Оглавление
Группа авторов. Machine Learning Approach for Cloud Data Analytics in IoT
Table of Contents
Guide
List of Illustrations
List of Tables
Pages
Machine Learning Approach for Cloud Data Analytics in IoT
Preface
Acknowledgment
1. Machine Learning–Based Data Analysis
1.1 Introduction
1.2 Machine Learning for the Internet of Things Using Data Analysis
1.2.1 Computing Framework
1.2.2 Fog Computing
1.2.3 Edge Computing
1.2.4 Cloud Computing
1.2.5 Distributed Computing
1.3 Machine Learning Applied to Data Analysis
1.3.1 Supervised Learning Systems
1.3.2 Decision Trees
1.3.3 Decision Tree Types
1.3.4 Unsupervised Machine Learning
1.3.5 Association Rule Learning
1.3.6 Reinforcement Learning
1.4 Practical Issues in Machine Learning
1.5 Data Acquisition
1.6 Understanding the Data Formats Used in Data Analysis Applications
1.7 Data Cleaning
1.8 Data Visualization
1.9 Understanding the Data Analysis Problem-Solving Approach
1.10 Visualizing Data to Enhance Understanding and Using Neural Networks in Data Analysis
1.11 Statistical Data Analysis Techniques
1.11.1 Hypothesis Testing
1.11.2 Regression Analysis
1.12 Text Analysis and Visual and Audio Analysis
1.13 Mathematical and Parallel Techniques for Data Analysis
1.13.1 Using Map-Reduce
1.13.2 Leaning Analysis
1.13.3 Market Basket Analysis
1.14 Conclusion
References
2. Machine Learning for Cyber-Immune IoT Applications
2.1 Introduction
2.2 Some Associated Impactful Terms. 2.2.1 IoT
2.2.2 IoT Device
2.2.3 IoT Service
2.2.4 Internet Security
2.2.5 Data Security
2.2.6 Cyberthreats
2.2.7 Cyber Attack
2.2.8 Malware
2.2.9 Phishing
2.2.10 Ransomware
2.2.11 Spear-Phishing
2.2.12 Spyware
2.2.13 Cybercrime
2.2.14 IoT Cyber Security
2.2.15 IP Address
2.3 Cloud Rationality Representation. 2.3.1 Cloud
2.3.2 Cloud Data
2.3.3 Cloud Security
2.3.4 Cloud Computing
2.4 Integration of IoT With Cloud
2.5 The Concepts That Rules Over. 2.5.1 Artificial Intelligent
2.5.2 Overview of Machine Learning
2.5.2.1 Supervised Learning
2.5.2.2 Unsupervised Learning
2.5.3 Applications of Machine Learning in Cyber Security
2.5.4 Applications of Machine Learning in Cybercrime
2.5.5 Adherence of Machine Learning With Cyber Security in Relevance to IoT
2.5.6 Distributed Denial-of-Service
2.6 Related Work
2.7 Methodology
2.8 Discussions and Implications
2.9 Conclusion
References
3. Employing Machine Learning Approaches for Predictive Data Analytics in Retail Industry
3.1 Introduction
3.2 Related Work
3.3 Predictive Data Analytics in Retail
3.3.1 ML for Predictive Data Analytics
3.3.2 Use Cases
3.3.3 Limitations and Challenges
3.4 Proposed Model
3.4.1 Case Study
3.5 Conclusion and Future Scope
References
4. Emerging Cloud Computing Trends for Business Transformation
4.1 Introduction
4.1.1 Computing Definition Cloud
4.1.2 Advantages of Cloud Computing Over On-Premises IT Operation
4.1.3 Limitations of Cloud Computing
4.2 History of Cloud Computing
4.3 Core Attributes of Cloud Computing
4.4 Cloud Computing Models
4.4.1 Cloud Deployment Model
4.4.2 Cloud Service Model
4.5 Core Components of Cloud Computing Architecture: Hardware and Software
4.6 Factors Need to Consider for Cloud Adoption
4.6.1 Evaluating Cloud Infrastructure
4.6.2 Evaluating Cloud Provider
4.6.3 Evaluating Cloud Security
4.6.4 Evaluating Cloud Services
4.6.5 Evaluating Cloud Service Level Agreements (SLA)
4.6.6 Limitations to Cloud Adoption
4.7 Transforming Business Through Cloud
4.8 Key Emerging Trends in Cloud Computing
4.8.1 Technology Trends
4.8.2 Business Models
4.8.3 Product Transformation
4.8.4 Customer Engagement
4.8.5 Employee Empowerment
4.8.6 Data Management and Assurance
4.8.7 Digitalization
4.8.8 Building Intelligence Cloud System
4.8.9 Creating Hyper-Converged Infrastructure
4.9 Case Study: Moving Data Warehouse to Cloud Boosts Performance for Johnson & Johnson
4.10 Conclusion
References
5. Security of Sensitive Data in Cloud Computing
5.1 Introduction
5.1.1 Characteristics of Cloud Computing
5.1.2 Deployment Models for Cloud Services
5.1.3 Types of Cloud Delivery Models
5.2 Data in Cloud
5.2.1 Data Life Cycle
5.3 Security Challenges in Cloud Computing for Data
5.3.1 Security Challenges Related to Data at Rest
5.3.2 Security Challenges Related to Data in Use
5.3.3 Security Challenges Related to Data in Transit
5.4 Cross-Cutting Issues Related to Network in Cloud
5.5 Protection of Data
5.6 Tighter IAM Controls
5.7 Conclusion and Future Scope
References
6. Cloud Cryptography for Cloud Data Analytics in IoT
6.1 Introduction
6.2 Cloud Computing Software Security Fundamentals
6.3 Security Management
6.4 Cryptography Algorithms
6.4.1 Types of Cryptography
6.5 Secure Communications
6.6 Identity Management and Access Control
6.7 Autonomic Security
6.8 Conclusion
References
7. Issues and Challenges of Classical Cryptography in Cloud Computing
7.1 Introduction
7.1.1 Problem Statement and Motivation
7.1.2 Contribution
7.2 Cryptography
7.2.1 Cryptography Classification
7.2.1.1 Classical Cryptography
7.2.1.1.1 Hash Cryptography
7.2.1.1.2 Symmetric Key Cryptography
7.2.1.1.3 Asymmetric Key Cryptography
7.2.1.2 Homomorphic Encryption
7.2.1.2.1 Partial Homomorphic Encryption
7.2.1.2.2 Somewhat Homomorphic Encryption
7.2.1.2.3 Homomorphic Encryption
7.3 Security in Cloud Computing
7.3.1 The Need for Security in Cloud Computing
7.3.2 Challenges in Cloud Computing Security
7.3.3 Benefits of Cloud Computing Security
7.3.4 Literature Survey
7.4 Classical Cryptography for Cloud Computing
7.4.1 RSA
7.4.2 AES
7.4.3 DES
7.4.4 Blowfish
7.5 Homomorphic Cryptosystem
7.5.1 Paillier Cryptosystem
7.5.1.1 Additive Homomorphic Property
7.5.2 RSA Homomorphic Cryptosystem
7.5.2.1 Multiplicative Homomorphic Property
7.6 Implementation
7.7 Conclusion and Future Scope
References
8. Cloud-Based Data Analytics for Monitoring Smart Environments
8.1 Introduction
8.2 Environmental Monitoring for Smart Buildings
8.2.1 Smart Environments
8.3 Smart Health
8.3.1 Description of Solutions in General
8.3.2 Detection of Distress
8.3.3 Green Protection
8.3.4 Medical Preventive/Help
8.4 Digital Network 5G and Broadband Networks
8.4.1 IoT-Based Smart Grid Technologies
8.5 Emergent Smart Cities Communication Networks
8.5.1 RFID Technologies
8.5.2 Identifier Schemes
8.6 Smart City IoT Platforms Analysis System
8.7 Smart Management of Car Parking in Smart Cities
8.8 Smart City Systems and Services Securing: A Risk-Based Analytical Approach
8.9 Virtual Integrated Storage System
8.10 Convolutional Neural Network (CNN)
8.10.1 IEEE 802.15.4
8.10.2 BLE
8.10.3 ITU-T G.9959 (Z-Wave)
8.10.4 NFC
8.10.5 LoRaWAN
8.10.6 Sigfox
8.10.7 NB-IoT
8.10.8 PLC
8.10.9 MS/TP
8.11 Challenges and Issues
8.11.1 Interoperability and Standardization
8.11.2 Customization and Adaptation
8.11.3 Entity Identification and Virtualization
8.11.4 Big Data Issue in Smart Environments
8.12 Future Trends and Research Directions in Big Data Platforms for the Internet of Things
8.13 Case Study
8.14 Conclusion
References
9. Performance Metrics for Comparison of Heuristics Task Scheduling Algorithms in Cloud Computing Platform
9.1 Introduction
9.2 Workflow Model
9.3 System Computing Model
9.4 Major Objective of Scheduling
9.5 Task Computational Attributes for Scheduling
9.6 Performance Metrics
9.7 Heuristic Task Scheduling Algorithms
9.7.1 Heterogeneous Earliest Finish Time (HEFT) Algorithm
9.7.2 Critical-Path-on-a-Processor (CPOP) Algorithm
9.7.3 As Late As Possible (ALAP) Algorithm
9.7.4 Performance Effective Task Scheduling (PETS) Algorithm
9.8 Performance Analysis and Results
9.9 Conclusion
References
10. Smart Environment Monitoring Models Using Cloud-Based Data Analytics: A Comprehensive Study
10.1 Introduction
10.1.1 Internet of Things
10.1.2 Cloud Computing
10.1.3 Environmental Monitoring
10.2 Background and Motivation
10.2.1 Challenges and Issues
10.2.2 Technologies Used for Designing Cloud-Based Data Analytics
10.2.2.1 Communication Technologies
10.2.3 Cloud-Based Data Analysis Techniques and Models
10.2.3.1 MapReduce for Data Analysis
10.2.3.1.1 MapReduce Hypothesis
10.2.3.1.2 Framework of MapReduce
10.2.3.1.3 MapReduce Algorithms
10.2.3.2 Data Analysis Workflows
10.2.3.2.1 Cloud Workflow Management System
10.2.3.3 NoSQL Models
10.2.3.3.1 NoSQL Key Features
10.2.3.3.2 Various NoSQL Systems
10.2.4 Data Mining Techniques
10.2.5 Machine Learning
10.2.5.1 Significant Importance of Machine Learning and Its Algorithms
10.2.6 Applications
10.3 Conclusion
References
11. Advancement of Machine Learning and Cloud Computing in the Field of Smart Health Care
11.1 Introduction
11.2 Survey on Architectural WBAN
11.3 Suggested Strategies. 11.3.1 System Overview
11.3.2 Motivation
11.3.3 DSCB Protocol
11.3.3.1 Network Topology
11.3.3.2 Starting Stage
11.3.3.3 Cluster Evolution
11.3.3.4 Sensed Information Stage
11.3.3.5 Choice of Forwarder Stage [26, 27]
11.3.3.6 Energy Consumption as Well as Routing Stage
11.4 CNN-Based Image Segmentation (UNet Model)
11.5 Emerging Trends in IoT Healthcare
11.6 Tier Health IoT Model
11.7 Role of IoT in Big Data Analytics
11.8 Tier Wireless Body Area Network Architecture
11.9 Conclusion
References
12. Study on Green Cloud Computing—A Review
12.1 Introduction
12.2 Cloud Computing
12.2.1 Cloud Computing: On-Request Outsourcing-Pay-as-You-Go
12.3 Features of Cloud Computing
12.4 Green Computing
12.5 Green Cloud Computing
12.6 Models of Cloud Computing
12.7 Models of Cloud Services
12.8 Cloud Deployment Models
12.9 Green Cloud Architecture
12.10 Cloud Service Providers
12.11 Features of Green Cloud Computing
12.12 Advantages of Green Cloud Computing
12.13 Limitations of Green Cloud Computing
12.14 Cloud and Sustainability Environmental
12.15 Statistics Related to Cloud Data Centers
12.16 The Impact of Data Centers on Environment
12.17 Virtualization Technologies
12.18 Literature Review
12.19 The Main Objective
12.20 Research Gap
12.21 Research Methodology
12.22 Conclusion and Suggestions
12.23 Scope for Further Research
References
13. Intelligent Reclamation of Plantae Affliction Disease
13.1 Introduction
13.2 Existing System
13.3 Proposed System
13.4 Objectives of the Concept
13.5 Operational Requirements
13.6 Non-Operational Requirements
13.7 Depiction Design Description
13.8 System Architecture
13.8.1 Module Characteristics
13.8.2 Convolutional Neural System
13.8.3 User Application
13.9 Design Diagrams. 13.9.1 High-Level Design
13.9.2 Low-Level Design
13.9.3 Test Cases
13.10 Comparison and Screenshot
13.11 Conclusion
References
14. Prediction of the Stock Market Using Machine Learning–Based Data Analytics
14.1 Introduction of Stock Market
14.1.1 Impact of Stock Prices
14.2 Related Works
14.3 Financial Prediction Systems Framework
14.3.1 Conceptual Financial Prediction Systems
14.3.2 Framework of Financial Prediction Systems Using Machine Learning
14.3.2.1 Algorithm to Predicting the Closing Price of the Given Stock Data Using Linear Regression
14.3.3 Framework of Financial Prediction Systems Using Deep Learning
14.3.3.1 Algorithm to Predict the Closing Price of the Given Stock Using Long Short-Term Memory
14.4 Implementation and Discussion of Result
14.4.1 Pharmaceutical Sector
14.4.1.1 Cipla Limited
14.4.1.2 Torrent Pharmaceuticals Limited
14.4.2 Banking Sector
14.4.2.1 ICICI Bank
14.4.2.2 State Bank of India
14.4.3 Fast-Moving Consumer Goods Sector
14.4.3.1 ITC
14.4.3.2 Hindustan Unilever Limited
14.4.4 Power Sector
14.4.4.1 Adani Power Limited
14.4.4.2 Power Grid Corporation of India Limited
14.4.5 Automobiles Sector
14.4.5.1 Mahindra & Mahindra Limited
14.4.5.2 Maruti Suzuki India Limited
14.4.6 Comparison of Prediction Using Linear Regression Model and Long-Short-Term Memory Model
14.5 Conclusion
14.5.1 Future Enhancement
References
Web Citations
15. Pehchaan: Analysis of the ‘Aadhar Dataset’ to Facilitate a Smooth and Efficient Conduct of the Upcoming NPR
15.1 Introduction
15.2 Basic Concepts
15.3 Study of Literature Survey and Technology
15.4 Proposed Model
15.5 Implementation and Results
15.6 Conclusion
References
16. Deep Learning Approach for Resource Optimization in Blockchain, Cellular Networks, and IoT: Open Challenges and Current Solutions
16.1 Introduction
16.1.1 Aim
16.1.2 Research Contribution
16.1.3 Organization
16.2 Background
16.2.1 Blockchain
16.2.2 Internet of Things (IoT)
16.2.3 5G Future Generation Cellular Networks
16.2.4 Machine Learning and Deep Learning Techniques
16.2.5 Deep Reinforcement Learning
16.3 Deep Learning for Resource Management in Blockchain, Cellular, and IoT Networks
16.3.1 Resource Management in Blockchain for 5G Cellular Networks
16.3.2 Deep Learning Blockchain Application for Resource Management in IoT Networks
16.4 Future Research Challenges
16.4.1 Blockchain Technology
16.4.1.1 Scalability
16.4.1.2 Efficient Consensus Protocols
16.4.1.3 Lack of Skills and Experts
16.4.2 IoT Networks. 16.4.2.1 Heterogeneity of IoT and 5G Data
16.4.2.2 Scalability Issues
16.4.2.3 Security and Privacy Issues
16.4.3 5G Future Generation Networks. 16.4.3.1 Heterogeneity
16.4.3.2 Security and Privacy
16.4.3.3 Resource Utilization
16.4.4 Machine Learning and Deep Learning
16.4.4.1 Interpretability
16.4.4.2 Training Cost for ML and DRL Techniques
16.4.4.3 Lack of Availability of Data Sets
16.4.4.4 Avalanche Effect for DRL Approach
16.4.5 General Issues. 16.4.5.1 Security and Privacy Issues
16.4.5.2 Storage
16.4.5.3 Reliability
16.4.5.4 Multitasking Approach
16.5 Conclusion and Discussion
References
17. Unsupervised Learning in Accordance With New Aspects of Artificial Intelligence
17.1 Introduction
17.2 Applications of Machine Learning in Data Management Possibilities
17.2.1 Terminology of Basic Machine Learning
17.2.2 Rules Based on Machine Learning
17.2.3 Unsupervised vs. Supervised Methodology
17.3 Solutions to Improve Unsupervised Learning Using Machine Learning
17.3.1 Insufficiency of Labeled Data
17.3.2 Overfitting
17.3.3 A Closer Look Into Unsupervised Algorithms
17.3.3.1 Reducing Dimensionally
17.3.3.2 Principal Component Analysis
17.3.4 Singular Value Decomposition (SVD)
17.3.4.1 Random Projection
17.3.4.2 Isomax
17.3.5 Dictionary Learning
17.3.6 The Latent Dirichlet Allocation
17.4 Open Source Platform for Cutting Edge Unsupervised Machine Learning
17.4.1 TensorFlow
17.4.2 Keras
17.4.3 Scikit-Learn
17.4.4 Microsoft Cognitive Toolkit
17.4.5 Theano
17.4.6 Caffe
17.4.7 Torch
17.5 Applications of Unsupervised Learning
17.5.1 Regulation of Digital Data
17.5.2 Machine Learning in Voice Assistance
17.5.3 For Effective Marketing
17.5.4 Advancement of Cyber Security
17.5.5 Faster Computing Power
17.5.6 The Endnote
17.6 Applications Using Machine Learning Algos. 17.6.1 Linear Regression
17.6.2 Logistic Regression
17.6.3 Decision Tree
17.6.4 Support Vector Machine (SVM)
17.6.5 Naive Bayes
17.6.6 K-Nearest Neighbors
17.6.7 K-Means
17.6.8 Random Forest
17.6.9 Dimensionality Reduction Algorithms
17.6.10 Gradient Boosting Algorithms
References
18. Predictive Modeling of Anthropomorphic Gamifying Blockchain-Enabled Transitional Healthcare System
18.1 Introduction
18.1.1 Transitional Healthcare Services and Their Challenges
18.2 Gamification in Transitional Healthcare: A New Model
18.2.1 Anthropomorphic Interface With Gamification
18.2.2 Gamification in Blockchain
18.2.3 Anthropomorphic Gamification in Blockchain: Motivational Factors
18.3 Existing Related Work
18.4 The Framework
18.4.1 Health Player
18.4.2 Data Collection
18.4.3 Anthropomorphic Gamification Layers
18.4.4 Ethereum
18.4.4.1 Ethereum-Based Smart Contracts for Healthcare
18.4.4.2 Installation of Ethereum Smart Contract
18.4.5 Reward Model
18.4.6 Predictive Models
18.5 Implementation
18.5.1 Methodology
18.5.2 Result Analysis
18.5.3 Threats to the Validity
18.6 Conclusion
References
Index
WILEY END USER LICENSE AGREEMENT
