Cloud Computing Technologies for Smart Agriculture and Healthcare (Chapman & Hall/CRC Cloud Computing for Society 5.0)

Cover
Half Title
Series Page
Title Page
Copyright Page
Contents
Preface
Editors
Contributors
Section I: Cloud Management
1. Virtualization Technology for Cloud-Based Services
	1.1 Cloud Computing Overview
		1.1.1 Features of Cloud Computing
		1.1.2 Impact of Cloud Computing on Business and Its Ecosystems
		1.1.3 Deployment Models for Cloud Based Agriculture Services
	1.2 Virtualization Technology
		1.2.1 Advantages of Virtualization
		1.2.2 Benefits of Virtualization
		1.2.3 Components Associated for Implementation of Virtualization
		1.2.4 Benefits of Virtualization to Cloud Data Centers
		1.2.5 Role of Virtualization in Cloud Resource Management
	1.3 Virtual Machine Migration
		1.3.1 Types of VM Migration
		1.3.2 Cost of VM Live Migration
		1.3.3 Applications of VM Live Migration
	1.4 Applications of Cloud-Based Services in Agriculture Sector
	1.5 Conclusion
	References
2. Hybrid Cloud Architecture for Better Cloud Interoperability
	2.1 Introduction
	2.2 Super Five Technologies of Cloud
		2.2.1 Standardization Technology
		2.2.2 Virtualization Technology
		2.2.3 Intercloud Technology
		2.2.4 Fault Tolerance
		2.2.5 Energy Efficiency
	2.3 Architecture of Interoperable Clouds
	2.4 Hybrid Cloud Interoperability Methodology
	2.5 Modelling of Hybrid Interoperability Cloud Methodology
	2.6 Tools Used to Design Hybrid Interoperability Methodology
	2.7 Proposed Framework for Hybrid Cloud Interoperability
	2.8 Working Philosophy of Hybrid Cloud Framework
	2.9 Simulation of Hybrid Cloud in Cloudsim
	2.10 Conclusions
	References
3. Autoscaling Techniques for Web Applications in the Cloud
	3.1 Introduction
		3.1.1 Service Models
			3.1.1.1 IaaS
			3.1.1.2 PaaS
			3.1.1.3 SaaS
	3.2 Deployment Models
		3.2.1 Public Cloud
		3.2.2 Private Cloud
		3.2.3 Hybrid Cloud
		3.2.4 Community Cloud
	3.3 Pricing Models
		3.3.1 On-Demand Instances
		3.3.2 Reserved Instances
		3.3.3 Spot Instances
	3.4 Scaling in the Cloud
		3.4.1 Vertical Scaling
		3.4.2 Horizontal Scaling
	4.5 Auto Scaling Techniques
		4.5.1 Reactive Approach: Threshold-based
		3.5.2 Proactive Approach
		3.5.3 Time Series Analysis
			3.5.3.1 Linear Regression, Neural Network, SVM
			3.5.3.2 Autoregressive Models (ARs)
			3.5.3.3 Signal Prediction
		3.5.4 Control Theory
		3.5.5 Reinforcement Learning
		3.5.6 Queuing Theory
	3.6 Proactive Auto Scaling Technique Using SVM: A Case Study
		3.6.1 Solving Approach
		3.6.2 Experimental Setup
		3.6.3 Client Infrastructure
		3.6.4 Architecture
		3.6.4 Algorithm
		3.6.6 Implementation
			3.6.6.1 Data Collection
			3.6.6.2 Data Preprocessing
			3.6.6.3 SVM Training
			3.6.6.4 Process for Scaling
			3.6.6.5 Results
	3.7 Discussion
	References
4. Community Cloud Service Model for People with Special Needs
	4.1 Introduction
	4.2 Deployment Models of Cloud
	4.3 Main Objectives to Develop Community Service Model
	4.4 Community Cloud Service Model
		4.4.1  Sign Language Dictionary
		4.4.2 Sign Language Learning Applications
		4.4.3 Tools for Translation of Sign Language into Spoken Language and Vice Versa
			4.4.3.1 Distance Learning Education System
		4.4.4 Telemedicine and Healthcare Service for the Deaf and Mute
		4.4.5 Employment Opportunities for Disabled
	4.5 Benefit to Society
	4.6 Conclusion and Future Scope
	References
Section II: Cloud for Agriculture
5. Sensor Applications in Agriculture - A Review
	5.1 Introduction
	5.2 IOT in Agriculture
	5.3 Major Applications in Agriculture
		5.3.1 Benefits of Smart Agriculture Solutions
		5.3.2 Soil Moisture Sensing
		5.3.3 Land/Seedbed Preparation
		5.3.4 Spray Drift Evaluation
		5.3.5 Weeding Robot
	5.4 Cloud Based Air Quality Monitoring: Case Study
		5.4.1 Role of IoT
		5.4.2 Role of Cloud Computing
		5.4.3 Applications of Cloud Computing in Agriculture
		5.4.4 Overview of Air Quality Monitoring System
			The Real-Time Dataset
	5.5 Future Advancements in Farm Management
	5.6 Conclusion
	References
6. Crop Biophysical Parameters Estimation Using SAR Imagery for Precision Agriculture Applications
	6.1 Introduction
		6.1.1 Morphological Characterization Sensors
		6.1.2 Physiological Assessment Sensors for Vegetation
	6.2 Motivation
	6.3 Literature Survey
	6.4 Proposed Systems
	6.5 Case Studies for Precision Agriculture
		6.5.1 Case Study 1: Classification of Crop Diseases Using IoT and Machine Learning in the Cloud Environment
		6.5.2 Case Study 2: IoT-Based Smart System to Support Agricultural Parameters
		6.5.3 Case Study 3: Climate Monitoring
		6.5.4 Case Study 4: Crop Management
		6.5.5 Case Study 5: Greenhouse Automation
	6.6 Conclusion
	References
7. Importance of Cloud Computing Technique in Agriculture Field Using Different Methodologies
	7.1 Introduction
	7.2 Methods and Values of Agriculture Entry to the Field of Cloud Computing
		7.2.1 Agriculture and Cloud Computing
		7.2.2 Cloud Computing Mechanisms to Support Agricultural Operations
	7.3 Farmer\'s Attraction with the Cloud Computing Technology
	7.4 Proposed Cloud Computing Platform for the Farmers
	7.5 Cloud Computing is Helping the Agricultural Sector to Grow
	7.6 Responsibilities of Cloud Computing in Agriculture Domain (Rural and Hills)
	7.7 Advantages of Cloud Computing Technology in Agriculture
	7.8 Challenges of Cloud Computing Technology in Agriculture
	7.9 Applications of Cloud Computing Technology in the Field of Agriculture
	7.10 Conclusion
	References
8. Optimal Clustering Scheme for Cloud Operations Management Over Mobile Ad Hoc Network of Crop Systems
	8.1 Introduction
	8.2 Background
	8.3 Previous Work Done
	8.4 Existing Methodologies
	8.5 Proposed Methodology
	8.6 Stimulation and Result
	8.7 Result and Discussion
	8.8 Conclusion
	8.9 Future Scope
	References
9. A Novel Hybrid Method for Cloud Security Using Efficient IDS for Agricultural Weather Forecasting Systems
	9.1 Introduction
	9.2 Background
	9.3 Previous Work Done
	9.4 Existing Methodologies
	9.5 Analysis of Methods
	9.6 Proposed Methodology
	9.7 Stimulation and Result
	9.8 Results and Discussion
	9.9 Conclusion
	9.10 Future Scope
	References
Section III: Cloud for Healthcare
10. Cloud Model for Real-Time Healthcare Services
	10.1 Introduction
		10.1.1 Objectives of Research
		10.1.2 Organization
	10.2 Related Work
	10.3 Different Cloud Computing Uses in Real-Time Healthcare Services
	10.4 Cloud Computing in Healthcare Applications
		10.4.1 Healthcare Data Management, Data Sharing, and Access in the Cloud
		10.4.2 Preventive Medical Care Using Cloud Computing
	10.5 Issues and Challenges in Using Cloud Computing in Healthcare
	10.6 Real-Time Virtual Machine Scheduling Framework of the Cloud Environment
		10.6.1 Real-Time Healthcare Sensing and Actuation in the Cloud Environment
		10.6.2 Real-Time Patients and Physician Interactions
	10.7 Case Study of Different Healthcare Cloud Providers
	10.8 Conclusions
	Acknowledgment
	References
11. Cloud Computing-Based Smart Healthcare System
	11.1 Introduction
		11.1.1 Fractal Dimension
	11.2 Materials and Methods
		11.2.1 EEG
		11.2.2 Data Set
		11.2.3 Higuchi\'s Fractal Dimension Method
		11.2.4 Katz\'s Fractal Dimension Method
		11.2.5 Classifier
		11.2.6 Cloud Platform
		11.2.7 Data Access Interface
		11.2.8 Client Development
	11.3 Results
		11.3.1 HFD Method
		11.3.2 KFD Method
	11.4 Discussion
	11.5 Conclusion
	11.6 Future Scope
	References
12. Rehearsal of Cloud and IoT Devices in the Healthcare System
	12.1 Introduction
	12.2 Efficient Services Provided for Healthcare Systems
		12.2.1 Microsoft Cloud Services
		12.2.2 Information Security Management (SMS)
	12.3 Need of Cloud Computing for Healthcare
	12.4 Benefits of Cloud Computing for Healthcare
		12.4.1 Security
		12.4.2 Cost
		12.4.3 Scalability
		12.4.4 Data Storage
		12.4.5 Artificial Intelligence and Machine Learning
		12.4.5 Collaboration
	12.5 Risks of Cloud Computing in Healthcare System
	12.6 Benefit of Microsoft Cloud in the Healing Healthcare System
	12.7 Healthcare\'s Future is in the Cloud
		12.7.1 The Circumstances for the Cloud
		12.7.2 The Circumstances for IoT Devices
	12.8 Classification Techniques in the Cloud and IoT-Based Health Monitoring and Diagnosis Approach
		12.8.1 DXC Technology
		12.8.2 Flexible Multi-Level Architecture
		12.8.3 Dynamic Cloud Platform for an eHealth System Based on a Cloud SOA Architecture (DCCSOA)
		12.8.4 Cloud Based 8E-Prescription Management System for Healthcare Services Using IoT Devices
		12.8.5 Android-Based Mobile Data Acquisition (DAQ)
		12.8.6 WSN Architecture with IoT
		12.8.7 Fog Computing
		12.8.8 Hospital Information Systems (HIS)
		12.8.9 E-Health Internet of Things (IoT)
		12.8.10 Mobile Cloud Computing for Emergency Healthcare (MCCEH) Model
		12.8.11 Cloud-Based Intelligent Healthcare Monitoring System (CIHMS)
		12.8.12 Remote Healthcare Service
	12.9 Analysisof Existing Techniques
	12.10 Conclusion
	12.11 Future Scope
	References
13. Cloud-Based Diagnostic and Management Framework for Remote Health Monitoring
	13.1 Introduction
	13.2 Literature Review
	13.3 Diverse Approaches for a Remote Healthcare Monitoring System
		13.3.1 E-Health Monitoring System
		13.3.2 Wearable Sensors-Based Remote Health Monitoring System
		13.3.3 Secured Remote Health Monitoring System
		13.3.4 Smart Technology for Healthcare Professionals - An Analysis
		13.3.5 Disease Prediction as an Added Feature of an e-Healthcare Application
		13.3.6 Cloud Technology Supported Hospital File Management System
	13.4 Exemplary Design \"Smart Doctor-Patient Diagnostic and Management System\"
		13.4.1 System at a Glance
		13.4.2 Overview
		13.4.3 System Modules
			13.4.3.1 Disease Prediction
			13.4.3.2 Finding a Doctor
			13.4.3.3 Online Prescription
			13.4.3.4 Text-to-Speech Conversion
			13.4.3.5 Emergency Alert Button
			13.4.3.6 Doctor Login with Registration Number
		13.4.4 System Design
		13.4.5 ER Diagram
		13.4.6 Algorithm Details
		13.4.7 Dashboard for Patient and for Doctors
		13.4.8 Concluding Remarks
	13.5 Conclusions and Future Work
	Acknowledgments
	References
14. Efficient Accessibility in Cloud Databases of Health Networks with Natural Neighbor Approach for RNN-DBSCAN
	14.1 Introduction
	14.2 Background
	14.3 Previous Work Done
	14.4 Existing Methodologies
		14.4.1 Natural Neighbor to Identify the Density of Data Objects
		14.4.2 RNN-DBSCAN Method
		14.4.3 DPC-KNN Method
		14.4.4 A-DPC Method
		14.4.5 LP-SNG Algorithm
	14.5 Analysis of Method
	14.6 Proposed Methodology
	14.7 Simulation and Results
	14.8 Results and Discussion
	14.9 Conclusion
	14.10 Future Scope
	References
15. Blood Oxygen Level and Pulse Rate Monitoring Using IoT and Cloud-Based Data Storage
	15.1 Introduction
		15.1.1 Overview
		15.1.2 Problem Statement
		15.1.3 Background
	15.2 Literature Review
	15.3 Problem with Existing System
		15.3.1 Problems Faced by Doctors
		15.3.2 Problems Faced by the Patient
	15.4 Components and Sensors
		15.4.1 Pulse Oximeter
			15.4.1.1 MAXIM MAX30100 Sensor
			15.4.1.2 Working of MAX30100 Sensor
		15.4.2 Firebase Realtime Database
			15.4.2.1 Structure of Firebase Realtime Database
			15.4.2.2 Configuration of Firebase Realtime Database
			15.4.2.3 Read and Write Data on Firebase Realtime Database
				15.4.2.3.1 Write Data
				15.4.2.3.2 Read Data
		15.4.3 NodeMCU (ESP 8266)
	15.5 System Architecture
	15.6 Implementation
		15.6.1 Patient Monitoring
			15.6.1.1 Connection Between MAX30100 and ESP8266
			15.6.1.2 Communication Between ESP8266 and Cloud Data Storage
			15.6.1.3 Data Storage in the Cloud and Its Data Structure
		15.6.2 User Interface
	15.7 Data Analysis and Results
	15.8 Future Scope
	15.9 Conclusion
	References
16. Parkinson Disease Prediction Model and Deployment on AWS Cloud
	16.1 Introduction
	16.2 Related Work
	16.3 Description of Data Set
	16.4 Feature Importance Analysis
	16.5 Prediction Techniques
		16.5.1 Logistic Regression
		16.5.2 Decision Tree
		16.5.3 SVM (Support Vector Machine)
		16.5.4 KNN (K-Nearest Neighbor)
		16.5.5 Random Forest
	16.6 Deploying Model on AWS Cloud
	16.7 Result
	16.8 Conclusion
	References
17. Federated Learning for Brain Tumor Segmentation on the Cloud
	17.1 Introduction
	17.2 Data Set and Preprocessing
		17.2.1 Data Set
		17.2.2 Data Set Preprocessing
	17.3 Double Clustered Federated Learning System
		17.3.1 U-Net Architecture
			17.3.1.1 Downsampling Stage of U-Net
			17.3.1.2 ResNet
			17.3.1.3 Upsampling in U-Net Architecture
	17.4 General Training
		17.4.1 Pre-Training the U-Net
	17.5 Federated Learning and Cloud Development
		17.5.1 Federated Learning
			17.5.1.1 FedProx
			17.5.2 Federated Training
			17.5.3 Cloud Deployment
	17.6 Global Deployment
	17.7 Conclusion
	References
18. Smart System for COVID-19 Susceptibility Test and Prediction of Risk along with Validation of Guidelines Conformity Using the Cloud
	18.1 Introduction
	18.2 Proposed Solution
	18.3 Methodology
		18.3.1 SpO2 Level Measurement
		18.3.2 COVID Risk Detection
		18.3.3 Mask Detection
		18.3.4 Social Distancing Using Bluetooth
	18.4 Results
	18.5 Conclusion
	Acknowledgments
	References
19. Designing a Policy Data Prediction Framework in Cloud for Trending COVID-19 Issues over Social Media
	19.1 Introduction
	19.2 Background
	19.3 Previous Work Done
	19.4 Existing Methodologies
	19.5 Analysis of Methods
	16.6 Proposed Methodology
	19.7 Simulation and Results
	19.8 Results and Discussion
	19.9 Conclusion
	19.10 Future Scope
	References
Index