Computational Intelligence Techniques for Combating COVID-19

Preface
Acknowledgment
Contents
Chapter 1: South Asian Countries Are Less Fatal Concerning COVID-19: A Hybrid Approach Using Machine Learning and M-AHP
1.1 Introduction
1.2 Related Studies
1.3 Reasons for less Disaster Regarding COVID-19 in South Asian Countries
1.4 Experimental Result and Discussion
1.5 Concluding Remarks
Appendix: Multiple Analytical Hierarchy Process (M-AHP)
References
Chapter 2: Application of Deep Learning Strategies to Assess COVID-19 Patients
2.1 Introduction
2.1.1 Deep Learning
2.2 Deep Learning with Image Processing to Classify COVID-19 Patients
2.2.1 Using CT Scan Images
2.2.1.1 Methods and Materials
2.2.2 X-Ray Scans Using CNN and Class Activation Maps
2.2.3 COVID-19 Detection Using X-Ray Images and CNN
2.2.4 DL System to Screen COVID-19 Pneumonia
2.2.4.1 Process
2.2.4.2 Dataset Pre-processing and Candidate Region Segmentation
2.2.4.3 Image Data Processing and Augmentation
2.2.4.4 DL Model for Classification
2.3 Hybrid Model for COVID-19 Classification
2.4 Future Research Directions
2.5 Conclusions
References
Chapter 3: Applications of Artificial Intelligence (AI) Protecting from COVID-19 Pandemic: A Clinical and Socioeconomic Perspective
3.1 Introduction
3.2 Artificial Intelligence-Based COVID-19 Early Warning and Management
3.3 Clinical Perspective of AI in COVID-19
3.3.1 Detection and Diagnosis
3.3.2 Structural and Molecular Analysis
3.3.3 Drug Development
3.4 AI-Based Robotic Technologies
3.5 Socioeconomic Perspectives
3.6 Limitations and Future Perspectives
3.7 Conclusion
References
Chapter 4: COVID-19 Risk Assessment Using the C4.5 Algorithm
4.1 Introduction
4.2 ML-Assisted COVID-19 Healthcare System
4.2.1 ML Process
4.2.2 The C4.5 Algorithm
4.2.3 ML Challenges in COVID-19
4.3 COVID-19 Global Status
4.3.1 Dataset Description
4.3.2 COVID-19 Global Map
4.3.3 COVID-19 Case Status
4.3.4 Time-Series Forecast of Confirmed Cases
4.4 Proposed Work
4.4.1 Dataset Description
4.4.2 Environmental Setup and the C4.5 Algorithm Implementation
4.4.3 Results
4.5 Conclusion and Future Work
References
Chapter 5: Recent Diagnostic Techniques for COVID-19
5.1 Introduction
5.2 Molecular Assay Techniques
5.2.1 Reverse Transcription-Polymerase Chain Reaction (RT-PCR)
5.2.2 COBAS 6800/8800
5.2.3 Loop-Mediated Isothermal Amplification (LAMP)
5.2.4 Transcription-Mediated Amplification (TMA)
5.2.5 Programmed RNA-Targeted Analysis
5.2.6 Rolling Circle Amplification
5.2.7 Microarray
5.2.8 Metagenomic Next-Generation Sequencing (mNGS)
5.3 Serologic Assay
5.3.1 Enzyme-Linked Immunosorbent Assay (ELISA)
5.3.2 COVID-19 IgM/IgG Antibody Rapid Test
5.3.3 Chest CT Scan and Chest Radiograph for COVID-19
5.4 Latest Techniques
5.4.1 Biosensor
5.4.2 Aptamer-Based Nano-biosensor
5.4.3 Paper-Based Detection
5.5 Summary and Conclusion
References
Chapter 6: COVID-19: AI-Enabled Social Distancing Detector Using CNN
6.1 Introduction
6.1.1 Types of Coronavirus
6.1.2 Symptoms of COVID-19
6.1.3 Impact of Social Distancing
6.1.4 Literature Survey
6.2 Materials and Methods
6.2.1 Methods
6.2.1.1 Deep Learning
6.2.2 Materials
6.2.2.1 Data Collection
6.3 Social Distancing Detector Algorithm Using Convolution Neural Network
6.3.1 Building YOLO Object Detector
6.3.2 Bounding Boxes
6.3.3 Compute Pairwise Distance
6.3.4 Checking Whether the Pairwise Distance Is Greater Than N Pixel
6.3.5 Message and Alert Module
6.4 Integration of Embedded Hardware Kit with Social Distancing Application
6.4.1 Implementation of Code in Jetson Nano
6.4.2 Preparing the Jetson Nano with the Hardware Environment
6.5 Conclusion
References
Chapter 7: IoT-Enabled Applications and Other Techniques to Combat COVID-19
7.1 Introduction
7.2 IoT-Based Applications
7.2.1 IoT in Healthcare
7.2.2 Internet of Medical Things (IoMT)
7.2.3 Proposed Internet of Covid Things (IoCT)
7.2.3.1 Smart Thermometers
7.2.3.2 Wearables
7.2.3.3 Artificial Intelligence-Based IoCT Applications
7.2.3.4 Blockchain-Based IoCT Applications
7.2.3.5 IoCT Security Challenges
7.3 Telemedicine
7.4 IoHT Industry Status
7.5 Conclusion
References
Chapter 8: Optimum Distribution of Protective Materials for COVID−19 with a Discrete Binary Gaining-Sharing Knowledge-Based Optimization Algorithm
8.1 Introduction
8.2 Coronavirus (COVID-19): An Overview
8.3 Distribution of Coronavirus Protective Materials
8.4 Mathematical Model for the Optimum Distribution of Protective Materials
8.5 Real Application Case Study
8.6 The Proposed Methodology
8.6.1 Gaining-Sharing Knowledge-Based Optimization Algorithm (GSK)
8.6.2 Discrete Binary Gaining-Sharing Knowledge-Based Optimization Algorithm (DBGSK)
8.7 Experimental Results
8.8 Conclusions and Points for Future Researches
References
Chapter 9: Developing COVID-19 Vaccines by Innovative Bioinformatics Approaches
9.1 Introduction
9.2 Concepts of Reverse Vaccinology and Immunoinformatics
9.2.1 Previous Studies on Reverse Vaccinology with Immunoinformatics
9.3 Bioinformatics Strategies for Emergent Peptide-Based Vaccines Against SARS-CoV-2
9.3.1 Reverse Vaccinology
9.3.1.1 Retrieval of Proteome of SARS-CoV-2
9.3.1.2 Antigenicity Prediction
9.3.1.3 Allergenicity and Toxicity
9.3.1.4 Physicochemical Property Analysis
9.3.1.5 Adhesion Nature
9.3.1.6 Subcellular Localizations
9.3.1.7 Transmembrane Region
9.3.1.8 Signal Peptides
9.3.1.9 Similarity with Host Proteins
9.3.1.10 Conserved Domain Identification
9.3.2 Immunoinformatics
9.3.2.1 B-Cell Epitope Prediction
9.3.2.2 T-Cell Epitope Prediction
MHC Class I Binding Epitope Prediction
MHC Class II Binding Epitope Prediction
9.3.2.3 Epitope Conservation Analyses
9.3.2.4 Population Coverage Calculation
9.3.3 Structural Vaccinology
9.3.3.1 Homology Modeling
9.3.3.2 Protein-Ligand Docking Studies
9.3.3.3 Protein-Protein Docking
9.3.3.4 Molecular Dynamics (MD) Simulations
9.4 Immune Dynamics Simulation
9.5 In Silico Codon Adaptation and Cloning
References
Chapter 10: Big Data Analytics for Modeling COVID-19 and Comorbidities: An Unmet Need
10.1 Multi-organ Association of COVID-19
10.2 Crowdsourcing and Data Collection
10.3 Big Data Modeling for Personalized Treatment
10.4 Big Data Analysis and Integration: Modeling Data on Comorbidities
10.4.1 The Need for Comorbidity Data Integration
10.4.2 Omics Data on COVID-19 and Associated Comorbidities
10.5 Drug Repurposing: Treating COVID-19 and Comorbidities
10.6 Data Analytics for ACE2 Inhibitors: A Common Link in COVID-19 Comorbidity Network
10.7 Artificial Intelligence (AI) and COVID-19
10.8 Conclusions
References
Chapter 11: AR and VR and AI Allied Technologies and Depression Detection and Control Mechanism
11.1 Introduction
11.1.1 Applications of AR/VR
11.1.1.1 Gaming/Entertainment
11.1.1.2 Education
11.1.1.3 Healthcare
11.1.1.4 Tourism
11.1.1.5 Virtual Shopping
11.2 Working Process of AR/VR for COVID-19
11.2.1 Patient Education
11.2.2 Physical Therapies
11.2.3 Psychological Treatment
11.3 COVID-19 and Application of AR/VR for Psychological Support
11.4 Impact of AR/VR on Mental Health
11.5 Overview of Deep Learning
11.5.1 Deep Autoencoder
11.5.2 Restricted Boltzmann Machines (RBMs)
11.5.3 Deep Belief Networks (DBNs)
11.5.4 Convolutional Neural Networks (CNNs)
11.5.5 Recurrent Neural Networks (RNNs)
11.5.6 Generative Adversarial Network (GAN)
11.6 Application of Deep Learning in Mental Healthcare
11.7 Depression Diagnosis Using EEG Signals
11.8 Depression Detection and Control Methodology Using AR/VR
11.8.1 Signal Acquisition
11.8.2 Feature Extraction
11.8.3 Classification
11.8.3.1 CNN Architecture
11.8.3.2 Propagation in CNN Layers
11.8.4 Control Signals
11.9 Discussion
11.9.1 Positive Impact of AR/VR on Society
11.10 Conclusion
References
Chapter 12: Machine Learning Techniques for the Identification and Diagnosis of COVID-19
12.1 Introduction
12.2 Identified ML Techniques and Treatment for COVID-19
12.3 Data Collection
12.4 Data Summary of ML Implementation for COVID-19 Diagnosis Using X-Ray Imaging
12.5 Methodology
12.6 Machine Learning Data Molecules for Predicting COVID-19
12.7 ML Time Series Data Molecule Estimation
12.8 Present ML Approach for Identifying and Diagnosing COVID-19 Infection
12.9 ML Significance in Controlling COVID-19 Cases
12.10 Result and Discussion
12.11 Classification Performance Results from CNN Models of Different Classifiers
12.12 Recommendations and the Future of ML in Controlling Viruses
12.13 Conclusion
References
Chapter 13: Factors Associated with COVID-19 and Predictive Modelling of Spread Across Five Urban Metropolises in the World
13.1 Introduction
13.2 Data Used and Methods
13.3 Methodology
13.3.1 COVID-19 Infection Rates and Population Density
13.3.2 SVM-Based Predictive Modelling for the Number of Infections
13.4 Results
13.4.1 COVID-19 Infections Cases and Mortality Across Five Cities
13.4.2 Association of Climatic Variables and Population Density with the Spread of Cases
13.4.3 Association of COVID-19 Infection Rate and Population Density
13.4.4 Predictive Modelling for the Number of Infections
13.4.5 Effect of Lockdowns on Air Pollutants Across Select Cities
13.5 Discussion and Conclusions
References
Chapter 14: Chatbots for Coronavirus: Detecting COVID-19 Symptoms with Virtual Assessment Tool
14.1 Introduction
14.2 Fundamentals of Chatbots
14.2.1 What Is a Chatbot?
14.2.2 Evolution of Chatbots
14.2.2.1 1950s: The Turing Test
14.2.2.2 1964: ELIZA
14.2.2.3 1980s: Jabberwacky
14.2.2.4 1990s: A.L.I.C.E
14.2.2.5 2000s: SmarterChild Arrives
14.2.2.6 2010s: Chatbots and Personal Assistants
14.3 Types of Chatbots
14.3.1 Entertainment Chatbots
14.3.2 Enterprise Chatbots
14.3.3 Classification of Chatbots
14.3.3.1 Knowledge Domain
14.3.3.2 Service Provided
14.3.3.3 Goals Achieved
14.3.3.4 Input Distilling
14.3.3.5 Construction
14.4 Architecture and Design of Chatbots
14.4.1 Architecture
14.4.1.1 Generative Models
14.4.1.2 Retrieval-Based Models
14.4.1.3 Mechanism for Response Generation
Pattern-Based Heuristics
Intent Classification Using Machine Learning
14.4.1.4 Generation of Response
14.4.2 Chatbots and Its Functionality
14.4.2.1 AIML Fundamental Design
14.4.2.2 Paradigm Identification Using Snippets
14.4.2.3 Portal Value Assessment
14.4.2.4 Instrumentation
14.4.2.5 Multilingualism
14.4.2.6 Calibrations and Collation
14.5 Applications of Chatbots
14.5.1 Chatbots in Education
14.5.1.1 Language Study
14.5.1.2 Performance Reviewer
14.5.1.3 Motivation Builder
14.5.2 Chatbots in Client Service
14.6 Chatbots for COVID-19 [30]
14.6.1 Detecting COVID-19 Symptoms
14.6.2 Information Device
14.6.3 Interactions and Guidance
14.6.4 Examples
14.6.5 Antiviral Therapies
14.6.6 Ongoing Treatment
14.6.7 Bots Already in Use for COVID-19
14.6.7.1 Orbita COVID-19 Screening Chatbot and Knowledge Base
14.6.7.2 NHS WhatsApp Bot
14.6.7.3 Corona Helpdesk Chatbot on Facebook
14.6.7.4 Microsoft’s Coronavirus Self-Checker Bot
14.7 Challenges
14.7.1 Communiqué Elucidate
14.7.2 Gadget-to-Human Leap
14.7.3 Personalization
14.7.4 Chatbot Style
14.7.5 AI Uncertainty
14.8 The Virtual Assessment Tool and Its Possibilities
14.8.1 Product Service Bots on Webpage
14.8.2 Communication via SMS Chatbots
14.8.3 Teams Bots for Internal Maintenance
14.8.4 Wearable Devices
14.9 Future Possibilities
14.9.1 Situation Awareness
14.9.2 Types of Responses
14.9.3 Objective-Based Responses
14.9.4 Identity
14.9.5 Customer Awareness
14.9.6 Continuity
14.9.7 Narrative
14.10 Conclusion
References
Chapter 15: Enabled IoT Applications for Covid-19
15.1 Introduction
15.1.1 Context and Background
15.2 IoT and Its Interrelated Discoveries for Alleviating Covid-19 Problems
15.3 IoT Significance to Covid-19 Pandemic
15.4 Enabled Applications for Covid-19
15.5 Arising Issues and Solutions of the Study
15.6 Methods, Hypothesis, and Literature Review
15.7 Data Analysis
15.8 Results and Recommendations
15.9 Conclusion
References
Chapter 16: Impact of Covid-19 Infodemic on the Global Picture
16.1 Introduction
16.1.1 Information Versus Misinformation
16.1.2 Accelerated Disinformation and Social Media Hype
16.1.3 Conflict of Interest and Content Validation
16.1.4 Infodemic and the Role on the Global Picture
16.2 An Account of Literature Review on the Context of Infodemic
16.2.1 The Influence of Infodemic in Worsening the Ongoing Pandemic
16.3 Principle Aids of Disinformation about Covid-19 Pandemic
16.3.1 Primary Things We Should Adhere to Counteract the Infodemic
16.4 The Role of Covid-19 Infodemic on the Psychological Aspects
16.4.1 Consequences of Negative Infodemic of Covid-19
16.4.2 The Isolation and Quarantine Saga
16.5 Social Media and Infodemic: The Crucial Passage of Play
16.5.1 Phenomenon of Racism: The Most Unwelcome Aspect
16.6 Future Directives
16.7 Conclusion
References
Chapter 17: COVIDz: Deep Learning for Coronavirus Disease Detection
17.1 Introduction
17.2 Related Works
17.3 COVID-19 Diagnosis and Therapeutic Care
17.3.1 Diagnostic Approach
17.3.1.1 Anamnesis
17.3.1.2 Biological Examinations
17.3.1.3 Imaging
17.4 Methods and Materials
17.4.1 Python
17.4.2 VGG-16
17.4.3 Dataset
17.4.4 Classification
17.4.5 Implementation Details
17.5 Experimental Setup
17.6 Performance Evaluation
17.7 Results and Discussions
17.8 Conclusion and Future Works
References
Index