Applications of Machine Learning in Big-Data Analytics and Cloud Computing

Cover
Applications of Machine Learning in Big-Data Analytics and Cloud Computing
Contents
Preface
List of Contributors
List of Figures
List of Tables
List of Abbreviations
1 Pattern Analysis of COVID-19 Death and Recovery Cases Data of Countries Using Greedy Biclustering Algorithm
	Abstract
	1.1 Introduction
	1.2 Problem Description
		1.2.1 Greedy Approach: Bicluster Size Maximization Based Fitness Function
		1.2.2 Data Description
	1.3 Proposed Work: COVID 19 Pattern Identification Using Greedy Biclustering
	1.4 Results and Discussions
	1.5 Conclusion
	1.6 Acknowledgements
	References
2 Artificial Fish Swarm Optimization Algorithm with Hill Climbing Based Clustering Technique for Throughput Maximization in Wireless Multimedia Sensor Network
	Abstract
	2.1 Introduction
	2.2 The Proposed AFSA-HC Technique
		2.2.1 AFSA-HC Based Clustering Phase
		2.2.2 Deflate-Based Data Aggregation Phase
		2.2.3 Hybrid Data Transmission Phase
	2.3 Performance Validation
	2.4 Conclusion
	References
3 Analysis of Machine Learning Techniques for Spam Detection
	Abstract
	3.1 Introduction
		3.1.1 Ham Messages
		3.1.2 Spam Messages
	3.2 Types of Spam Attack
		3.2.1 Email Phishing
		3.2.2 Spear Phishing
		3.2.3 Whaling
	3.3 Spammer Methods
	3.4 Some Prevention Methods From User End
		3.4.1 Protect Email Addresses
		3.4.2 Preventing Spam from Being Sent
		3.4.3 Block Spam to be Delivered
		3.4.4 Identify and Separate Spam After Delivery
			3.4.4.1 Targeted Link Analysis
			3.4.4.2 Bayesian Filters
		3.4.5 Report Spam
	3.5 Machine Learning Algorithms
		3.5.1 Naïve Bayes (NB)
		3.5.2 Random Forests (RF)
		3.5.3 Support Vector Machine (SVM)
		3.5.4 Logistic Regression (LR)
	3.6 Methodology
		3.6.1 Database Used
		3.6.2 Work Flow
	3.7 Results and Analysis
		3.7.1 Performance Metric
		3.7.2 Experimental Results
			3.7.2.1 Cleaning Data by Removing Punctuations, White Spaces, and Stop Words
			3.7.2.2 Stemming the Messages
			3.7.2.3 Analyzing the Common Words from the Spam and Ham Messages
		3.7.3 Analyses of Machine Learning Algorithms
			3.7.3.1 Accuracy Score Before Stemming
			3.7.3.2 Accuracy Score After Stemming
			3.7.3.3 Splitting Dataset into Train and Test Data
			3.7.3.4 Mapping Confusion Matrix
			3.7.3.5 Accuracy
	3.8 Conclusion and Future Work
	References
4 Smart Sensor Based Prognostication of Cardiac Disease Prediction Using Machine Learning Techniques
	Abstract
	4.1 Introduction
	4.2 Literature Survey
	4.3 Proposed Method
	4.4 Data Collection in IoT
		4.4.1 Fetching Data from Sensors
		4.4.2 K-Nearest Neighbor Classifier
		4.4.3 Random Forest Classifier
		4.4.4 Decision Tree Classifier
		4.4.5 Extreme Gradient Boost Classifier
	4.5 Results and Discussions
	4.6 Conclusion
	4.7 Acknowledgements
	References
5 Assimilate Machine Learning Algorithms in Big Data Analytics: Review
	Abstract
	5.1 Introduction
	5.2 Literature Survey
	5.3 Big Data
	5.4 Machine Learning
	5.5 File Categories
	5.6 Storage And Expenses
	5.7 The Device Learning Anatomy
	5.8 Machine Learning Technology Methods in Big Data Analytics
	5.9 Structure Mapreduce
	5.10 Associated Investigations
	5.11 Multivariate Data Coterie in Machine Learning
	5.12 Machine Learning Algorithm
		5.12.1 Machine Learning Framework
		5.12.2 Parametric and Non-Parametric Techniques in Machine Learning
			5.12.2.1 Bias
			5.12.2.2 Variance
		5.12.3 Parametric Techniques
			5.12.3.1 Linear Regression
			5.12.3.2 Decision Tree
			5.12.3.3 Naive Bayes
			5.12.3.4 Support Vector Machine
			5.12.3.5 Random Forest
			5.12.3.6 K-Nearest Neighbor
			5.12.3.7 Deep Learning
			5.12.3.8 Linear Vector Quantization (LVQ)
			5.12.3.9 Transfer Learning
		5.12.4 Non-Parametric Techniques
			5.12.4.1 K-Means Clustering
			5.12.4.2 Principal Component Analysis
			5.12.4.3 A Priori Algorithm
			5.12.4.4 Reinforcement Learning (RL)
			5.12.4.5 Semi-Supervised Learning
	5.13 Machine Learning Technology Assessment Parameters
		5.13.1 Ranking Performance
		5.13.2 Loss in Logarithmic Form
		5.13.3 Assessment Measures
			5.13.3.1 Accuracy
			5.13.3.2 Precision/Specificity
			5.13.3.3 Recall
			5.13.3.4 F-Measure
		5.13.4 Mean Definite Error (MAE)
		5.13.5 Mean Quadruple Error (MSE)
	5.14 Correlation of Outcomes of ML Algorithms
	5.15 Applications
		5.15.1 Economical Facilities
		5.15.2 Business and Endorsement
		5.15.3 Government Bodies
		5.15.4 Hygiene
		5.15.5 Transport
		5.15.6 Fuel and Energy
		5.15.7 Spoken Validation
		5.15.8 Perception of the Device
		5.15.9 Bio-Surveillance
		5.15.10 Mechanization or Realigning
		5.15.11 Mining Text
	5.16 Conclusion
	References
6 Resource Allocation Methodologies in Cloud Computing: A Review and Analysis
	Abstract
	6.1 Introduction
		6.1.1 Cloud Services Models
			6.1.1.1 Infrastructure as a Service
			6.1.1.2 Platform as a Service
			6.1.1.3 Software as a Service
		6.1.2 Types of Cloud Computing
			6.1.2.1 Public Cloud
			6.1.2.2 Private Cloud
			6.1.2.3 Community Cloud
			6.1.2.4 Hybrid Cloud
	6.2 Resource Allocations in Cloud Computing
		6.2.1 Static Allocation
		6.2.2 Dynamic Allocation
	6.3 Dynamic Resource Allocation Models in Cloud Computing
		6.3.1 Service-Level Agreement Based Dynamic Resource Allocation Models
		6.3.2 Market-Based Dynamic Resource Allocation Models
		6.3.3 Utilization-Based Dynamic Resource Allocation Models
		6.3.4 Task Scheduling in Cloud Computing
	6.4 Research Challenges
	6.5 Future Research Paths
	6.6 Advantages and Disadvantages
	6.7 Conclusion
	References
7 Role of Machine Learning in Big Data
	Abstract
	7.1 Introduction
	7.2 Related Work
	7.3 Tools in Big Data
		7.3.1 Batch Analysis Big Data Tools
		7.3.2 Stream Analysis Big Data Tools
		7.3.3 Interactive Analysis Big Data Tools
	7.4 Machine Learning Algorithms in Big Data
	7.5 Applications of Machine Learning in Big Data
	7.6 Challenges of Machine Learning in Big Data
		7.6.1 Volume
		7.6.2 Variety
		7.6.3 Velocity
		7.6.4 Veracity
	7.7 Conclusion
	References
8 Healthcare System for COVID-19: Challenges and Developments
	Abstract
	8.1 Introduction
	8.2 Related Work
	8.3 IoT with Architecture
	8.4 IoHT Security Requirements and Challenges
	8.5 COVID-19 (Coronavirus Disease 2019)
	8.6 The Potential of IoHT in COVID-19 Like Disease Control
	8.7 The Current Applications of IoHT During COVID-19
		8.7.1 Using IoHT to Dissect an Outbreak
		8.7.2 Using IoHT to Ensure Compliance to Quarantine
		8.7.3 Using IoHT to Manage Patient Care
	8.8 IoHT Development for COVID-19
		8.8.1 Smart Home
		8.8.2 Smart Office
		8.8.3 Smart Hotel
		8.8.4 Smart Hospitals
	8.9 Conclusion
	References
9 An Integrated Approach of Blockchain & Big Data in Health Care Sector
	Abstract
	9.1 Introduction
	9.2 Blockchain for Health care
		9.2.1 Healthcare data sharing through gem Network
		9.2.2 OmniPHR
		9.2.3 Medrec
		9.2.4 PSN (Pervasive Social Network) System
		9.2.5 Healthcare Data Gateway
		9.2.6 Resources that are virtual
	9.3 Overview of Blockchain & Big data in health care
		9.3.1 Big Data in Healthcare
		9.3.2 Blockchain in Health Care
		9.3.3 Benefits of Blockchain in Healthcare
			9.3.3.1 Master patient indices
			9.3.3.2 Supply chain management
			9.3.3.3 Claims adjudication
			9.3.3.4 Interoperability
			9.3.3.5 Single, longitudinal patient records
	9.4 Application of Big Data for Blockchain
		9.4.1 Smart Ecosystem
		9.4.2 Digital Trust
		9.4.3 Cybersecurity
		9.4.4 Fighting Drugs
		9.4.5 Online Accessing of Patient’s Data
		9.4.6 Research as well as Development
		9.4.7 Management of Data
		9.4.8 Due to privacy storing of off-chain data
		9.4.9 Collaboration of patient data
	9.5 Solutions of Blockchain For Big Data in Health Care
	9.6 Conclusion and Future Scope
	References
10 Cloud Resource Management for Network Cameras
	Abstract
	10.1 Introduction
	10.2 Resource Analysis
		10.2.1 Network Cameras
		10.2.2 Resource Management on Cloud Environment
		10.2.3 Image and Video Analysis
	10.3 Cloud Resource Management Problems
	10.4 Cloud Resource Manager
		10.4.1 Evaluation of Performance
		10.4.2 View of Resource Requirements
	10.5 Bin Packing
		10.5.1 Analysis of Dynamic Bin Packing
		10.5.2 MinTotal DBP Problem
	10.6 Resource Monitoring and Scaling
	10.7 Conclusion
	References
11 Software-Defined Networking for Healthcare Internet of Things
	Abstract
	11.1 Introduction
	11.2 Healthcare Internet of Things
		11.2.1 Challenges in H-IoT
	11.3 Software-Defined Networking
	11.4 Opportunities, challenges, and possible solutions
	11.5 Conclusion
	References
12 Cloud Computing in the Public Sector: A Study
	Abstract
	12.1 Introduction
	12.2 History and Evolution of Cloud Computing
	12.3 Application of Cloud Computing
	12.4 Advantages of Cloud Computing
	12.5 Challenges
	12.6 Conclusion
13 Big Data Analytics: An overview
	Abstract
	13.1 Introduction
	13.2 Related Work
		13.2.1 Big Data: What Is It?
			13.2.1.1 Characteristics of Big Data
		13.2.2 Big Data Analytics: What Is It?
	13.3 Hadoop and Big Data
	13.4 Big Data Analytics Framework
	13.5 Big Data Analytics Techniques
		13.5.1 Partitioning on Big Data
		13.5.2 Sampling on Big Data
		13.5.3 Sampling-Based Approximation
	13.6 Big Social Data Analytics
	13.7 Applications
		13.7.1 Manufacturing Production
		13.7.2 Smart Grid
		13.7.3 Outbreak of Flu Prediction from Social Site
		13.7.4 Sentiment Analysis of Twitter Data
	13.8 Electricity Price Forecasting
	13.9 Security Situational Analysis for Smart Grid
	13.10 Future Scope
	13.11 Challenges
	13.12 Conclusion
	References
14 Video Usefulness Detection in Big Surveillance Systems
	Abstract
	14.1 Introduction
		14.1.1 Challenges of Video Usefulness Detection
		14.1.2 Video Usefulness Model
	14.2 Background
		14.2.1 (a) Quality of Video Services (QoS)
		14.2.2 Edge Computing
	14.3 Failure of Video Data in Video Surveillance Systems
	14.4 Approaches of Video Failure Detection
	14.5 Failure Detection and Scheduling
		14.5.1 Failure Detection Approaches in Domains
			14.5.1.1 Failure Detection in Fedge Domain
			14.5.1.2 Failure Detection in the Fuser Domain
			14.5.1.3 Failure Detection in the Fcloud Domain
	14.6 Methodological Analysis
		14.6.1 Test of Video Usefulness Model
	14.7 Conclusion
	References
Index
About the Editors
Back Cover