Secure Edge and Fog Computing Enabled AI for IoT and Smart Cities: Includes selected Papers from International Conference on Advanced Computing & ... Innovations in Communication and Computing)

Preface
Introduction
	Structure of the Book
	About This Book
	Key Aspects of the Book
	Target Audience
	References
Contents
About the Editors
Part I AI Enabled Smart City IoT System Using Edge/Fog Computing
	Multilevel Edge Computing System for Autonomous Vehicles
		1 Introduction
		2 V2X Technology Description
		3 The Advantage of Edge Computing Technology
		4 Model Description
		5 Analyze Modeling for the Environment VANET
		6 Conclusion
		References
	UAV-Based Edge Computing System for Smart City Applications
		1 Introduction
		2 Network Architecture Using MEC/SDN Technologies and UAVs as Edge Nodes
		3 Development of a Network Model with Edge and Cloud Computing Nodes
		4 Results of the Network Delay Measurement Experiment in the Cloud and Edge Computing Model in High and Low Network Load Scenarios
		5 Conclusion
		References
	Organization of Smart City Services Based on MicroserviceArchitecture
		1 Introduction
		2 Formulation of the Problem
		3 Methodology
			3.1 The Architecture of the Developed Service Organization Software
			3.2 Service IoTDM
			3.3 Smart Device Traffic Generator
			3.4 Statistics Service
			3.5 The General Architecture of the Developed Software
		4 Results and Discussion
			4.1 Results of Testing the Developed Model Without Load Distribution Between Microservices
			4.2 Results of Testing the Developed Model with Load Distribution Between Microservices
		5 Conclusion
		References
	Pseudo-Random Error-Correcting Codes in Network Coding
		1 Introduction
		2 Principle of Network Coding
		3 Error Control in Network Coding
		4 Using Binary Pseudo-Random Codes to Combat Errors in Network Coding
			4.1 Maximum Length Code
			4.2 Gold Code
			4.3 Decoding of MLC and Gold Code
			4.4 Network Coding with MLC and Gold Code
		5 Conclusion
		References
	Proactive Management in Smart City: Transport Convoys
		1 The Smart City Concept
		2 Consistency of Smart City Information Systems
		3 System Architecture for Proactive Control of Traffic Columns in Smart City
		References
	Federated Learning for Linux Malware Detection: An Experimental Study
		1 Introduction
		2 Related Works
		3 Federated Learning Approach for Linux Malware Detection
			3.1 Data Collection
			3.2 Data Preprocessing
			3.3 Training Model
			3.4 Model Evaluation
			3.5 Server
		4 Experiment
			4.1 Training Process
			4.2 Results
		5 Conclusions
		References
	Delay Prediction in M2M Networks Using the Deep LearningApproach
		1 Introduction
		2 Literature Review
		3 Problem Statement and System Modeling
		4 Simulation Results
		5 Conclusion
		References
	Energy-Efficient Beam Shaping in MIMO System Using Machine Learning
		1 Introduction
		2 Beam-Shaping App
		3 Conclusion
		References
	Channel Cluster Configuration Selection Method for IEEE 802.11 Network Planning
		1 Introduction
		2 Problem Statement
		3 Channel Configuration Selection Method
		4 Conclusions
		References
	Service Migration Algorithm for UAV Recharge Zones in Future 6G Network
		1 Introduction
		2 Software-Defined Networks
		3 Flying Software-Defined Network Architecture
		4 Basic Architecture Elements
		5 The Main Functions Performed in the UAV Cluster
		6 The Proposed Algorithm
		7 Conducted Experiment
		8 Conclusion
		References
	FedBA: Non-IID Federated Learning Framework in UAV Networks
		1 Introduction
		2 Related Works
			2.1 Privacy-Preserving UAV Image Recognition
			2.2 Federated Learning on Non-IID Data
		3 Methodology
			3.1 Federated Learning
			3.2 Proposed Algorithm
		4 Experiment
			4.1 Experiment Setup
			4.2 Training Details
			4.3 Experiment Result
		5 Conclusion
		References
Part II Fog/Edge Computing Security Issues
	Big Data Analytics for Secure Edge-Based Manufacturing Internet of Things (MIoT)
		1 Introduction
		2 Data Analytics in Manufacturing
		3 Data Analytics
		4 Data Acquisition
		5 Anomaly Detection
		6 Data Analytics in MIoT
		7 Characteristics of MIoT
		8 Comparative Analysis: MIoT vs. CIoT
			8.1 Data Acquisition
			8.2 Data Processing and Storage
			8.3 Data Analytics
		9 Necessities of Big Data Analytics
			9.1 Improving Processes and Production in Factories
			9.2 Reducing Downtime on Computers
			9.3 Product Quality Management
			9.4 Enhancing Productivity in the Supply Chain
		10 Benefits of Big Data Analytics for MIoT
		11 Cost Reduction
		12 Fraud Detection
		13 Product Quality
		14 Supply Chain Optimization
		15 Demand Forecasting
		16 Helps Increase the Businesses\' ROI
		17 Advantages to Manufacturing Companies
		18 Analysis Depth
		19 Security
		20 Improving Factory Operations and Production
		21 Reducing Machine Downtime
		22 Improving Product Quality
		23 Enhancing Supply Chain Efficiency
		24 Monitoring Manufacturing Process
		25 Reduction in Energy Consumption and Energy Costs
		26 Reduction of Scrap Rate
		27 Challenges of Big Data Analytics for MIoT
		28 Easing Security Concerns
		29 Overcoming Connectivity Issues
		30 Data Acquisition
			30.1 Data Representation and Transmission
		31 Data Preprocessing and Storage
			31.1 Data Integration
			31.2 Redundancy Reduction
			31.3 Data Cleaning and Data Compression
			31.4 Reliability and Persistence of Data Storage
			31.5 Scalability
			31.6 Efficiency
		32 Data Analytics
			32.1 Data Temporal and Spatial Correlation
			32.2 Efficient Data Mining Schemes
			32.3 Privacy and Security
		33 Conclusion
		References
	Artificial Intelligence-Based Secure Edge Computing Systems for IoTDs and Smart Cities: A Survey
		1 Introduction
			1.1 Chapter Organization
		2 Edge Computing
			2.1 Security Issues in EC
		3 AI Techniques for Securing EC
			3.1 Fuzzy Logic-Based Algorithms
			3.2 Learning-Based Algorithms
		4 AI in Addressing Security Issues in EC
			4.1 FLAs for Security and Privacy in EC
			4.2 LBAs for Security and Privacy Issues in EC
		5 Discussion and Future Research Trends
			5.1 Discussion
			5.2 Future Research Trends
				5.2.1 From EC Perspective
				5.2.2 From AI Algorithms Perspective
		6 Conclusions
		References
	Machine Learning Techniques for Secure Edge SDN
		1 Introduction
		2 Background
			2.1 SDN Architecture
			2.2 SDN Benefits
		3 Security Threats in SDN
		4 Machine Learning for Secure SDN
		5 Conclusion and Future Directions
		References
	Machine Learning –Based Identity and Access Management for Cloud Security
		1 Introduction
			1.1 Motivation
			1.2 Comparison
		2 Proposed System Architecture
			2.1 Clients
			2.2 Cloud Service Provider (CSP)
			2.3 Multi-cloud Database
			2.4 Third-Party Auditor (TPA)
		3 Revolutionizing Authentication: A Deep Dive into Federated Identity Transposition
		4 Platform for Client Authentication Use of Provisioning in Cloud Computing Structure
		5 Results and Discussion
			5.1 Dataset Description
			5.2 Machine Learning Model Evaluation
			5.3 Network Throughput
		6 Conclusions, Future Recommendations, and Research Implication
			6.1 Future Work
			6.2 Implications of the Study
		References
	Spatial Data of Smart Cities: Trust
		1 Spatial Data: Smart City
		2 Spatial Data: Confidence Assessment
		3 Spatial Data: Ensuring Trust
		References
	Smart City Infrastructure Projects: Spatial Data of Risks
		1 Infrastructure Projects in Smart City
		2 Infrastructure Projects Risks in Smart City
		References
	A Comparative Analysis of Blockchain-Based Authentication Models for IoT Networks
		1 Introduction
		2 Authentication Methods in IoT Networks
		3 Blockchain Concept
			3.1 Role of Smart Contract
			3.2 Analysis of Blockchain-Based Authentication Models for IoT Networks
		4 Conclusions
		References
	Development of Determining a Wireless Client Location Method in the IEEE 802.11 Network to Ensure the IT Infrastructure Security
		1 Introduction
			1.1 General Principles of a Wireless Client Positioning in an IEEE 802.11 Network
			1.2 Existing Trilateration Methods Based on RSSI
		2 Problematics
		3 Materials and Methods
		4 Results
			4.1 Wireless Client Positioning Method
			4.2 Placement of Sensors on the Object
			4.3 Object\'s Map Creation and Power Map Generation
			4.4 Saving Data to a Database
			4.5 Client Device Discovery
			4.6 Wireless Client Positioning
		5 Discussion
			5.1 Operation Checking of the Wireless Client Location Method
		6 Conclusion
		References
Index