Distributed Artificial Intelligence: A Modern Approach

Cover
Half Title
Series Page
Title Page
Copyright Page
Table of Contents
Preface
Editors
Contributors
Chapter 1 Distributed Artificial Intelligence
	1.1 Introduction
	1.2 Why Distributed Artificial Intelligence?
	1.3 Characteristics of Distributed Artificial Intelligence
	1.4 Planning of DAI Multi-Agents
	1.5 Coordination among Multi-Agents
		1.5.1 Forestalling Mobocracy or Confusion
		1.5.2 Meeting Overall Requirements
		1.5.3 Distributed Skill, Resources, and Data
		1.5.4 Dependency among the Agents
		1.5.5 Efficiency
	1.6 Communication Modes among the Agents
	1.7 Categories of RPC
	1.8 Participation of Multi-Agents
		1.8.1 Fully Cooperative Architecture
		1.8.2 Partial Cooperative Architecture
	1.9 Applications of DAI
		1.9.1 Electricity Distribution
		1.9.2 Telecommunications Systems
		1.9.3 Database Technologies for Service Order Processing
			1.9.3.1 Concurrent Engineering
			1.9.3.2 Weather Monitoring
			1.9.3.3 Intelligent Traffic Control
	1.10 Conclusion
	References
Chapter 2 Intelligent Agents
	2.1 Introduction
	2.2 Need for Evolving Agents in Evolutionary Software Systems
		2.2.1 Change of Requirements
		2.2.2 Need for an Evolving System
		2.2.3 Software System
		2.2.4 Evolving Software System
	2.3 Agents
		2.3.1 Evolving Agents
		2.3.2 Agent Architecture
		2.3.3 Application Domain
			2.3.3.1 Types of Agents
	References
Chapter 3 Knowledge-Based Problem-Solving: How AI and Big Data Are Transforming Health Care
	3.1 Introduction
	3.2 The Role of AI, Big Data, and IoT in Health Care
	3.3 Image-Based Diagnosis
	3.4 Big Data Analytics Process Using Machine Learning
	3.5 Discussion
	3.6 Conclusion
	References
Chapter 4 Distributed Artificial Intelligence for Document Retrieval
	4.1 Introduction
	4.2 Proposed Research
		4.2.1 Improving Precision
	4.3 General-Purpose Ranking
	4.4 Structure-Weighted Ranking
	4.5 The Structure-Weighted/Learned Function
	4.6 Improving Recall and Precision
		4.6.1 Stemming
		4.6.2 Relevance Feedback
		4.6.3 Thesaurus
	4.7 Preliminary Results
	4.8 Scope for Distributed AI in This Process
	4.9 Benefits of Decentralized Search Engines
	4.10 Discussion
	4.11 Conclusion
	References
Chapter 5 Distributed Consensus
	5.1 Introduction
	5.2 Nakamoto Consensus
		5.2.1 Nakamoto Consensus Working
			5.2.1.1 Proof of Work
			5.2.1.2 Block Selection
			5.2.1.3 Scarcity
			5.2.1.4 Incentive Structure
		5.2.2 Security of Bitcoin
		5.2.3 The PoW Algorithm
		5.2.4 Proof of Stake
		5.2.5 Proof of Burn
		5.2.6 Difficulty Level
		5.2.7 Sybil Attack
			5.2.7.1 Eclipse Attack
		5.2.8 Hyperledger Fabric: A Blockchain Development
	5.3 Conclusions and Discussions
	References
Chapter 6 DAI for Information Retrieval
	6.1 Introduction
	6.2 Distributed Problem-Solving
	6.3 Multiagents
	6.4 A Multiagent Approach for Peer-to-Peer-Based Information Recoupment Systems
		6.4.1 A Mediator-Free Framework
		6.4.2 Agent-View Algorithm
		6.4.3 Distributed Search Algorithms
	6.5 Blackboard Model
	6.6 DIALECT 2: An Information Recoupment System
		6.6.1 The Control in Blackboard Systems
		6.6.2 Control in DIALECT 2
			6.6.2.1 The Linguistic Parser
			6.6.2.2 The Reformation Module
	6.7 Analysis and Discussion
	6.8 Conclusion
	References
Chapter 7 Decision Procedures
	7.1 Motivation
	7.2 Introduction
	7.3 Distributed Artificial Intelligence
	7.4 Applying Artificial Intelligence to Decision-Making
	7.5 Automated Decision-Making by AI
		7.5.1 Impact of Automated Decision System
		7.5.2 Forms of Automated Decision System
		7.5.3 Application of Automated Decision System
		7.5.4 Cyber Privacy Concerns
		7.5.5 Discussion and Future Impact
	7.6 Cooperation in Multi-Agent Environments
		7.6.1 Notations and Workflow
		7.6.2 Action Independence
	7.7 Game Theory Scenario
	7.8 Data-Driven or AI-Driven
		7.8.1 Human Judgment
		7.8.2 Data-Driven Decision-Making
		7.8.3 Working of Data-Driven Decisions
		7.8.4 AI-Driven Decision-Making
		7.8.5 Leveraging Human and AI-Driven Workflows Together
	7.9 Calculative Rationality
	7.10 Meta-Level Rationality and Meta-Reasoning
	7.11 The Role of Decision Procedures in Distributed Decision-Making
	7.12 Advantages of Distributed Decision-Making
	7.13 Optimization Decision Theory
		7.13.1 Multi-Level (Hierarchical) Algorithms
	7.14 Dynamic Programming
	7.15 Network Flow
	7.16 Large-Scale Decision-Making (LSDM)
		7.16.1 Key Elements in an LSDM Model
	7.17 Conclusion
	Reference
Chapter 8 Cooperation through Communication in a Distributed Problem-Solving Network
	8.1 Introduction
	8.2 Distributed Control System
		8.2.1 Design Decisions
		8.2.2 Host Node Software Communication
		8.2.3 Convolutional Software Node Network
		8.2.4 Assessment of Distributed Situation
		8.2.5 Computer-Aided Control Engineering (CACE)
		8.2.6 Knowledge Base
		8.2.7 Training Dataset
	8.3 Motivation and Development of the ICE Architecture
		8.3.1 History of ICE Model
			8.3.1.1 Operators on Information States
			8.3.1.2 Relations to Observable Quantum Mechanics
			8.3.1.3 The Influence of Sociology and Intentional States
		8.3.2 Requirements of a Theory of Animal and Robotics Communication
	8.4 A Brief Conceptual History of Formal Semantics
		8.4.1 Tarski Semantics
		8.4.2 Possible World Semantics
		8.4.3 Semantics of Temporal Logic
		8.4.4 Limitations of Kripke Possible World Semantics
	8.5 Related Work
	8.6 Dynamic Possible World Semantics
	8.7 Situation Semantics and Pragmatics
	8.8 Modeling Distributed AI Systems as a Distributed Goal Search Problem
	8.9 Discussion
	8.10 Conclusion
	References
Chapter 9 Instantiating Descriptions of Organizational Structures
	9.1 Introduction
		9.1.1 Example of Organizational Structure
		9.1.2 Purpose
		9.1.3 Components
			9.1.3.1 Obligations
			9.1.3.2 Assets
			9.1.3.3 Information
			9.1.3.4 Apparatuses
			9.1.3.5 Experts and Subcontractors
		9.1.4 Relation between Components
			9.1.4.1 Correspondence
			9.1.4.2 Authority
			9.1.4.3 Area, Proximity, and so on
		9.1.5 Description of the Organizational Structures with EFIGE
		9.1.6 The Constraint Solution Algorithm
			9.1.6.1 Requirement Propagation
			9.1.6.2 Imperative Utility
	9.2 Comparative Study of Organization Structure
	9.3 Conclusion
	References
Chapter 10 Agora Architecture
	10.1 Introduction
		10.1.1 Characteristics of System for which Agora Is Useful
	10.2 Architecture of Agora
	10.3 Agora’s Virtual Machine
		10.3.1 Element Cliques (EC)
		10.3.2 Knowledge Source (KS)
		10.3.3 Mapping of KS into Mach layer
		10.3.4 Frameworks
			10.3.4.1 Typical Framework Tools
			10.3.4.2 Knowledge Base: CFrame
	10.4 Examples of Systems Built Using Agora
		10.4.1 Intelligent Transport System (ITS)
			10.4.1.1 Architecture of Agora ITS Framework
			10.4.1.2 Agora ITS Applications
		10.4.2 CMU Speech Recognition System
	10.5 Application of Agora as a Minimal Distributed Protocol for E-Commerce
		10.5.1 Basic Protocol
		10.5.2 Accounts
		10.5.3 Transactions
		10.5.4 Properties of Agora Protocol
			10.5.4.1 Minimal
			10.5.4.2 Distribution
			10.5.4.3 Authentication
			10.5.4.4 Security
		10.5.5 Enhanced Protocol to Regulate Fraud
			10.5.5.1 New Message
			10.5.5.2 Batch Processing
			10.5.5.3 Selection of Parameter
			10.5.5.4 Online Arbitration
	References
Chapter 11 Test Beds for Distributed AI Research
	11.1 Introduction
	11.2 Background
	11.3 Tools and Methodology
		11.3.1 MACE
			11.3.1.1 MACE System
		11.3.2 Actor Model
		11.3.3 MICE Testbed
		11.3.4 ARCHON
			11.3.4.1 Multiagent Environment
			11.3.4.2 The ARCHON Architecture
		11.3.5 Distributed Vehicle Monitoring Testbed (DVMST)
		11.3.6 AGenDA Testbed
			11.3.6.1 Architectural Level
			11.3.6.2 System Development Level
			11.3.6.3 Other Testbeds for DAI
	11.4 Conclusion
	References
Chapter 12 Real-Time Framework Competitive Distributed Dilemma
	12.1 Introduction
	12.2 Real-Time Route Guidance Distributed System Framework
	12.3 Experts Cooperating
	12.4 A Distributed Problem-Solving Perspective
	12.5 Caveats for Cooperation
	12.6 Task Sharing
	12.7 Result-Sharing
	12.8 Task-Sharing and Result-Sharing: A Comparative Analysis
	12.9 Conclusion
	References
Chapter 13 Comparative Studied Based on Attack Resilient and Efficient Protocol with Intrusion Detection System Based on Deep Neural Network for Vehicular System Security
	13.1 Introduction
	13.2 Related Work
	13.3 Background
		13.3.1 Processing Phase
		13.3.2 Training Phase
	13.4 Intrusion Detection System
	13.5 IDS with Machine Learning
	13.6 Proposed Technique
		13.6.1 Proposed Deep Neural Network Intrusion Detection System
		13.6.2 Training the Deep Neural Network Structure
			13.6.2.1 ANN Parameters
			13.6.2.2 Input Layer’s Neurons
			13.6.2.3 Hidden Layer’s Neurons
			13.6.2.4 Output Layer’s Neurons
			13.6.2.5 Transfer Function
	13.7 Simulation Parameters
		13.7.1 Average End-to-End Delay
		13.7.2 Average Energy Consumption
		13.7.3 Average Network Throughput
		13.7.4 Packet Delivery Ratio (PDR)
	13.8 Conclusion
	References
Chapter 14 A Secure Electronic Voting System Using Decentralized Computing
	14.1 Introduction
	14.2 Background and Motivation
		14.2.1 Secret Ballot
		14.2.2 One Man, One Vote
		14.2.3 Voter Eligibility
		14.2.4 Transparency
		14.2.5 Votes Accurately Recorded and Counted
		14.2.6 Reliability
	14.3 Literature Survey
	14.4 Main Contributions
		14.4.1 Variables of the Contract
		14.4.2 Preparing the Ballot
		14.4.3 Vote Counting
	14.5 E-Voting and Blockchain
		14.5.1 Cryptography
	14.6 Use of Blockchain in Voting System
	14.7 Result and Analysis
	14.8 Conclusion
	References
Chapter 15 DAI for Document Retrieval
	15.1 Introduction
	15.2 Artificial Intelligence
		15.2.1 Some Real-Life Examples of AI
		15.2.2 Advantages of AI
		15.2.3 Information Retrieval
		15.2.4 Information Retrieval Assessment
	15.3 Distributed Artificial Intelligence
		15.3.1 Introduction to Distributed Artificial Intelligence
		15.3.2 Distributed Artificial Intelligence Tools
		15.3.3 Complete Document and Document Interchange Format
		15.3.4 Data Network Architecture for Distributed Information Retrieval
		15.3.5 Types of DAI
		15.3.6 Challenges in Distributed AI
		15.3.7 The Objectives of Distributed Artificial Intelligence
		15.3.8 Areas in Which DAI Is Implemented
		15.3.9 Software Agents
	15.4 Conclusion
	References
Chapter 16 A Distributed Artificial Intelligence: The Future of AI
	16.1 Introduction
	16.2 Background and Challenges of AI
		16.2.1 Hardware for AI
		16.2.2 Platform and Programming Languages for AI
		16.2.3 Challenges of AI
	16.3 Components and Proposed Environment of Distributed AI
		16.3.1 Graphical Processing Unit (GPU)
		16.3.2 Storage
		16.3.3 High-Speed Reliable Network
		16.3.4 Proposed Distributed Environment of DAI
	16.4 Application of Distributed AI
		16.4.1 Healthcare Systems
		16.4.2 Agriculture Systems
		16.4.3 E-Commerce
	16.5 Future Scope
	16.6 Conclusion
	References
Chapter 17 Analysis of Hybrid Deep Neural Networks with Mobile Agents for Traffic Management in Vehicular Adhoc Networks
	17.1 Introduction
	17.2 Network Model
	17.3 Traffic Management Model
		17.3.1 Mobile Agent Unit
		17.3.2 Infrastructure Unit
	17.4 Performance Evaluation
	17.5 Conclusion
	References
Chapter 18 Data Science and Distributed AI
	18.1 Introduction
	18.2 Inspiration
	18.3 Distributed Sensor Networks
	18.4 Associations Tested
		18.4.1 Human-Based Network Experiments
		18.4.2 Examinations with Machine Networks
	18.5 An Abstract Model for Problem-Solving
		18.5.1 The HSII Organization: A Production System Approach
		18.5.2 Hearsay-II Multiprocessing Mechanisms
		18.5.3 Nearby Context
		18.4.4 Data Integrity
		18.5.5 Contextual Analysis
		18.5.6 HSII Multiprocessor Performance Analysis through Simulation
		18.5.7 The HSII Speech Understanding System: The Simulation Configuration
	18.6 Hierarchical Distribution of Work
	18.7 Agora
	18.8 Exploratory Outcomes for Image Processing
	18.9 Summary and Conclusions
	References
Index