Computational Modeling and Data Analysis in COVID-19 Research

Description

Cover Half Title Series Page Title Page Copyright Page Table of Contents Preface Editors Contributors Chapter 1 Machine Learning Implementations in COVID-19 1.1 Introduction 1.1.1 A Brief History of Coronaviruses 1.1.2 Current Scenario of COVID-19 1.1.3 Symptoms, Diagnosis, and Preventions Steps for COVID-19 1.2 Machine Learning in COVID-19 Outbreak 1.2.1 Application of ML in the War on COVID-19 1.2.2 Machine Learning in COVID-19 Future Forecasting 1.2.3 Machine Learning as a Diagnostic Tool for COVID-19 1.2.4 COVID Patient’s Health Prediction Using Machine Learning 1.2.5 Machine Learning in Survival Analysis and Discharge Time Prediction of COVID-19 Patients 1.2.6 Machine Learning in Contact Tracing of COVID-19 1.3 Conclusion References Chapter 2 Analysis of COVID-19 Data Using Consensus Clustering Technique 2.1 Introduction 2.2 Literature Study 2.3 Methodology Used 2.3.1 Clustering 2.3.2 Consensus Clustering 2.3.3 Problem Formulation 2.3.4 Pairwise-Similarity-Based Consensus Clustering Method 2.4 Proposed Method 2.5 Experimental Setup and Result Analysis 2.6 Conclusion References Chapter 3 MoBMGAN: Modified GAN-Based Transfer Learning for Automatic Detection of COVID-19 Cases Using Chest X-ray Images 3.1 Introduction 3.2 Literature Survey 3.3 Proposed Method 3.3.1 Data Collection and Preprocessing 3.3.2 Generation of Expanded Dataset via MGAN 3.3.3 Fine-tuning Transfer Learning Models for Classification 3.4 Result and Analysis 3.4.1 Accuracy vs Computational Complexity 3.5 Conclusion References Chapter 4 Application and Progress of Drone Technology in the COVID-19 Pandemic: A Comprehensive Review 4.1 Introduction 4.2 Research Needs 4.3 A Historical Overview of Drone and UAV Technologies 4.4 Different Applications of Drones 4.4.1 Agriculture 4.4.2 Health Sector 4.4.3 Mass Media and Journalism 4.4.4 Civil Surveillance 4.4.5 Other Applications 4.5 Opportunity and Challenges 4.6 Conclusion and Outlook References Chapter 5 Smart War on COVID-19 and Global Pandemics: Integrated AI and Blockchain Ecosystem 5.1 Introduction: COVID-19 in the Era of Modern Technology 5.2 Tracking and Forecasting the COVID-19 Outbreak in Real Time: Role of AI 5.3 Data Authentication: A Case for Blockchain Integration for Diverse AI Systems 5.4 Role of AI in Diagnosis, Detection, and Identification of COVID-19 Patients 5.5 Accelerating Drug Discovery for COVID-19: The Big Role of AI 5.6 Securing Different Supply Chains at Time of Crisis 5.6.1 Medical Supply Chain 5.6.2 Food Supply Chain 5.6.3 Relocation of Medical, Law Enforcement, and Other Critical Service Professionals 5.7 Impact of COVID-19 on World Economy and Role of AI and Blockchain 5.8 Other Smart Interventions 5.8.1 Facial Recognition and Fever Detector AI 5.8.2 AI-Enabled Drones and Robots 5.8.3 Virtual Healthcare Assistants (Chatbots) 5.8.4 Managing Finance/Donation (Blockchain) 5.9 Outlook/Perspective 5.9.1 Trust: The Missing Piece in Today’s Societal and Technological Architecture 5.9.2 Integrated AI and Blockchain Ecosystem: Smart Defense against Global Pandemics 5.10 Future Research Directions 5.10.1 The Big Canvas of Integration of Emerging Technological Paradigms 5.10.2 Development of Integrated Frameworks 5.11 Conclusion References Chapter 6 Machine Learning-Based Text Mining in Social Media for COVID-19 6.1 Introduction 6.1.1 Activities Involved in COVID-19 Text Mining Process 6.2 Value of Text Mining and Motivation 6.2.1 Applications of Text Mining 6.2.2 Design Issues in Text Mining 6.3 General Outline of Text Pre-Processing in COVID-19 6.3.1 Main Challenges Related to Social Media Text of COVID-19 6.3.2 Text Pre-Processing 6.3.3 Scope and Recent Pre-Processing Approaches in COVID-19 6.4 Various Text Pre-Processing Approaches for COVID-19 6.5 Extraction Mechanism and Analysis of Social Text of COVID-19 6.6 Scope of Various Machine Learning Approaches in Text Mining in Social Media for COVID-19 6.7 Recent Approaches for COVID-19 and Their Scope 6.8 Prediction and Analysis of the Impact of COVID-19 on Different Parameters 6.9 Conclusion References Chapter 7 Containing the Spread of COVID-19 with IoT: A Visual Tracing Approach 7.1 Introduction 7.1.1 Motivation 7.2 Overview of Techniques for Combating COVID-19 7.2.1 COVID-19 and IoT 7.2.2 Computer Vision 7.2.3 Human Activity Recognition 7.2.4 Fog/Edge Computing 7.2.5 Synthesis 7.3 System Model 7.3.1 IoT-Based Network Architecture for COVI-SCANNER 7.3.2 Information Flow in COVI-SCANNER 7.3.3 Proposed Solution 7.3.3.1 The Contamination Module 7.3.3.2 The Sanitization Module 7.4 Performance Evaluation 7.4.1 Experimental Setup 7.4.2 Results 7.4.2.1 Output from Contamination Phase 7.4.2.2 Output from Sanitization Phase 7.4.2.3 Detection and Removal of Fomite Spaces 7.4.2.4 Accuracy of the COVI-SCANNER Phases 7.4.2.5 Delays in Executing COVI-SCANNER and Its Phases 7.4.2.6 Upload and Download Rates 7.5 Conclusion References Chapter 8 Crowd-Sourced Centralized Thermal Imaging for Isolation and Quarantine 8.1 Introduction 8.2 Innovative Solutions for Fighting against COVID-19 8.2.1 Challenges and Their Solutions 8.3 Objective 8.4 Thermal Imaging 8.4.1 Infrared Thermal Scanner 8.4.2 Thermal Camera 8.4.3 Medical Uses of Thermal Imaging 8.4.4 Other Uses of Thermal Imaging 8.5 Methodology 8.5.1 Algorithm 8.5.2 Data Updating and Timestamping 8.5.3 Data Synchronization 8.6 Conclusion 8.7 Future Scope References Chapter 9 Blockchain Technology for Limiting the Impact of Pandemic: Challenges and Prospects 9.1 Introduction: Background and Driving Forces 9.2 Problem Statement 9.3 Literature Review 9.4 Research Methodology 9.4.1 Identification of Research Area 9.4.2 Review Study Scope and Research Conduct 9.4.3 Extraction of Relevant Data 9.5 Practical Applications of Blockchain Technology in Combating COVID-19 9.5.1 Prediction and Spread Prevention 9.5.2 Treatment 9.5.3 Direction and Prospects of Blockchain 9.6 Blockchain Technology for Revival of Sectors Post COVID-19 9.6.1 Education 9.6.2 Business, Supply Chain, and Logistics 9.6.3 Agriculture 9.6.4 Banking 9.6.5 Manufacturing 9.6.6 Security 9.7 Challenges of Implementing Blockchain Technology 9.8 Factors Encouraging Adoption of Blockchain Technology 9.9 Discussion 9.10 Conclusion and Future Scope References Chapter 10 A Study on Mathematical and Computational Models in the Context of COVID-19 10.1 Introduction 10.1.1 Classification of Mathematical Models 10.1.2 Features of Mathematical Models 10.2 Study of Mathematical Models for COVID-19 10.2.1 SIR Model 10.3 Extensions of the SIR Model 10.3.1 SIR Model with Parameters such as Birth and Death 10.3.2 SIR Model with Vaccine Impact 10.3.3 SIR Model with Impact of Vaccine and Re-Infection Rate 10.4 SEIR Model 10.5 SUQC Model 10.6 Modified SEIR Model for COVID-19 10.7 SEIAR (Susc​eptib​le–Ex​posed​–Infe​cted–​Asymp​tomat​ic–Re​cover​ed) Model 10.8 SEIAR with Hospitalization 10.9 Mathematical Model with Rate of Spreading Proportional to Square Root of Time 10.10 A Mathematical Model Incorporating Multiple Transmission Pathways Including Environment to Humans 10.11 Challenges of Modeling and Forecasting the Spread of COVID-19 10.11.1 Accurate Assessment of Viral Transmission 10.12 Models Not Addressing the Exit Strategy 10.12.1 Herd Immunity 10.12.2 Seroprevalence Survey for Transmission Dynamics and Herd Immunity 10.13 Heterogeneities in Transmission 10.14 Conclusions References Chapter 11 A Detailed Study on AI-Based Diagnosis of Novel Coronavirus from Radiograph Images 11.1 Introduction 11.2 COVID-19 Etiology, Clinical Imaging Features, and Prognosis 11.2.1 Chest Imaging 11.3 COVID-19 Classification Methodology 11.4 Experimental Outcomes 11.4.1 Database 11.4.2 Performance Metric 11.4.2.1 Results: Two-Class (COVID-19 vs. Normal) Problem 11.4.2.2 Results: Multi-Class (COVID-19 vs. Normal vs. Viral Pneumonia) Problem 11.4.3 Results: Multi-Class Classification for Pre-Trained Network 11.5 Conclusion and Future Directives Acknowledgment References Chapter 12 Data Analytics for COVID-19 12.1 Introduction 12.2 Literature Study 12.3 Exploratory Data Analysis 12.4 Compartmental Models for Epidemiology 12.5 Deep Learning for COVID-19 Diagnosis 12.6 Survival Analysis for COVID-19 12.7 COVID-19 Forecasting Models 12.8 Conclusion References Index