Machine Learning Approach for Cloud Data Analytics in IoT

The book covers the multidimensional perspective of machine learning through the perspective of cloud computing and Internet of Things ranging from fundamentals to advanced applications

Sustainable computing paradigms like cloud and fog are capable of handling issues related to performance, storage and processing, maintenance, security, efficiency, integration, cost, energy and latency in an expeditious manner. In order to expedite decision-making involved in the complex computation and processing of collected data, IoT devices are connected to the cloud or fog environment. Since machine learning as a service provides the best support in business intelligence, organizations have been making significant investments in this technology.

Machine Learning Approach for Cloud Data Analytics in IoT elucidates some of the best practices and their respective outcomes in cloud and fog computing environments. It focuses on all the various research issues related to big data storage and analysis, large-scale data processing, knowledge discovery and knowledge management, computational intelligence, data security and privacy, data representation and visualization, and data analytics. The featured technologies presented in the book optimizes various industry processes using business intelligence in engineering and technology. Light is also shed on cloud-based embedded software development practices to integrate complex machines so as to increase productivity and reduce operational costs. The various practices of data science and analytics which are used in all sectors to understand big data and analyze massive data patterns are also detailed in the book.

Preface xix

Acknowledgment xxiii

1 Machine Learning–Based Data Analysis 1
M. Deepika and K. Kalaiselvi

1.1 Introduction 1

1.2 Machine Learning for the Internet of Things Using Data Analysis 4

1.2.1 Computing Framework 6

1.2.2 Fog Computing 6

1.2.3 Edge Computing 6

1.2.4 Cloud Computing 7

1.2.5 Distributed Computing 7

1.3 Machine Learning Applied to Data Analysis 7

1.3.1 Supervised Learning Systems 8

1.3.2 Decision Trees 9

1.3.3 Decision Tree Types 9

1.3.4 Unsupervised Machine Learning 10

1.3.5 Association Rule Learning 10

1.3.6 Reinforcement Learning 10

1.4 Practical Issues in Machine Learning 11

1.5 Data Acquisition 12

1.6 Understanding the Data Formats Used in Data Analysis Applications 13

1.7 Data Cleaning 14

1.8 Data Visualization 15

1.9 Understanding the Data Analysis Problem-Solving Approach 15

1.10 Visualizing Data to Enhance Understanding and Using Neural Networks in Data Analysis 16

1.11 Statistical Data Analysis Techniques 17

1.11.1 Hypothesis Testing 18

1.11.2 Regression Analysis 18

1.12 Text Analysis and Visual and Audio Analysis 18

1.13 Mathematical and Parallel Techniques for Data Analysis 19

1.13.1 Using Map-Reduce 20

1.13.2 Leaning Analysis 20

1.13.3 Market Basket Analysis 21

1.14 Conclusion 21

References 22

2 Machine Learning for Cyber-Immune IoT Applications 25
Suchismita Sahoo and Sushree Sangita Sahoo

2.1 Introduction 25

2.2 Some Associated Impactful Terms 27

2.2.1 IoT 27

2.2.2 IoT Device 28

2.2.3 IoT Service 29

2.2.4 Internet Security 29

2.2.5 Data Security 30

2.2.6 Cyberthreats 31

2.2.7 Cyber Attack 31

2.2.8 Malware 32

2.2.9 Phishing 32

2.2.10 Ransomware 33

2.2.11 Spear-Phishing 33

2.2.12 Spyware 34

2.2.13 Cybercrime 34

2.2.14 IoT Cyber Security 35

2.2.15 IP Address 36

2.3 Cloud Rationality Representation 36

2.3.1 Cloud 36

2.3.2 Cloud Data 37

2.3.3 Cloud Security 38

2.3.4 Cloud Computing 38

2.4 Integration of IoT With Cloud 40

2.5 The Concepts That Rules Over 41

2.5.1 Artificial Intelligent 41

2.5.2 Overview of Machine Learning 41

2.5.2.1 Supervised Learning 41

2.5.2.2 Unsupervised Learning 42

2.5.3 Applications of Machine Learning in Cyber Security 43

2.5.4 Applications of Machine Learning in Cybercrime 43

2.5.5 Adherence of Machine Learning With Cyber Security in Relevance to IoT 43

2.5.6 Distributed Denial-of-Service 44

2.6 Related Work 45

2.7 Methodology 46

2.8 Discussions and Implications 48

2.9 Conclusion 49

References 49

3 Employing Machine Learning Approaches for Predictive Data Analytics in Retail Industry 53
Rakhi Akhare, Sanjivani Deokar, Monika Mangla and Hardik Deshmukh

3.1 Introduction 53

3.2 Related Work 55

3.3 Predictive Data Analytics in Retail 56

3.3.1 ML for Predictive Data Analytics 58

3.3.2 Use Cases 59

3.3.3 Limitations and Challenges 61

3.4 Proposed Model 61

3.4.1 Case Study 63

3.5 Conclusion and Future Scope 68

References 69

4 Emerging Cloud Computing Trends for Business Transformation 71
Prasanta Kumar Mahapatra, Alok Ranjan Tripathy and Alakananda Tripathy

4.1 Introduction 71

4.1.1 Computing Definition Cloud 72

4.1.2 Advantages of Cloud Computing Over On-Premises IT Operation 73

4.1.3 Limitations of Cloud Computing 74

4.2 History of Cloud Computing 74

4.3 Core Attributes of Cloud Computing 75

4.4 Cloud Computing Models 77

4.4.1 Cloud Deployment Model 77

4.4.2 Cloud Service Model 79

4.5 Core Components of Cloud Computing Architecture: Hardware and Software 83

4.6 Factors Need to Consider for Cloud Adoption 84

4.6.1 Evaluating Cloud Infrastructure 84

4.6.2 Evaluating Cloud Provider 85

4.6.3 Evaluating Cloud Security 86

4.6.4 Evaluating Cloud Services 86

4.6.5 Evaluating Cloud Service Level Agreements (SLA) 87

4.6.6 Limitations to Cloud Adoption 87

4.7 Transforming Business Through Cloud 88

4.8 Key Emerging Trends in Cloud Computing 89

4.8.1 Technology Trends 90

4.8.2 Business Models 92

4.8.3 Product Transformation 92

4.8.4 Customer Engagement 92

4.8.5 Employee Empowerment 93

4.8.6 Data Management and Assurance 93

4.8.7 Digitalization 93

4.8.8 Building Intelligence Cloud System 93

4.8.9 Creating Hyper-Converged Infrastructure 94

4.9 Case Study: Moving Data Warehouse to Cloud Boosts Performance for Johnson & Johnson 94

4.10 Conclusion 95

References 96

5 Security of Sensitive Data in Cloud Computing 99
Kirti Wanjale, Monika Mangla and Paritosh Marathe

5.1 Introduction 100

5.1.1 Characteristics of Cloud Computing 100

5.1.2 Deployment Models for Cloud Services 101

5.1.3 Types of Cloud Delivery Models 102

5.2 Data in Cloud 102

5.2.1 Data Life Cycle 103

5.3 Security Challenges in Cloud Computing for Data 105

5.3.1 Security Challenges Related to Data at Rest 106

5.3.2 Security Challenges Related to Data in Use 107

5.3.3 Security Challenges Related to Data in Transit 107

5.4 Cross-Cutting Issues Related to Network in Cloud 108

5.5 Protection of Data 109

5.6 Tighter IAM Controls 114

5.7 Conclusion and Future Scope 117

References 117

6 Cloud Cryptography for Cloud Data Analytics in IoT 119
N. Jayashri and K. Kalaiselvi

6.1 Introduction 120

6.2 Cloud Computing Software Security Fundamentals 120

6.3 Security Management 122

6.4 Cryptography Algorithms 123

6.4.1 Types of Cryptography 123

6.5 Secure Communications 127

6.6 Identity Management and Access Control 133

6.7 Autonomic Security 137

6.8 Conclusion 139

References 139

7 Issues and Challenges of Classical Cryptography in Cloud Computing 143
Amrutanshu Panigrahi, Ajit Kumar Nayak and Rourab Paul

7.1 Introduction 144

7.1.1 Problem Statement and Motivation 145

7.1.2 Contribution 146

7.2 Cryptography 146

7.2.1 Cryptography Classification 147

7.2.1.1 Classical Cryptography 147

7.2.1.2 Homomorphic Encryption 149

7.3 Security in Cloud Computing 150

7.3.1 The Need for Security in Cloud Computing 151

7.3.2 Challenges in Cloud Computing Security 152

7.3.3 Benefits of Cloud Computing Security 153

7.3.4 Literature Survey 154

7.4 Classical Cryptography for Cloud Computing 157

7.4.1 RSA 157

7.4.2 AES 157

7.4.3 DES 158

7.4.4 Blowfish 158

7.5 Homomorphic Cryptosystem 158

7.5.1 Paillier Cryptosystem 159

7.5.1.1 Additive Homomorphic Property 159

7.5.2 RSA Homomorphic Cryptosystem 160

7.5.2.1 Multiplicative Homomorphic Property 160

7.6 Implementation 160

7.7 Conclusion and Future Scope 162

References 162

8 Cloud-Based Data Analytics for Monitoring Smart Environments 167
D. Karthika

8.1 Introduction 167

8.2 Environmental Monitoring for Smart Buildings 169

8.2.1 Smart Environments 169

8.3 Smart Health 171

8.3.1 Description of Solutions in General 171

8.3.2 Detection of Distress 172

8.3.3 Green Protection 173

8.3.4 Medical Preventive/Help 174

8.4 Digital Network 5G and Broadband Networks 174

8.4.1 IoT-Based Smart Grid Technologies 174

8.5 Emergent Smart Cities Communication Networks 175

8.5.1 RFID Technologies 177

8.5.2 Identifier Schemes 177

8.6 Smart City IoT Platforms Analysis System 177

8.7 Smart Management of Car Parking in Smart Cities 178

8.8 Smart City Systems and Services Securing: A Risk-Based Analytical Approach 178

8.9 Virtual Integrated Storage System 179

8.10 Convolutional Neural Network (CNN) 181

8.10.1 IEEE 802.15.4 182

8.10.2 BLE 182

8.10.3 ITU-T G.9959 (Z-Wave) 183

8.10.4 NFC 183

8.10.5 LoRaWAN 184

8.10.6 Sigfox 184

8.10.7 NB-IoT 184

8.10.8 PLC 184

8.10.9 MS/TP 184

8.11 Challenges and Issues 185

8.11.1 Interoperability and Standardization 185

8.11.2 Customization and Adaptation 186

8.11.3 Entity Identification and Virtualization 187

8.11.4 Big Data Issue in Smart Environments 187

8.12 Future Trends and Research Directions in Big Data Platforms for the Internet of Things 188

8.13 Case Study 189

8.14 Conclusion 191

References 191

9 Performance Metrics for Comparison of Heuristics Task Scheduling Algorithms in Cloud Computing Platform 195
Nidhi Rajak and Ranjit Rajak

9.1 Introduction 195

9.2 Workflow Model 197

9.3 System Computing Model 198

9.4 Major Objective of Scheduling 198

9.5 Task Computational Attributes for Scheduling 198

9.6 Performance Metrics 200

9.7 Heuristic Task Scheduling Algorithms 201

9.7.1 Heterogeneous Earliest Finish Time (HEFT) Algorithm 202

9.7.2 Critical-Path-on-a-Processor (CPOP) Algorithm 208

9.7.3 As Late As Possible (ALAP) Algorithm 213

9.7.4 Performance Effective Task Scheduling (PETS) Algorithm 217

9.8 Performance Analysis and Results 220

9.9 Conclusion 224

References 224

10 Smart Environment Monitoring Models Using Cloud-Based Data Analytics: A Comprehensive Study 227
Pradnya S. Borkar and Reena Thakur

10.1 Introduction 228

10.1.1 Internet of Things 229

10.1.2 Cloud Computing 230

10.1.3 Environmental Monitoring 232

10.2 Background and Motivation 234

10.2.1 Challenges and Issues 234

10.2.2 Technologies Used for Designing Cloud-Based Data Analytics 240

10.2.2.1 Communication Technologies 241

10.2.3 Cloud-Based Data Analysis Techniques and Models 243

10.2.3.1 MapReduce for Data Analysis 243

10.2.3.2 Data Analysis Workflows 246

10.2.3.3 NoSQL Models 247

10.2.4 Data Mining Techniques 248

10.2.5 Machine Learning 251

10.2.5.1 Significant Importance of Machine Learning and Its Algorithms 253

10.2.6 Applications 253

10.3 Conclusion 261

References 262

11 Advancement of Machine Learning and Cloud Computing in the Field of Smart Health Care 273
Aradhana Behura, Shibani Sahu and Manas Ranjan Kabat

11.1 Introduction 274

11.2 Survey on Architectural WBAN 278

11.3 Suggested Strategies 280

11.3.1 System Overview 280

11.3.2 Motivation 281

11.3.3 DSCB Protocol 281

11.3.3.1 Network Topology 282

11.3.3.2 Starting Stage 282

11.3.3.3 Cluster Evolution 282

11.3.3.4 Sensed Information Stage 283

11.3.3.5 Choice of Forwarder Stage 283

11.3.3.6 Energy Consumption as Well as Routing Stage 285

11.4 CNN-Based Image Segmentation (UNet Model) 287

11.5 Emerging Trends in IoT Healthcare 290

11.6 Tier Health IoT Model 294

11.7 Role of IoT in Big Data Analytics 294

11.8 Tier Wireless Body Area Network Architecture 296

11.9 Conclusion 303

References 303

12 Study on Green Cloud Computing—A Review 307
Meenal Agrawal and Ankita Jain

12.1 Introduction 307

12.2 Cloud Computing 308

12.2.1 Cloud Computing: On-Request Outsourcing-Pay-as-You-Go 308

12.3 Features of Cloud Computing 309

12.4 Green Computing 309

12.5 Green Cloud Computing 309

12.6 Models of Cloud Computing 310

12.7 Models of Cloud Services 310

12.8 Cloud Deployment Models 311

12.9 Green Cloud Architecture 312

12.10 Cloud Service Providers 312

12.11 Features of Green Cloud Computing 313

12.12 Advantages of Green Cloud Computing 313

12.13 Limitations of Green Cloud Computing 314

12.14 Cloud and Sustainability Environmental 315

12.15 Statistics Related to Cloud Data Centers 315

12.16 The Impact of Data Centers on Environment 315

12.17 Virtualization Technologies 316

12.18 Literature Review 316

12.19 The Main Objective 318

12.20 Research Gap 319

12.21 Research Methodology 319

12.22 Conclusion and Suggestions 320

12.23 Scope for Further Research 320

References 321

13 Intelligent Reclamation of Plantae Affliction Disease 323
Reshma Banu, G.F Ali Ahammed and Ayesha Taranum

13.1 Introduction 324

13.2 Existing System 327

13.3 Proposed System 327

13.4 Objectives of the Concept 328

13.5 Operational Requirements 328

13.6 Non-Operational Requirements 329

13.7 Depiction Design Description 330

13.8 System Architecture 330

13.8.1 Module Characteristics 331

13.8.2 Convolutional Neural System 332

13.8.3 User Application 332

13.9 Design Diagrams 333

13.9.1 High-Level Design 333

13.9.2 Low-Level Design 333

13.9.3 Test Cases 335

13.10 Comparison and Screenshot 335

13.11 Conclusion 342

References 342

14 Prediction of Stock Market Using Machine Learning–Based Data Analytics 347
Maheswari P. and Jaya A.

14.1 Introduction of Stock Market 348

14.1.1 Impact of Stock Prices 349

14.2 Related Works 350

14.3 Financial Prediction Systems Framework 352

14.3.1 Conceptual Financial Prediction Systems 352

14.3.2 Framework of Financial Prediction Systems Using Machine Learning 353

14.3.2.1 Algorithm to Predicting the Closing Price of the Given Stock Data Using Linear Regression 355

14.3.3 Framework of Financial Prediction Systems Using Deep Learning 355

14.3.3.1 Algorithm to Predict the Closing Price of the Given Stock Using Long Short-Term Memory 356

14.4 Implementation and Discussion of Result 357

14.4.1 Pharmaceutical Sector 357

14.4.1.1 Cipla Limited 357

14.4.1.2 Torrent Pharmaceuticals Limited 359

14.4.2 Banking Sector 359

14.4.2.1 ICICI Bank 359

14.4.2.2 State Bank of India 359

14.4.3 Fast-Moving Consumer Goods Sector 362

14.4.3.1 ITC 363

14.4.3.2 Hindustan Unilever Limited 363

14.4.4 Power Sector 363

14.4.4.1 Adani Power Limited 363

14.4.4.2 Power Grid Corporation of India Limited 364

14.4.5 Automobiles Sector 368

14.4.5.1 Mahindra & Mahindra Limited 368

14.4.5.2 Maruti Suzuki India Limited 368

14.4.6 Comparison of Prediction Using Linear Regression Model and Long-Short-Term Memory Model 368

14.5 Conclusion 371

14.5.1 Future Enhancement 372

References 372

Web Citations 373

15 Pehchaan: Analysis of the ‘Aadhar Dataset’ to Facilitate a Smooth and Efficient Conduct of the Upcoming NPR 375
Soumyadev Mukherjee, Harshit Anand, Nishan Acharya, Subham Char, Pritam Ghosh and MinakhiRout

15.1 Introduction 376

15.2 Basic Concepts 377

15.3 Study of Literature Survey and Technology 380

15.4 Proposed Model 381

15.5 Implementation and Results 383

15.6 Conclusion 389

References 389

16 Deep Learning Approach for Resource Optimization in Blockchain, Cellular Networks, and IoT: Open Challenges and Current Solutions 391
Upinder Kaur and Shalu

16.1 Introduction 392

16.1.1 Aim 393

16.1.2 Research Contribution 395

16.1.3 Organization 396

16.2 Background 396

16.2.1 Blockchain 397

16.2.2 Internet of Things (IoT) 398

16.2.3 5G Future Generation Cellular Networks 398

16.2.4 Machine Learning and Deep Learning Techniques 399

16.2.5 Deep Reinforcement Learning 399

16.3 Deep Learning for Resource Management in Blockchain, Cellular, and IoT Networks 401

16.3.1 Resource Management in Blockchain for 5G Cellular Networks 402

16.3.2 Deep Learning Blockchain Application for Resource Management in IoT Networks 402

16.4 Future Research Challenges 413

16.4.1 Blockchain Technology 413

16.4.1.1 Scalability 414

16.4.1.2 Efficient Consensus Protocols 415

16.4.1.3 Lack of Skills and Experts 415

16.4.2 IoT Networks 416

16.4.2.1 Heterogeneity of IoT and 5G Data 416

16.4.2.2 Scalability Issues 416

16.4.2.3 Security and Privacy Issues 416

16.4.3 5G Future Generation Networks 416

16.4.3.1 Heterogeneity 416

16.4.3.2 Security and Privacy 417

16.4.3.3 Resource Utilization 417

16.4.4 Machine Learning and Deep Learning 417

16.4.4.1 Interpretability 418

16.4.4.2 Training Cost for ML and DRL Techniques 418

16.4.4.3 Lack of Availability of Data Sets 418

16.4.4.4 Avalanche Effect for DRL Approach 419

16.4.5 General Issues 419

16.4.5.1 Security and Privacy Issues 419

16.4.5.2 Storage 419

16.4.5.3 Reliability 420

16.4.5.4 Multitasking Approach 420

16.5 Conclusion and Discussion 420

References 422

17 Unsupervised Learning in Accordance With New Aspects of Artificial Intelligence 429
Riya Sharma, Komal Saxena and Ajay Rana

17.1 Introduction 430

17.2 Applications of Machine Learning in Data Management Possibilities 431

17.2.1 Terminology of Basic Machine Learning 432

17.2.2 Rules Based on Machine Learning 434

17.2.3 Unsupervised vs. Supervised Methodology 434

17.3 Solutions to Improve Unsupervised Learning Using Machine Learning 436

17.3.1 Insufficiency of Labeled Data 436

17.3.2 Overfitting 437

17.3.3 A Closer Look Into Unsupervised Algorithms 437

17.3.3.1 Reducing Dimensionally 437

17.3.3.2 Principal Component Analysis 438

17.3.4 Singular Value Decomposition (SVD) 439

17.3.4.1 Random Projection 439

17.3.4.2 Isomax 439

17.3.5 Dictionary Learning 439

17.3.6 The Latent Dirichlet Allocation 440

17.4 Open Source Platform for Cutting Edge Unsupervised Machine Learning 440

17.4.1 TensorFlow 441

17.4.2 Keras 441

17.4.3 Scikit-Learn 441

17.4.4 Microsoft Cognitive Toolkit 442

17.4.5 Theano 442

17.4.6 Caffe 442

17.4.7 Torch 442

17.5 Applications of Unsupervised Learning 443

17.5.1 Regulation of Digital Data 443

17.5.2 Machine Learning in Voice Assistance 443

17.5.3 For Effective Marketing 444

17.5.4 Advancement of Cyber Security 444

17.5.5 Faster Computing Power 444

17.5.6 The Endnote 445

17.6 Applications Using Machine Learning Algos 445

17.6.1 Linear Regression 445

17.6.2 Logistic Regression 446

17.6.3 Decision Tree 446

17.6.4 Support Vector Machine (SVM) 446

17.6.5 Naive Bayes 446

17.6.6 K-Nearest Neighbors 447

17.6.7 K-Means 447

17.6.8 Random Forest 447

17.6.9 Dimensionality Reduction Algorithms 448

17.6.10 Gradient Boosting Algorithms 448

References 449

18 Predictive Modeling of Anthropomorphic Gamifying Blockchain-Enabled Transitional Healthcare System 461
Deepa Kumari, B.S.A.S. Rajita, Medindrao Raja Sekhar, Ritika Garg and Subhrakanta Panda

18.1 Introduction 462

18.1.1 Transitional Healthcare Services and Their Challenges 462

18.2 Gamification in Transitional Healthcare: A New Model 463

18.2.1 Anthropomorphic Interface With Gamification 464

18.2.2 Gamification in Blockchain 465

18.2.3 Anthropomorphic Gamification in Blockchain: Motivational Factors 466

18.3 Existing Related Work 468

18.4 The Framework 478

18.4.1 Health Player 479

18.4.2 Data Collection 480

18.4.3 Anthropomorphic Gamification Layers 480

18.4.4 Ethereum 480

18.4.4.1 Ethereum-Based Smart Contracts for Healthcare 481

18.4.4.2 Installation of Ethereum Smart Contract 481

18.4.5 Reward Model 482

18.4.6 Predictive Models 482

18.5 Implementation 483

18.5.1 Methodology 483

18.5.2 Result Analysis 484

18.5.3 Threats to the Validity 486

18.6 Conclusion 487

References 487

Index 491