Wellness Management Powered by AI Technologies

Bharat Bhushan, PhD, is an assistant professor in the Department of Computer Science and Engineering, School of Engineering and Technology, Sharda University, Greater Noida, India. He has published more than 150 research papers, contributed over 30 book chapters, and edited 20 books. Akib Khanday, PhD, is a post-doctoral research fellow in the Department of Computer Science and Software Engineering-CIT, United Arab Emirates University, Abu Dhabi, United Arab Emirates. His research interests include computational social sciences, natural language processing (NLP), and machine/deep learning. Khursheed Aurangzeb, PhD, is an associate professor in the Department of Computer Engineering, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia. Over his 15 years of research, he has been involved in several projects related to machine/deep learning and embedded systems. His research interests focus on computer architecture, signal processing, and wireless sensor networks. Sudhir Kumar Sharma, PhD, is a professor and head of the Department of Computer Science at the Institute of Information Technology & Management, affiliated with GGSIPU, New Delhi, India. His research interests include machine learning, data mining, and security. He has published more than 60 research papers in various international journals and conferences and is the author of seven books in the fields of IoT, wireless sensor networks (WSN), and blockchain. Parma Nand, PhD, is the dean of the School of Engineering and Technology, Sharda University, Greater Noida, India. His expertise includes wireless and sensor networks, cryptography, algorithms, and computer graphics. He has published more than 85 papers in peer-reviewed journals and filed two patents.

• Preface xv1 Exploring Functional Modules Using Co-Clustering of Protein Interaction Networks 1R. Gowri and R. Rathipriya1.1 Introduction 21.2 Related Works 41.3 Basic Terminologies 91.3.1 Scientific Terms Used 101.4 Existing Methods 121.4.1 Binary Co-Clustering Approaches 131.4.1.1 Binary Inclusion-Maximal Algorithm 131.4.1.2 xMotif Algorithm 141.5 About Dataset 151.5.1 Protein Interaction Networks 151.5.1.1 STRING Repository 161.5.2 Protein Complex Dataset 171.5.2.1 CORUM Database 171.6 Experimental Environment 181.6.1 MapReduce Framework 181.7 Validation Measures 191.7.1 Match Score Measure 191.7.2 Functional Coherence 201.8 Biological Significances 211.9 Proposed Co-Clustering Approach: MR-CoC 221.9.1 SCoC for Non-Symmetric Matrix 221.9.1.1 Toy Example: SCoCnsym 221.9.1.2 Synthetic Dataset Description 241.9.1.3 Experimental Analysis: SCoC nsym 251.9.2 Randomized SCoC 271.9.2.1 Synthetic Dataset Description 301.9.2.2 Experimental Analysis: SCoC rand 311.9.3 SCoC with MapReduce (MR-CoC) 341.9.3.1 Synthetic Dataset Description 361.9.3.2 Experimental Analysis: MR-CoC 371.10 Functional Module Mining Using MR-CoC 391.11 Conclusion 49Appendix 50References 512 Natural Language Processing in Healthcare: Enhancing Wellbeing through a COVID-19 Case Study 55Akib Mohi Ud Din Khanday, Salah Bouktif and Ali Ouni2.1 Introduction 562.2 NLP Approaches 572.3 NLP Pipeline for Smart Healthcare 592.3.1 Preprocessing 602.3.2 Feature Extraction 602.3.3 Classification 602.3.4 Model Interpretability 612.4 Applications of NLP in Healthcare 612.4.1 Clinical Records 612.4.2 Information Extraction 622.4.3 Decision Support 632.4.4 Health Assistance 632.4.5 Opinion Mining 642.5 COVID Detection Using NLP 652.5.1 Data Collection 662.5.2 Preprocessing 672.5.3 Feature Engineering 672.5.4 Classification 682.5.5 Ensemble Classification 692.6 Results and Discussion 702.6.1 Traditional Machine Learning 702.6.2 Ensemble Machine Learning 712.7 Conclusion 72References 723 Artificial Intelligence Assisted Internet of Medical Things (AIoMTs) in Sustainable Healthcare Ecosystem 75Wasswa Shafik3.1 Introduction 763.1.1 Key Contributions of the Chapter 783.1.2 Chapter Organization 793.2 Medical Wearable Electronics 793.2.1 Electronic Sensor Traits 793.2.2 Disposable Health Sensors 803.2.3 Ingestible Sensors 803.2.4 Patch Sensors 803.2.5 Connected Health Sensors 803.2.6 Wearables 803.2.7 Smart Clothing 813.2.8 Implantable Sensors 813.3 Electronic Signals in Sensors 823.3.1 Gait Analysis 823.3.2 Photoplethysmography 823.3.3 Electromyography 833.3.4 Auscultation 833.4 Electronic Devices Challenges in the AIoMT 843.4.1 Data Security Threats 853.4.2 Data Interoperability 863.4.3 Regulatory Challenges 863.4.4 High Infrastructure Costs 863.4.5 Standardization Challenges 873.4.6 Cybersecurity 873.4.7 Device Mobility 873.4.8 Adoption Scale 883.4.9 Advanced Analytics 883.4.10 Trust Maintenance 893.4.11 Data Security 893.4.12 Licensing Challenge 893.5 AIoMT Benefits 893.5.1 Medical Diagnosis 893.5.2 Medical Treatment 903.5.3 Patient Empowerment 903.5.4 Reduction in Medical Costs 903.5.5 Reduction in Human Error 913.6 AIoMTs Challenges 913.6.1 Privacy Concerns 913.6.2 Missteps and Errors 913.6.3 Data Management and Power Issues 923.6.4 Bias 923.7 AIoMT Limitations 933.8 Future Research Direction 933.9 Conclusions and Future Scope 94References 954 An Online Platform for Timely Access to Medical Care with the Help of Real-Time Data Analysis 103Pancham Singh and Mrignainy Kansal4.1 Introduction 1044.1.1 Research Questions 1044.1.2 Inspiration Drawn 1054.1.3 Limitations 1054.1.4 Importance of Machine Learning in this Research Work 1054.2 What Happened 1054.3 Literature Review 1084.4 Methodology 1154.4.1 Dataset Collection 1174.4.2 Data Preprocessing 1174.4.3 Model Building 1184.4.4 Clustering Algorithm 1184.4.5 A* Algorithm 1204.5 Hardware Component 1224.5.1 Blockchain in Health Care 1244.6 Conclusion 1264.7 Future Work 127References 1275 A Comprehensive Review of Cardiac Image Analysis for Precise Heart Disease Diagnosis Using Deep Learning Techniques 133Anuj Gupta, Vikas Kumar and Aryan Nakhale5.1 Introduction and Major Contribution 1345.2 Literature Review 1355.3 Machine Learning Methods 1375.4 Proposed System 1385.4.1 Dataset 1385.4.2 Preprocessing 1395.4.3 Network Architecture 1395.5 Mathematical Model 1415.6 Data Preparation 1435.7 Model Training and Evaluation 1455.8 Results and Discussion 1465.9 Conclusion and Future Work 152References 1526 A Hybrid Machine Learning Model for an Efficient Detection of Liver Inflammation 157Hema Ramachandran and Syedakbar Syed YusuffAbbreviations 1586.1 Introduction 1586.1.1 Novelty of Detection of NAFLD Using Conglomeration of Machine Learning Techniques 1596.2 Machine Learning for Liver Disease Prediction 1606.2.1 Data Collection and Pre-Processing 1606.2.2 Feature Selection 1606.2.3 Modeling with Algorithms 1616.2.4 Evaluating the Models 1616.3 Related Works 1626.3.1 Method 1626.3.2 Detecting Liver Inflammation with Random Forest Classifier 1636.4 Experimental Analysis 1656.5 Result Evaluation 1696.6 Conclusion 1706.7 Enhancement of PCA Over Other Dimensionality Reductions 170References 1707 Advancements in Parkinson’s Disease Diagnosis through Automated Speech Analysis 173P. Deepa, Rashmita Khilar and Saumendra Kumar Mohapatra7.1 Introduction 1747.1.1 Overview 1747.1.2 Traditional Diagnostic Methods 1767.1.3 Emergence of Automated Speech Analysis 1767.1.4 Major Contributions of the Work 1767.2 Speech Characteristics in Parkinson’s Disease 1777.2.1 Speech-Related Difficulties 1787.2.2 Specific Speech Features 1787.3 Technological Advances in Speech Analysis 1797.3.1 Digital Signal Processing 1797.3.2 Machine Learning and Artificial Intelligence 1797.4 Integration of Multimodal Data 1807.4.1 Complementary Modalities 1807.4.2 Improved Diagnostic Precision 1817.5 Related Works 1827.6 Building a Machine Learning (ML) Model 1847.6.1 Dataset Description 1847.6.2 Preprocessing 1877.6.3 Feature Extraction 1877.6.4 Classification 1897.7 Experimental Analysis and Performance Measures 1957.7.1 Evaluating Classifiers 1977.7.2 Tuning Hyperparameters 1987.8 Future Directions 2007.8.1 Advancements in Technology 2007.8.2 Personalized Medicine 2007.9 Challenges and Limitations 2017.9.1 Influencing Factors 2017.9.2 Ethical Considerations 2017.9.3 Standardization and Validation 2027.10 Conclusion and Implications 2027.10.1 Implications for Clinical Practice 203References 2038 Public Opinion Segmentation on COVID-19 Vaccination and Its Impact on Wellbeing 207Akib Mohi Ud Din Khanday, Salah Bouktif and K. Nimmi8.1 Introduction 2078.2 Background and Related Work 2088.3 Machine Learning Techniques 2128.3.1 Logistic Regression 2138.3.2 Multinomial Naïve Bayes 2138.3.3 Support Vector Machine (SVM) 2158.3.4 Decision Trees 2168.4 Ensemble Machine Learning Algorithms 2178.4.1 Bagging 2178.4.2 AdaBoost 2178.4.3 Random Forest Classifier 2178.4.4 Stochastic Gradient Boosting 2188.5 Methodology 2188.5.1 Data Collection 2188.5.2 Data Preprocessing 2198.5.3 Feature Engineering 2218.5.4 Classification 2228.6 Results and Discussion 2238.7 Impact on Wellbeing 2268.8 Conclusion 227References 2279 Revolutionizing Healthcare with IoT in Cardiology 231Aafreen Jan, K. Nimmi and Mohd Anas Wajid9.1 Introduction 2329.1.1 Characteristics of IoT 2339.1.2 Healthcare 2349.1.3 Components of Healthcare 2369.1.4 The Role of IoT in Healthcare 2379.1.4.1 Remote Monitoring and Management 2379.1.4.2 Personalized Healthcare 2379.1.4.3 Enhancing Hospital Efficiency and Patient Experience 2379.1.4.4 Telemedicine and Remote Consultations 2389.1.4.5 Improving Emergency Responses 2389.1.4.6 Drug Management and Supply Chain Optimization 2389.2 Background 2399.3 Motivation 2409.3.1 Access to Healthcare 2409.3.2 Cost and Affordability 2419.3.3 Quality of Care 2419.3.4 Aging Population and Chronic Diseases 2419.3.5 Healthcare Infrastructure 2419.3.6 Healthcare Technology and Innovation 2429.3.7 Global Health Threats 2429.3.8 Mental Health 2429.4 Primary Diseases Globally 2439.5 IoT Revolutionizes Healthcare 2449.6 IoT Patient Monitoring Devices and Early Detection of Heart-Related Problems 2489.7 An IoT-Based Heart Disease Monitoring System 2549.7.1 Photoplethysmography 2569.7.2 Software Requirements 2599.7.3 Hardware Prerequisite 2619.8 Conclusions 267References 26710 Human Biological Analysis Through Fitness Watch Using Deep Learning Algorithm 275Nilesh Bhaskarrao Bahadure, Ramdas Khomane, Anjali Singh, Anisha Jaiswal, Rashmi Kadu, Rohini Bharne, Bhumika Kosarkar and Sidheswar Routray10.1 Introduction 27610.2 Literature Survey 27810.3 Methodology 28210.4 Results and Discussion 28710.5 Limitation of the Work 29010.6 Validation and Comparative Analysis 29110.7 Conclusion 292References 29311 Decoding Kidney Health: Effectiveness of Machine Learning Techniques in Diagnosis of Chronic Kidney Disease 297Suhail Rashid Wani, Syed Naseer Ahmad Shah, Roshni Afshan and Asif Adil11.1 Introduction 29811.2 Methods 29911.2.1 Data and Features 29911.2.2 Preprocessing 30011.3 Methodology 30111.3.1 Logistic Regression 30211.3.2 Random Forest 30211.3.3 Knn 30211.3.4 Support Vector Machine (SVM) 30311.3.5 Decision Tree 30411.3.6 Adjusting Hyperparameters 30411.3.7 Boosting Algorithm 30511.4 Results and Discussion 30511.4.1 Discussion 30711.5 Conclusion 309References 30912 Integrating Metaheuristics and Machine Learning for Wellbeing Management: Case of COVID-19 313Safea Matar Al Senani and Salah Bouktif12.1 Introduction 31412.2 Related Work 31512.2.1 Modeling Non-Pharmaceutical COVID- 19Responses Cross Sectors 31512.2.2 Modeling COVID-19 Responses for Schools’ Management 31612.2.3 Modeling the Impact of Vaccines in Curbing the Outbreak 31712.3 Background Knowledge 31712.3.1 Machine Learning Techniques 31812.3.2 Deep Learning 31812.3.3 Genetic Algorithms 31912.4 Methodology 32012.4.1 Data Preparation 32112.4.2 Feature Engineering 32212.4.3 Model Selection 32212.5 Results and Discussions 32512.5.1 Model Validation 32512.6 Conclusion 337References 33713 Fusing Sentiment Analysis with Hybrid Collaborative Algorithms for Enhanced Recommender Systems 343Anindya Nag, Md. Mehedi Hassan, Mohammad Abu Tareq Rony, Biva Das, Riya Sil, Prianka Saha, Pronab Sarker and Anupam Kumar Bairagi13.1 Introduction 34413.1.1 Analysis of Sentiment 34613.1.2 Collaboration Filtering 34813.1.2.1 HCF-Based Recommender System 34913.2 Literature Survey 35013.3 Comparative Result Study 35813.4 Conclusion and Future Scope 359References 36014 The Future of Well-Being: AI-Powered Health Management with Privacy at its Core 363D. Dhinakaran, S. Edwin Raja, J. Jeno Jasmine, P. Vimal Kumar and R. Ramani14.1 Introduction 36414.1.1 Challenges in Traditional Wellness Management 36514.1.2 AI Accelerators: A Game-Changer 36614.1.3 The Privacy Revolution of Federated Learning 36714.1.4 Objectives 36814.1.5 Contributions 36914.2 Related Works 37014.3 Proposed Work 37514.3.1 Secure Data Access with Federated Identity 37514.3.2 Blockchain-Powered Data Sharing: Revolutionizing Patient Data Management 38014.3.3 AI-Powered Analytics for Personalized Care 38414.3.4 Privacy-Preserving AI Through Federated Learning 38614.4 Performance Evaluation 39014.4.1 Model Accuracy 39114.4.2 Privacy Preservation 39114.4.3 Metrics Comparison Across Systems 39614.5 Conclusion and Future Work 398References 39915 Artificial Pancreas: Enhancing Glucose Control and Overall Well-Being 403Owais Bhat, Syed Tanzeel Rabani, Syed Mohsin Saif, Zubair Jeelani and Nawaz Ali Lone15.1 Introduction 40415.1.1 Glucose Monitoring 40515.1.2 Insulin Pumps 40815.2 Closed-Loop Diabetes Control System 40915.3 Testing and Regulatory Approvals 41115.4 Safety Requirements in the Design of Artificial Pancreas 41315.4.1 General Safety Requirements 41315.4.2 Sensor Disturbance 41315.4.3 Insulin Pumps 41415.4.4 Control Algorithm 41415.4.5 Software/Network Vulnerabilities 41515.4.6 Profusion Site 41515.4.7 Meal and Other Disturbances 41515.4.8 Insulin Sensitivity 416Conclusion 417References 417Index 421