Cognitive Analytics and Reinforcement Learning

Elakkiya R., PhD, is an assistant professor in the Department of Computer Science at the Birla Institute of Technology & Science in Dubai, UAE. She received a Ph.D. in 2018 and did her doctoral research in sign language recognition. Her research focuses on addressing trending issues in computer science, mathematics, and engineering. Along with publishing two books, 50 research articles, and three patents, she is an editor of the Information Engineering and Applied Computing journal. She received the Young Achiever Award in 2019. Subramaniyaswamy V., PhD, is a professor at the School of Computing at SASTRA Deemed University in Tamilnadu, India. He received a Ph.D. from Anna University in 2013. His research areas include cognitive computing, reinforced learning, recommender systems, artificial intelligence, and the Internet of Things. He has published more than 200 research papers and book chapters in international journals and books.

Preface xiii

Part I: Cognitive Analytics in Continual Learning 1

1 Cognitive Analytics in Continual Learning: A New Frontier in Machine Learning Research 3
Renuga Devi T., Muthukumar K., Sujatha M. and Ezhilarasie R.

1.1 Introduction 4

1.2 Evolution of Data Analytics 5

1.3 Conceptual View of Cognitive Systems 7

1.4 Elements of Cognitive Systems 7

1.5 Features, Scope, and Characteristics of Cognitive System 9

1.6 Cognitive System Design Principles 12

1.7 Backbone of Cognitive System Learning/Building Process 13

1.8 Cognitive Systems vs. AI 17

1.9 Use Cases 18

1.10 Conclusion 25

2 Cognitive Computing System-Based Dynamic Decision Control for Smart City Using Reinforcement Learning Model 29
Sasikumar A., Logesh Ravi, Malathi Devarajan, Hossam Kotb and Subramaniyaswamy V.

2.1 Introduction 30

2.2 Smart City Applications 32

2.3 Related Work 36

2.4 Proposed Cognitive Computing RL Model 39

2.5 Simulation Results 45

2.6 Conclusion 47

3 Deep Recommender System for Optimizing Debt Collection Using Reinforcement Learning 51
Keerthana S., Elakkiya R. and Santhi B.

3.1 Introduction 52

3.2 Terminologies in RL 54

3.3 Different Forms of RL 57

3.4 Related Works 59

3.5 Proposed Methodology 62

3.6 Result Analysis 66

3.7 Conclusion 68

Part II: Computational Intelligence of Reinforcement Learning 73

4 Predicting Optimal Moves in Chess Board Using Artificial Intelligence 75
Thangaramya K., Logeswari G., Sudhakaran G., Aadharsh R., Bhuvaneshwar S., Dheepakraaj R. and Parasu Sunny

4.1 Introduction 76

4.2 Literature Survey 83

4.3 Proposed System 88

4.4 Results and Discussion 95

4.5 Conclusion 98

5 Virtual Makeup Try-On System Using Cognitive Learning 103
Divija Sanapala and J. Angel Arul Jothi

5.1 Introduction 104

5.2 Related Works 105

5.3 Proposed Method 111

5.4 Experimental Results and Analysis 118

5.5 Conclusion 119

6 Reinforcement Learning for Demand Forecasting and Customized Services 123
Sini Raj Pulari, T. S. Murugesh, Shriram K. Vasudevan and Akshay Bhuvaneswari Ramakrishnan

6.1 Introduction 124

6.2 RL Fundamentals 125

6.3 Demand Forecasting and Customized Services 130

6.4 eMart: Forecasting of a Real-World Scenario 131

6.5 Conclusion and Future Works 133

7 COVID-19 Detection through CT Scan Image Analysis: A Transfer Learning Approach with Ensemble Technique 135
P. Padmakumari, S. Vidivelli and P. Shanthi

7.1 Introduction 136

7.2 Literature Survey 137

7.3 Methodology 140

7.4 Results and Discussion 144

7.5 Conclusion 148

8 Paddy Leaf Classification Using Computational Intelligence 151
S. Vidivelli, P. Padmakumari and P. Shanthi

8.1 Introduction 151

8.2 Literature Review 153

8.3 Methodology 155

8.4 Results and Discussion 160

8.5 Conclusion 163

9 An Artificial Intelligent Methodology to Classify Knee Joint Disorder Using Machine Learning and Image Processing Techniques 167
M. Sharmila Begum, A. V. M. B. Aruna, A. Balajee and R. Murugan

9.1 Introduction 168

9.2 Literature Survey 169

9.3 Proposed Methodology 171

9.4 Experimental Results 182

9.5 Conclusion 185

Part III: Advancements in Cognitive Computing: Practical Implementations 189

10 Fuzzy-Based Efficient Resource Allocation and Schedulingin a Computational Distributed Environment 191
Suguna M., Logesh R. and Om Kumar C. U.

10.1 Introduction 192

10.2 Proposed System 193

10.3 Experimental Results 196

10.4 Conclusion 201

11 A Lightweight CNN Architecture for Prediction of Plant Diseases 203
Sasikumar A., Logesh Ravi, Malathi Devarajan, Selvalakshmi A. and Subramaniyaswamy V.

11.1 Introduction 204

11.2 Precision Agriculture 206

11.3 Related Work 211

11.4 Proposed Architecture for Prediction of Plant Diseases 214

11.5 Experimental Results and Discussion 217

11.6 Conclusion 219

12 Investigation of Feature Fusioned Dictionary Learning Model for Accurate Brain Tumor Classification 223
P. Saravanan, V. Indragandhi, R. Elakkiya and V. Subramaniyaswamy

12.1 Introduction 224

12.2 Literature Review 227

12.3 Proposed Feature Fusioned Dictionary Learning Model 229

12.4 Experimental Results and Discussion 232

12.5 Conclusion and Future Work 235

13 Cognitive Analytics-Based Diagnostic Solutions in Healthcare Infrastructure 239
Akshay Bhuvaneswari Ramakrishnan, T. S. Murugesh, Sini Raj Pulari and Shriram K. Vasudevan

13.1 Introduction 240

13.2 Cognitive Computing in Action 241

13.3 Increasing the Capabilities of Smart Cities Using Cognitive Computing 243

13.4 Cognitive Solutions Revolutionizing the Healthcare Industry 246

13.5 Application of Cognitive Computing to Smart Healthcare in Seoul, South Korea (Case Study) 249

13.6 Conclusion and Future Work 251

14 Automating ESG Score Rating with Reinforcement Learning for Responsible Investment 253
Mohan Teja G., Logesh Ravi, Malathi Devarajan and Subramaniyaswamy V.

14.1 Introduction 254

14.2 Comparative Study 259

14.3 Literature Survey 263

14.4 Methods 266

14.5 Experimental Results 273

14.6 Discussion 277

14.7 Conclusion 278

15 Reinforcement Learning in Healthcare: Applications and Challenges 283
Tribhangin Dichpally, Yatish Wutla and Sheela Jayachandran

15.1 Introduction 283

15.2 Structure of Reinforcement Learning 285

15.3 Applications 289

15.4 Challenges 310

15.5 Conclusion 312

16 Cognitive Computing in Smart Cities and Healthcare 317
Dave Mahadevprasad V., Ondippili Rudhra and Sanjeev Kumar Singh

16.1 Introduction 318

16.2 Machine Learning Inventions and Its Applications 322

16.3 What is Reinforcement Learning and Cognitive Computing? 326

16.4 Cognitive Computing 327

16.5 Data Expressed by the Healthcare and Smart Cities 331

16.6 Use of Computers to Analyze the Data and Predict the Outcome 332

16.7 Machine Learning Algorithm 332

16.8 How to Perform Machine Learning? 336

16.9 Machine Learning Algorithm 338

16.10 Common Libraries for Machine Learning Projects 340

16.11 Supervised Learning Algorithm 341

16.12 Future of the Healthcare 343

16.13 Development of Model and Its Workflow 346

16.13.1 Types of Evaluation 347

16.14 Future of Smart Cities 347

16.15 Case Study I 349

16.16 Case Study II 352

16.17 Case Study III 355

16.18 Case Study IV 358

16.19 Conclusion 360

References 360

Index 365