESULTS OF ANAC 2014 COMPETITION

4.1. Qualifying Round.

4.2. Final Round

5. IN DEPTH EVALUATION OF ANAC 2014 AGENTS

5.1. Experimental Setup

5.2. Experiment Results

5.3. Effect of Domain Size

5.4. Effect of Constraint Size

5.5. Effect of Constraint-Issue Distribution

A Multi Agent Model for Reverse Perception Effect

Nuno Trindade Magessi* and Luis Antunes

2. EXPLAINING PERCEPTION

3. GOING AROUND THEORIES

3.1. Direct Perception

3.2. Perception in Action

3.3. Evolutionary Psychological And Perception

3.4. Structural Information Theory

3.5. Interface Theory

3.6. Empirical Perception Theory

4. THE GAP BETWEEN PERCEPTION AND REALITY

5. STIMULI AND PERCEPTIBLES

6. THE FILTER OF CULTURE IN PERCEIVING REALITY

7. INSIDE THE PERCEPTION PROCESS OF REALITY

8. AIDS AS A CASE STUDY

9. AIDS PERCEPTION SIMULATOR MODEL

10. EXPLORING OUTPUT RESULTS

11. DISCUSSING RESULTS

PART II: INTERACTION WITH HUMANS

Lexicon-based Sentiment Analysis in Persian

Mohammad Ehsan Basiri1,*, Nasser Ghasem-Aghaee2,3 and Ahmad Reza Naghsh-Nilchi2

2. RELATED WORK

2.1. Sentiment Analysis

2.2. Sentiment Analysis in Persian

2.3. Sentiment Strength Detection

3. PROPOSED SYSTEM

3.1. Normalization

3.1. Example 1:

3.2. Spelling Correction

3.2. Example 2:

3.3. Stemming

3.4. Sentence Splitting

3.5. Strength Detection

3.6. Score Aggregation

3.7. Research Questions

4. EXPERIMENTS

4.1. Datasets and Evaluation Metrics

4.2. Results and Discussions

4.2. Example 3:

REFERENCES.

The Age of the Connected World of Intelligent Computational Entities: Reliability Issues including Ethics, Autonomy and Cooperation of Agents

Tuncer Ören1,* and Levent Yilmaz2

1.1. Significance of the Problem

1.2. Motivating Scenarios

1.3. Organization of the Chapter

2. CONNECTED WORLD

2.1. Characteristics of the Connected World

2.2. Some Examples for Connected Entities

3. THE EVOLUTION OF THE CONNECTED WORLD

3.1. Hand Tools

3.2. Power Tools (Industrial Age)

3.3. Knowledge Processing Tools (Information Age/Informatics age)

3.3.1. Advancements in Knowledge Processing Tools

3.3.2. Advancements in Entities with Additional Knowledge Processing Abilities

3.4. Smart Tools and Intelligent Tools (Cybernetic Age)

3.5. Connected Tools (Connected World of Intelligent Computational Entities)

3.6. Superintelligence (Post-human Era?)

4. WHAT MIGHT GO WRONG IN THE AGE OF THE CONNECTED WORLD

4.1. Approaches for Basic Sources of Failures

4.2. Some Counterintuitive Views of Autonomy and Cooperation

4.2.1. Autonomy

4.2.2. Cooperation

4.3. Ethics and its Limitations (in Uncivilized Environments)

4.3.1. Design Strategies for Ethical Agents

P-UTADIS: A Multi Criteria Classification Method

Majid Esmaelian1,*, Hadi Shahmoradi1 and Fateme Nemati2

2. CLASSIFICATION

2.1. Review of Classification Techniques

2.1.1. Common Techniques in Data Classification Problems

2.1.2. Common Techniques in Data Classification with Ordinal Class

2.2. Multi Criteria Decision Aid Classification Technique

2.2.1. UTilities Additives DIScriminantes (UTADIS)

3. EXTENSION OF THE UTADIS WITH POLYNOMIAL AND GA-PSO ALGORITHM IN CLASSIFICATION

3.1. P-UTADIS vs. UTADIS

3.2. Preliminaries.

3.2.1. Genetic Algorithm (GA)

3.2.2. Particle Swarm Optimization Algorithm (PSO)

3.3. P-UTADIS Method

3.3.1. Methodology

3.3.2. Algorithm Steps

3.3.3. P-UTADIS performance on IRIS Data Set

3.3.4. Comparison of P-UTADIS Performance versus UTADIS

3.4. Experimental Study

3.4.1. Test Problems

3.4.2. Algorithms for Comparison

3.4.3. Results and Discussion

3.5. P-UTADIS Time Complexity

CONCLUDING REMARKS

PART III: APPLICATIONS

Artificial Intelligence Techniques for Credit Risk Management

Abdolreza Nazemi* and Konstantin Heidenreich

2. SUPPORT VECTOR REGRESSION MODELING FOR RECOVERY RATES

3. EMPIRICAL ANALYSIS

3.1. Selection of factors for modeling

3.2. Exploratory data analysis

4. EMPIRICAL MODELLING RESULTS

A Novel Task-Driven Sensor-Management Method in Multi-Object Filters Using Stochastic Geometry

Amirali K. Gostar*, Reza Hoseinnezhad and Alireza Bab-Hadiashar

1.1. Multi-Sensor Management

1.2. Sensor-Selection and Sensor-Control in Target Tracking Scenarios

2. BACKGROUND

2.1. Sensor Management Solution Framework

Prediction

Pre-Estimation

Pseudo-Measurements

Pseudo-Update

Objective Function

Decision Making

Update

3. ASSUMPTIONS

3.1. Single-Step Look-Ahead

3.2. Pseudo-Measurement Approximation

4. OBJECTIVE FUNCTION

4.1. Task-driven Approach

4.2. Information-driven Approach

5. COMMON OBJECTIVE FUNCTIONS IN SENSOR MANAGEMENT STUDIES

5.1. Rényi Divergence

5.2. The Posterior Expected Number of Targets

5.3. The Cardinality-Variance Based Objective Function

6. RANDOM FINITE SET BASED MULTI-TARGET FILTER

6.1. Multi-Target System Model.

6.2. Stochastic Model for Multi-Target State Evolution

6.3. Stochastic Model for Multi-Target State Measurement

6.4. Multi-Object Bayes Recursion

6.5. Poisson RFS

6.6. IID Cluster RFS

6.7. Bernoulli RFS

6.8. Multi-Bernoulli RFS

7. LABELED MULTI-BERNOULLI FILTER

7.1. Prediction

7.2. Update

7.3. Implementation

8. LABELED MULTI-BERNOULLI

8.1. Sensor-Control

8.2. Cost Function

8.3. Implementation

8.4. Computing the Cost

9. OSPA METRIC

10. NUMERICAL STUDIES

CONCLUSIONS AND FUTURE STUDIES

Parallel Processing in Holonic Systems

Imane Basiry1,* and Nasser Ghasem-Aghaee2

2. LITERATURE REVIEW

3. FIPA STANDARD AND AGENTS COMMUNICATION LANGUAGE

4. DESIGNING A HOLONIC MODEL

5. MODEL DESIGN AND ANALYSIS

5.1. First Level of the Model

I. First level: Structural Analysis

II. First Level: Behavioral Analysis

III. First Level: Matching the Model to an Airport Control Systems

IV. First Level: Matching the Model to Factory Control Systems

5.2. Second Level of the Model

I. Second Level: Structural Analysis

II. Second Level: Behavioral Analysis

III. Second Level: Matching the Model to an Airport Control System

IV. Second Level: Matching the Model to a Factory Control System

5.3. Third Level of the Model

I. Third Level: Structural Analysis

II. Third Level: Behavioral Analysis

III. Third Level: Matching the Model to Airport Control Systems

IV. Third Level: Matching the Model to Factory Control Systems

6. PREPARING THE MODEL FOR CRITICAL CONDITIONS

7. IMPLEMENTATION AND NUMERIC EVALUATION IN THE FACTORY TEST CASE

8. REVIEW OF PROPOSED MODEL FEATURES

CONCLUSIONS AND FUTURE RESEARCH DIRECTIONS

Robot-Assisted Language Learning: Artificial Intelligence in Second Language Acquisition.

Notes:

Includes bibliographical references at the end of each chapters and index.

Description based on online resource; title from PDF title page (ebrary, viewed October 14, 2017).

ISBN:

9781681085029

168108502X

OCLC:

1006411861