Cognitive Engineering for Next Generation Computing

The cognitive approach to the IoT provides connectivity to everyone and everything since IoT connected devices are known to increase rapidly. When the IoT is integrated with cognitive technology, performance is improved, and smart intelligence is obtained. Discussed in this book are different types of datasets with structured content based on cognitive systems. The IoT gathers the information from the real time datasets through the internet, where the IoT network connects with multiple devices.

This book mainly concentrates on providing the best solutions to existing real-time issues in the cognitive domain. Healthcare-based, cloud-based and smart transportation-based applications in the cognitive domain are addressed. The data integrity and security aspects of the cognitive computing main are also thoroughly discussed along with validated results.

KOLLA BHANU PRAKASH is Professor and Research Group Head for Artificial Intelligence and Data Science Research Group in CSE Department, K L University, Andhra Pradesh, India. He received his MSc and MPhil in Physics from Acharya Nagarjuna University and his ME and PhD in Computer Science & Engineering from Sathyabama University, Chennai, India. Dr. Prakash has 14+ years of experience working in academia, research, and teaching. He has published multiple SCI journal articles as well as been granted 5 patents.

G. R. KANAGACHIDAMBARESAN received his BE degree in Electrical and Electronics Engineering from Anna University in 2010; ME in Pervasive Computing Technologies in Anna University in 2012, and his PhD in Anna University Chennai in 2017. He is currently an associate professor, Department of CSE, Veltech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology.

SRIKANTH VEMURU is a professor in the Department of Computer Science and Engineering, K L University. He received his PhD degree from Acharya Nagarjuna University (ANU) in 2011. He has more than 17 years of academic experience and in the software industry, and has published more than over 60 research papers in SCI journals and flagship conferences.

VAMSIDHAR ENIREDDY is an associate professor in CSE Department, K L University, Andhra Pradesh, India. He received his PhD from JNTU Kakinada, India. Dr. Enireddy has 17+years of experience working in academia, research, and teaching. He has authored over 28 research papers in various national and international journals and conferences as well as been granted 3 patents and 1 patent filed.

Preface xvii

Acknowledgments xix

1 INTRODUCTION TO COGNITIVE COMPUTING 1

Vamsidhar Enireddy, Sagar Imambi and C. Karthikeyan

1.1 Introduction: Definition of Cognition, Cognitive Computing 1

1.2 Defining and Understanding Cognitive Computing 2

1.3 Cognitive Computing Evolution and Importance 6

1.4 Difference Between Cognitive Computing and Artificial Intelligence 8

1.5 The Elements of a Cognitive System 11

1.5.1 Infrastructure and Deployment Modalities 11

1.5.2 Data Access, Metadata, and Management Services 12

1.5.3 The Corpus, Taxonomies, and Data Catalogs 12

1.5.4 Data Analytics Services 12

1.5.5 Constant Machine Learning 13

1.5.6 Components of a Cognitive System 13

1.5.7 Building the Corpus 14

1.5.8 Corpus Administration Governing and Protection Factors 16

1.6 Ingesting Data Into Cognitive System 17

1.6.1 Leveraging Interior and Exterior Data Sources 17

1.6.2 Data Access and Feature Extraction 18

1.7 Analytics Services 19

1.8 Machine Learning 22

1.9 Machine Learning Process 24

1.9.1 Data Collection 24

1.9.2 Data Preparation 24

1.9.3 Choosing a Model 24

1.9.4 Training the Model 24

1.9.5 Evaluate the Model 25

1.9.6 Parameter Tuning 25

1.9.7 Make Predictions 25

1.10 Machine Learning Techniques 25

1.10.1 Supervised Learning 25

1.10.2 Unsupervised Learning 27

1.10.3 Reinforcement Learning 27

1.10.4 The Significant Challenges in Machine Learning 28

1.11 Hypothesis Space 30

1.11.1 Hypothesis Generation 31

1.11.2 Hypotheses Score 32

1.12 Developing a Cognitive Computing Application 32

1.13 Building a Health Care Application 35

1.13.1 Healthcare Ecosystem Constituents 35

1.13.2 Beginning With a Cognitive Healthcare Application 37

1.13.3 Characterize the Questions Asked by the Clients 37

1.13.4 Creating a Corpus and Ingesting the Content 38

1.13.5 Training the System 38

1.13.6 Applying Cognition to Develop Health and Wellness 39

1.13.7 Welltok 39

1.13.8 CaféWell Concierge in Action 41

1.14 Advantages of Cognitive Computing 42

1.15 Features of Cognitive Computing 43

1.16 Limitations of Cognitive Computing 44

1.17 Conclusion 47

References 47

2 MACHINE LEARNING AND BIG DATA IN CYBER-PHYSICAL SYSTEM: METHODS, APPLICATIONS AND CHALLENGES 49

Janmenjoy Nayak, P. Suresh Kumar, Dukka Karun Kumar Reddy, Bighnaraj Naik and Danilo Pelusi

2.1 Introduction 50

2.2 Cyber-Physical System Architecture 52

2.3 Human-in-the-Loop Cyber-Physical Systems (HiLCPS) 53

2.4 Machine Learning Applications in CPS 55

2.4.1 K-Nearest Neighbors (K-NN) in CPS 55

2.4.2 Support Vector Machine (SVM) in CPS 58

2.4.3 Random Forest (RF) in CPS 61

2.4.4 Decision Trees (DT) in CPS 63

2.4.5 Linear Regression (LR) in CPS 65

2.4.6 Multi-Layer Perceptron (MLP) in CPS 66

2.4.7 Naive Bayes (NB) in CPS 70

2.5 Use of IoT in CPS 70

2.6 Use of Big Data in CPS 72

2.7 Critical Analysis 77

2.8 Conclusion 83

References 84

3 HEMOSMART: A NON-INVASIVE DEVICE AND MOBILE APP FOR ANEMIA DETECTION 93

J.A.D.C.A. Jayakody, E.A.G.A. Edirisinghe and S.Lokuliyana

3.1 Introduction 94

3.1.1 Background 94

3.1.2 Research Objectives 96

3.1.3 Research Approach 97

3.1.4 Limitations 98

3.2 Literature Review 98

3.3 Methodology 101

3.3.1 Methodological Approach 101

3.3.1.1 Select an Appropriate Camera 102

3.3.1.2 Design the Lighting System 102

3.3.1.3 Design the Electronic Circuit 104

3.3.1.4 Design the Prototype 104

3.3.1.5 Collect Data and Develop the Algorithm 104

3.3.1.6 Develop the Prototype 106

3.3.1.7 Mobile Application Development 106

3.3.1.8 Completed Device 107

3.3.1.9 Methods of Data Collection 109

3.3.2 Methods of Analysis 109

3.4 Results 110

3.4.1 Impact of Project Outcomes 110

3.4.2 Results Obtained During the Methodology 111

3.4.2.1 Select an Appropriate Camera 111

3.4.2.2 Design the Lighting System 112

3.5 Discussion 112

3.6 Originality and Innovativeness of the Research 116

3.6.1 Validation and Quality Control of Methods 117

3.6.2 Cost-Effectiveness of the Research 117

3.7 Conclusion 117

References 117

4 ADVANCED COGNITIVE MODELS AND ALGORITHMS 121

J. Ramkumar, M. Baskar and B. Amutha

4.1 Introduction 122

4.2 Microsoft Azure Cognitive Model 122

4.2.1 AI Services Broaden in Microsoft Azure 125

4.3 IBM Watson Cognitive Analytics 126

4.3.1 Cognitive Computing 126

4.3.2 Defining Cognitive Computing via IBM Watson Interface 127

4.3.2.1 Evolution of Systems Towards Cognitive Computing 128

4.3.2.2 Main Aspects of IBM Watson 129

4.3.2.3 Key Areas of IBM Watson 130

4.3.3 IBM Watson Analytics 130

4.3.3.1 IBM Watson Features 131

4.3.3.2 IBM Watson DashDB 131

4.4 Natural Language Modeling 132

4.4.1 NLP Mainstream 132

4.4.2 Natural Language Based on Cognitive Computation 134

4.5 Representation of Knowledge Models 134

4.6 Conclusion 137

References 138

5 IPARKING—SMART WAY TO AUTOMATE THE MANAGEMENT OF THE PARKING SYSTEM FOR A SMART CITY 141

J.A.D.C.A. Jayakody, E.A.G.A. Edirisinghe, S.A.H.M. Karunanayaka, E.M.C.S. Ekanayake, H.K.T.M. Dikkumbura and L.A.I.M. Bandara

5.1 Introduction 142

5.2 Background & Literature Review 144

5.2.1 Background 144

5.2.2 Review of Literature 145

5.3 Research Gap 151

5.4 Research Problem 151

5.5 Objectives 153

5.6 Methodology 154

5.6.1 Lot Availability and Occupancy Detection 154

5.6.2 Error Analysis for GPS (Global Positioning System) 155

5.6.3 Vehicle License Plate Detection System 156

5.6.4 Analyze Differential Parking Behaviors and Pricing 156

5.6.5 Targeted Digital Advertising 157

5.6.6 Used Technologies 157

5.6.7 Specific Tools and Libraries 158

5.7 Testing and Evaluation 159

5.8 Results 161

5.9 Discussion 162

5.10 Conclusion 164

References 165

6 COGNITIVE CYBER-PHYSICAL SYSTEM APPLICATIONS 167

John A., Senthilkumar Mohan and D. Maria Manuel Vianny

6.1 Introduction 168

6.2 Properties of Cognitive Cyber-Physical System 169

6.3 Components of Cognitive Cyber-Physical System 170

6.4 Relationship Between Cyber-Physical System for Human–Robot 171

6.5 Applications of Cognitive Cyber-Physical System 172

6.5.1 Transportation 172

6.5.2 Industrial Automation 173

6.5.3 Healthcare and Biomedical 176

6.5.4 Clinical Infrastructure 178

6.5.5 Agriculture 180

6.6 Case Study: Road Management System Using CPS 181

6.6.1 Smart Accident Response System for Indian City 182

6.7 Conclusion 184

References 185

7 COGNITIVE COMPUTING 189

T Gunasekhar and Marella Surya Teja

7.1 Introduction 189

7.2 Evolution of Cognitive System 191

7.3 Cognitive Computing Architecture 193

7.3.1 Cognitive Computing and Internet of Things 194

7.3.2 Cognitive Computing and Big Data Analysis 197

7.3.3 Cognitive Computing and Cloud Computing 200

7.4 Enabling Technologies in Cognitive Computing 202

7.4.1 Cognitive Computing and Reinforcement Learning 202

7.4.2 Cognitive Computive and Deep Learning 204

7.4.2.1 Rational Method and Perceptual Method 205

7.4.2.2 Cognitive Computing and Image Understanding 207

7.5 Applications of Cognitive Computing 209

7.5.1 Chatbots 209

7.5.2 Sentiment Analysis 210

7.5.3 Face Detection 211

7.5.4 Risk Assessment 211

7.6 Future of Cognitive Computing 212

7.7 Conclusion 214

References 215

8 TOOLS USED FOR RESEARCH IN COGNITIVE ENGINEERING AND CYBER PHYSICAL SYSTEMS 219

Ajita Seth

8.1 Cyber Physical Systems 219

8.2 Introduction: The Four Phases of Industrial Revolution 220

8.3 System 221

8.4 Autonomous Automobile System 221

8.4.1 The Timeline 222

8.5 Robotic System 223

8.6 Mechatronics 225

References 228

9 ROLE OF RECENT TECHNOLOGIES IN COGNITIVE SYSTEMS 231

V. Pradeep Kumar, L. Pallavi and Kolla Bhanu Prakash

9.1 Introduction 232

9.1.1 Definition and Scope of Cognitive Computing 232

9.1.2 Architecture of Cognitive Computing 233

9.1.3 Features and Limitations of Cognitive Systems 234

9.2 Natural Language Processing for Cognitive Systems 236

9.2.1 Role of NLP in Cognitive Systems 236

9.2.2 Linguistic Analysis 238

9.2.3 Example Applications Using NLP With Cognitive Systems 240

9.3 Taxonomies and Ontologies of Knowledge Representation for Cognitive Systems 241

9.3.1 Taxonomies and Ontologies and Their Importance in Knowledge Representation 242

9.3.2 How to Represent Knowledge in Cognitive Systems? 243

9.3.3 Methodologies Used for Knowledge Representation in Cognitive Systems 247

9.4 Support of Cloud Computing for Cognitive Systems 248

9.4.1 Importance of Shared Resources of Distributed Computing in Developing Cognitive Systems 248

9.4.2 Fundamental Concepts of Cloud Used in Building Cognitive Systems 249

9.5 Cognitive Analytics for Automatic Fraud Detection Using Machine Learning and Fuzzy Systems 254

9.5.1 Role of Machine Learning Concepts in Building Cognitive Analytics 255

9.5.2 Building Automated Patterns for Cognitive Analytics Using Fuzzy Systems 255

9.6 Design of Cognitive System for Healthcare Monitoring in Detecting Diseases 256

9.6.1 Role of Cognitive System in Building Clinical Decision System 257

9.7 Advanced High Standard Applications Using Cognitive Computing 259

9.8 Conclusion 262

References 263

10 QUANTUM META-HEURISTICS AND APPLICATIONS 265

Kolla Bhanu Prakash

10.1 Introduction 265

10.2 What is Quantum Computing? 267

10.3 Quantum Computing Challenges 268

10.4 Meta-Heuristics and Quantum Meta-Heuristics Solution Approaches 271

10.5 Quantum Meta-Heuristics Algorithms With Application Areas 273

10.5.1 Quantum Meta-Heuristics Applications for Power Systems 277

10.5.2 Quantum Meta-Heuristics Applications for Image Analysis 281

10.5.3 Quantum Meta-Heuristics Applications for Big Data or Data Mining 282

10.5.4 Quantum Meta-Heuristics Applications for Vehicular Trafficking 285

10.5.5 Quantum Meta-Heuristics Applications for Cloud Computing 286

10.5.6 Quantum Meta-Heuristics Applications for Bioenergy or Biomedical Systems 287

10.5.7 Quantum Meta-Heuristics Applications for Cryptography or Cyber Security 287

10.5.8 Quantum Meta-Heuristics Applications for Miscellaneous Domain 288

References 291

11 ENSURING SECURITY AND PRIVACY IN IOT FOR HEALTHCARE APPLICATIONS 299

Anjali Yeole and D.R. Kalbande

11.1 Introduction 299

11.2 Need of IoT in Healthcare 300

11.2.1 Available Internet of Things Devices for Healthcare 301

11.3 Literature Survey on an IoT-Aware Architecture for Smart Healthcare Systems 303

11.3.1 Cyber-Physical System (CPS) for e-Healthcare 303

11.3.2 IoT-Enabled Healthcare With REST-Based Services 304

11.3.3 Smart Hospital System 304

11.3.4 Freescale Home Health Hub Reference Platform 305

11.3.5 A Smart System Connecting e-Health Sensors and Cloud 305

11.3.6 Customizing 6LoWPAN Networks Towards IoT-Based Ubiquitous Healthcare Systems 305

11.4 IoT in Healthcare: Challenges and Issues 306

11.4.1 Challenges of the Internet of Things for Healthcare 306

11.4.2 IoT Interoperability Issues 308

11.4.3 IoT Security Issues 308

11.4.3.1 Security of IoT Sensors 309

11.4.3.2 Security of Data Generated by Sensors 309

11.4.3.3 LoWPAN Networks Healthcare Systems and its Attacks 309

11.5 Proposed System: 6LoWPAN and COAP Protocol-Based IoT System for Medical Data Transfer by Preserving Privacy of Patient 310

11.6 Conclusion 312

References 312

12 EMPOWERING SECURED OUTSOURCING IN CLOUD STORAGE THROUGH DATA INTEGRITY VERIFICATION 315

C. Saranya Jothi, Carmel Mary Belinda and N. Rajkumar

12.1 Introduction 315

12.1.1 Confidentiality 316

12.1.2 Availability 316

12.1.3 Information Uprightness 316

12.2 Literature Survey 316

12.2.1 PDP 316

12.2.1.1 Privacy-Preserving PDP Schemes 317

12.2.1.2 Efficient PDP 317

12.2.2 POR 317

12.2.3 HAIL 318

12.2.4 RACS 318

12.2.5 FMSR 318

12.3 System Design 319

12.3.1 Design Considerations 319

12.3.2 System Overview 320

12.3.3 Workflow 320

12.3.4 System Description 321

12.3.4.1 System Encoding 321

12.3.4.2 Decoding 322

12.3.4.3 Repair and Check 323

12.4 Implementation and Result Discussion 324

12.4.1 Creating Containers 324

12.4.2 File Chunking 324

12.4.3 XORing Partitions 326

12.4.4 Regeneration of File 326

12.4.5 Reconstructing a Node 327

12.4.6 Cloud Storage 327

12.4.6.1 NC-Cloud 327

12.4.6.2 Open Swift 329

12.5 Performance 330

12.6 Conclusion 332

References 333

Index 335