Green Internet of Things and Machine Learning: Towards a Smart Sustainable World

Cover
Half-Title Page
Series Page
Title Page
Copyright Page
Contents
Preface
1 G-IoT and ML for Smart Computing
	1.1 Introduction
	1.2 Machine Learning
		1.2.1 Difference Between Artificial Intelligence and Machine Learning
		1.2.2 Types of Machine Learning
			1.2.2.1 Supervised Learning
			1.2.2.2 Unsupervised Learning
			1.2.2.3 Semi-Supervised Learning
			1.2.2.4 Reinforcement Learning
	1.3 Deep Learning
	1.4 Correlation Between AI, ML, and DL
	1.5 Machine Learning–Based Smart Applications
		1.5.1 Supervised Learning–Based Applications
			1.5.1.1 Email Spam Filtering
			1.5.1.2 Face Recognition
			1.5.1.3 Speech Recognition
			1.5.1.4 Handwriting Recognition
			1.5.1.5 Intrusion Detection
			1.5.1.6 Data Center Optimization
		1.5.2 Unsupervised Learning–Based Applications
			1.5.2.1 Social Network Analysis
			1.5.2.2 Medical Records
			1.5.2.3 Speech Activity Detection
			1.5.2.4 Analysis of Cancer Diagnosis
		1.5.3 Semi-Supervised Learning–Based Applications
			1.5.3.1 Mobile Learning Environments
			1.5.3.2 Computational Advertisement
			1.5.3.3 Sentiment Analysis
		1.5.4 Reinforcement Learning–Based Applications
			1.5.4.1 Traffic Forecasting Service
			1.5.4.2 Computer Games
			1.5.4.3 Machinery Applications
			1.5.4.4 Stock Market Analysis
	1.6 IoT
	1.7 Green IoT
	1.8 Green IoT–Based Technologies
		1.8.1 Identification
		1.8.2 Sensing
		1.8.3 Communication Technologies
		1.8.4 Computation
		1.8.5 Services
		1.8.6 Semantic
	1.9 Life Cycle of Green IoT
	1.10 Applications
		1.10.1 Industrial Automation
			1.10.1.1 Machine to Machine Communications
			1.10.1.2 Plant Monitoring
		1.10.2 Healthcare
			1.10.2.1 Real-Time Tracking
			1.10.2.2 Identification
			1.10.2.3 Smart Data Collection
			1.10.2.4 Smart Sensing
		1.10.3 Environment Monitoring
			1.10.3.1 Agriculture
			1.10.3.2 Smog Control
			1.10.3.3 Waste Management
			1.10.3.4 Smart Water
		1.10.4 Suburban Sector
			1.10.4.1 Smart Buildings
			1.10.4.2 Garbage Collection
			1.10.4.3 Water Sensors
			1.10.4.4 Smart Metering
		1.10.5 People and Goods Transportation
			1.10.5.1 Smart Parking
			1.10.5.2 Smart Traffic Congestion Detection
		1.10.6 Marketing and Shipment Management
			1.10.6.1 Smart Logistics/Shipment
			1.10.6.2 Managing Quality
		1.10.7 Recycling
	1.11 Challenges and Opportunities for Green IoT
		1.11.1 Architecture of Green IoT
		1.11.2 Green Infrastructure
		1.11.3 Green Spectrum Management
		1.11.4 Green Communication
		1.11.5 Green Security and Servicing Provisioning
	1.12 Future of G-IoT
	1.13 Conclusion
	References
2 Machine Learning–Enabled Techniques for Reducing Energy Consumption of IoT Devices
	2.1 Introduction
		2.1.2 Motivation
		2.1.3 Methodology
	2.2 Internet of Things (IoT)
	2.3 Empowering Tools
		2.3.1 Sensor Devices
		2.3.2 Actuators
		2.3.3 Communication Technologies
		2.3.4 IoT Data and Computing
			2.3.4.1 Distributed Computing
			2.3.4.2 Fog Computing
	2.4 IoT in the Energy Sector
		2.4.1 IoT and Energy Generation
		2.4.2 Smart Metropolises
		2.4.3 Smart Grid
		2.4.4 Smart Buildings Structures
		2.4.5 Powerful Use of Energy in Industry
		2.4.6 Insightful Transportation
	2.5 Difficulties of Relating IoT
		2.5.1 Energy Consumption
		2.5.2 Synchronization of IoT With Subsystems
		2.5.3 Client Privacy
		2.5.4 Security Challenges
		2.5.5 IoT Standardization and Architectural Concept
	2.6 Future Trends
		2.6.1 IoT and Blockchain
		2.6.2 Artificial Intelligence and IoT
		2.6.3 Green IoT
	2.7 Conclusion
	References
3 Energy-Efficient Routing Infrastructure for Green IoT Network
	3.1 Introduction
	3.2 Overview of IoT
	3.3 Perspectives of Green Computing: Green IoT
		3.3.1 Green Radio-Frequency
		3.3.2 Green Wireless Sensor Network
		3.3.3 Green Data Centers
		3.3.4 Green Cloud Computing
		3.3.5 Green Edge Computing
		3.3.6 Green M2M
		3.3.7 Green Information and Communication Technology (ICT) Principles
	3.4 Routing Protocols for Heterogeneous IoT
		3.4.1 Energy-Harvesting-Aware Routing Algorithm
		3.4.2 Priority-Based Routing Algorithm
		3.4.3 Cluster-Based Routing Algorithm
		3.4.4 Bioinspired Routing Protocols
	3.5 Machine Learning Application in Green IoT
	3.6 Conclusion
	References
4 Green IoT Towards Environmentally Friendly, Sustainable and Revolutionized Farming
	4.1 Introduction
		4.1.1 Lifecycle of Agriculture
		4.1.2 An Overview on How Machine Learning Works
	4.2 How is Machine Learning Used in Agricultural Field?
		4.2.1 Crop Management
		4.2.2 Livestock Management
			4.2.2.1 Animal Welfare
			4.2.2.2 Livestock Production
		4.2.3 Literature Review of Research Papers That Used Machine Learning in Agriculture
	4.3 What is IoT? How Can IoT Be Applied in Agriculture?
		4.3.1 Monitoring Climate Conditions
		4.3.2 Greenhouse Automation
		4.3.3 Crop Management
		4.3.4 Cattle Monitoring and Management
		4.3.5 Precision Farming and Agricultural Drones
		4.3.6 Contract Farming
	4.4 What is Green IoT and Use of Green IoT in Agriculture?
	4.5 Conclusion: Risks of Using G-IoT in Agriculture
	References
5 CIoT: Internet of Green Things for Enhancement of Crop Data Using Analytics and Machine Learning
	5.1 Introduction
	5.2 Motivation
	5.3 Review of Literature
	5.4 Problem with Traditional Approach
	5.5 Tool Requirement
		5.5.1 Arduino UNO
		5.5.2 Humidity Sensor
		5.5.3 Relay
		5.5.4 DC Motor
		5.5.5 pH Sensor and CO
		Sensor
	5.6 Methodology
	5.7 Conclusion
	References
6 Smart Farming Through Deep Learning
	6.1 Introduction
	6.2 Literature Review
	6.3 Deep Learning in Agriculture
		6.3.1 Feedforward Neural Network
			6.3.1.1 Single-Layer Perceptron
			6.3.1.2 Multi-Layer Perceptron
		6.3.2 Recurrent Neural Network
		“St=f(Uxt+Wst-1)”
		6.3.3 Radial Basis Function Neural Network
		6.3.4 Kohenen Self Organizing Neural Network
		6.3.5 Modular Neural Network
	6.4 Smart Farming
	6.5 Image Analysis of Agricultural Products
	6.6 Land-Quality Check
		6.6.1 Nitrogen Status
		6.6.2 Moisture Content
	6.7 Arduino-Based Soil Moisture Reading Kit
		6.7.1 Wastage of Water
		6.7.2 Plants Dying Due to Over Watering
		6.7.3 Expensive Product
	6.8 Conclusion
	6.9 Future Work
	References
7 Green IoT and Machine Learning for Agricultural Applications
	7.1 Introduction
	7.2 Green IoT
		7.2.1 Components of GAHA
		7.2.2 Applications of Green IoT in Agriculture
			7.2.2.1 Livestock Tracking and Geofencing
			7.2.2.2 Fisheries
			7.2.2.3 Smart Crops
			7.2.2.4 G-Drones
			7.2.2.5 Weeding Robots
			7.2.2.6 Machine Navigation
			7.2.2.7 Harvesting Robots
		7.2.3 Green IoT Security Solutions for Agriculture
			7.2.3.1 Precision Technology
			7.2.3.2 Facility Agriculture
			7.2.3.3 Contract Farming
	7.3 Machine Learning
		7.3.1 Applications of Machine Learning in Agriculture
			7.3.1.1 Species Breeding and Species Selection
			7.3.1.2 Species Recognition
			7.3.1.3 Weed Detection
			7.3.1.4 Crop Quality
			7.3.1.5 Disease Detection
			7.3.1.6 Yield Prediction
			7.3.1.7 Field Conditions Management
			Xn
			x
			xmin
			xmax xmin
			rmax rmin) Tmin
			7.3.1.8 Plant Seedling Classification
			7.3.1.9 Greenhouse Simulation
	7.4 Conclusion
	References
8 IoT-Enabled AI-Based Model to Assess Land Suitability for Crop Production
	8.1 Introduction
	8.2 Literature Survey
		8.2.1 Internet of Things in Field of Agriculture
		8.2.2 Machine Learning With Internet of Things in Agriculture
		8.2.3 Deep Learning With Internet of Things in Agriculture
	8.3 Conclusion
	References
9 Green Internet of Things (GIoT): Agriculture and Healthcare Application System (GIoT-AHAS)
	9.1 Introduction
	9.2 Relevant Work and Research Motivation for GIoT-AHAS
		9.2.1 Ubiquitous Computing
		9.2.2 Ubiquitous Agriculture and Healthcare Application Requirement
		9.2.3 Green Cloud Computing
		9.2.4 Green IoT Agriculture and Healthcare Applications (GIoT-AHAS)
			9.2.4.1 GIoT-AHAS Architecture
			9.2.4.2 GIoT-AHAS Requirements
			9.2.4.3 Applying Green Internet of Things to Agriculture and Healthcare System
		9.2.5 Green IoT for AHAS (GIoT-AHAS)
			9.2.5.1 GIoT to AHAS Components
		9.2.6 Green Digital Wireless Sensor Networks
		9.2.7 Green Cloud Computing
		9.2.8 Green Machine-to-Machine
		9.2.9 Green Data Processing Center (GDPC)
	9.3 Conclusion
	References
10 Green IoT for Smart Transportation: Challenges, Issues, and Case Study
	10.1 Introduction
	10.2 Challenges of IoT
		10.2.1 Green IoT
			10.2.1.1 Hardware-Based
			10.2.1.2 Software-Based
			10.2.1.3 Policy-Based
			10.2.1.4 Awareness-Based
			10.2.1.5 Habitual-Based
			10.2.1.6 Recycling-Based
	10.3 Green IoT Communication Components
		10.3.1 Green Internet Technologies
		10.3.2 Green RFID Tags
		10.3.3 Green WSN
		10.3.4 Green Cloud Computing
		10.3.5 Green DC
		10.3.6 Green M2M
	10.4 Applications of IoT and Green IoT
		10.4.1 Green IoT in Transportation
	10.5 Issues of Concern
		10.5.1 End User Viewpoints
		10.5.2 Energy Conservation
		10.5.3 Data Security and Privacy
		10.5.4 Preserving Contextual Data
		10.5.5 Bandwidth Availability and Connectivity
	10.6 Challenges for Green IoT
		10.6.1 Standard Green IoT Architecture
		10.6.2 Security and Quality of Service
		10.6.3 Data Mining and Optimization
		10.6.4 Various Traffic Management and Scheduling-Based Smart Public Transport Solutions
		10.6.5 Scheduling and Admission Control for Independent Vehicle Public Transportation System
		10.6.6 Impacts on Public Transportation Management by Applying AVLs
		10.6.7 Lisbon and Portugal’s Bus Ride Study and Prediction of Transport Usage
		10.6.8 Smart Assistance for Public Transport System
	10.7 Green IoT in Smart Transportation: Case Studies
		10.7.1 Smart Traffic Signal
			10.7.1.1 Description
			10.7.1.2 Application
			10.7.1.3 Advantages
			10.7.1.4 Disadvantages
		10.7.2 Cloud-Based Smart Parking System
			10.7.2.1 Hardware—Car Parks CP1 and CP2
			10.7.2.2 Smart Airport Management System
			10.7.2.3 Intelligent Vehicle Parking System
			10.7.2.4 IoT-Based Smart Vehicle Monitoring System
	10.8 Conclusion
	References
11 Green Internet of Things (IoT) and Machine Learning (ML): The Combinatory Approach and Synthesis in the Banking Industry
	11.1 Introduction
	11.2 Research Objective
	11.3 Methodology
	11.4 Result and Discussion
		11.4.1 Internet of Thing (IoT) in the Banking Industry
			11.4.1.1 Internet of Things Facilitating Banking
			11.4.1.2 Benefits of Internet of Things (IoT) in Banking
			11.4.1.3 Other Benefits Benefits of the Internet of Thing (IoT) in Banking
		11.4.2 Artificial Intelligence and Machine Learning in Banking
			11.4.2.1 Significant Roles of Artificial Intelligence and Machine Learning in Banking and Finance
			11.4.2.2 Machine Learning for Safe Bank Transactions
		11.4.3 Application of Machine Learning in Banking will Expand in 2021
		11.4.4 Technologies that Can Be Adopted for Reducing Carbon Footprints
			11.4.4.1 Green Internet of Things (Green IoT)
			11.4.4.2 Green Cloud Computing Technology
			11.4.4.3 Green Data Centre (GDC) Technology
	11.5 Conclusion
	References
12 Green Internet of Things (G-IoT) Technologies, Application, and Future Challenges
	12.1 Introduction
	12.2 The Internet of Thing (IoT)
		12.2.1 How IoT Works
		12.2.2 Evolution of Internet of Things
	12.3 Elements of IoT
	12.4 The Green IoT: Overview
	12.5 Green IoT Technologies
		12.5.1 Green RFID Tags
		12.5.2 Green Sensing Networks
		12.5.3 Green Internet Technologies
	12.6 Green IoT Applications
		12.6.1 Smart Homes
		12.6.2 Modern Automation
		12.6.3 Smart Healthcare
		12.6.4 Keen Grid
		12.6.5 Smart City
		12.6.6 Green Cloud Computing Technology
	12.7 IoT in 5G Wireless Technologies
		12.7.1 Internet of Things and 5G: The Future of 5G Communications
			12.7.1.1 5G and IoT: The Possibilities
			12.7.1.2 5G and Business IoT
	12.8 Internet of Things in Smart City
		12.8.1 Physical Experiences of Smart Cities Around the World
			12.8.1.1 In Netherlands (Amsterdam)
			12.8.1.2 In France (Nice)
			12.8.1.3 Padova (Italy)
	12.9 Green IoT Architecture for Smart Cities
		12.9.1 Perception Layer
			12.9.1.1 Smart City Sensor Layer
		12.9.2 Network Layer
			12.9.2.1 Cloud Services Layer
		12.9.3 Application Layer
			12.9.3.1 Data Collection Layer
			12.9.3.2 Data Processing Layer
	12.10 Advantages and Disadvantages of Green IoT
		12.10.1 Advantages of Green IoT
		12.10.2 Disadvantages of Green IoT
	12.11 Opportunities and Challenges
	12.12 Future of Green IoT
	12.13 Conclusion
	References
Index