COVID-19, a novel coronavirus pandemic has disrupted our society in many ways. Digital healthcare innovations are required more than ever before as we have come across myriad challenges during this pandemic. Scientists and developers are learning and fi nding ways to use artifi cial intelligence applications and natural language processing to comprehend and tackle this disease.
AI technologies are playing an important role in the response to the COVID-19 pandemic. Experts are using all possible tools to study the virus, diagnose individuals, and analyze the public health impacts. This book is a collection of some of the leading efforts related to AI and COVID-19 focused on fi nding how AI can be helpful in monitoring situations from early warnings, swift emergency responses, and critical decision-making. It discusses the use of machine learning and how it may help to reduce the impacts of this pandemic in conjunction with all other research and strategies going on. The book serves as a technical resource of data analytics and AI applications in tracking infectious diseases. It will serve academics, students, data scientists, medical practitioners, and those involved in managing a global pandemic.
Features:
• Directs the attention to the smart digital healthcare system in this COVID-19 pandemic
• Simulates novel investigations and how they will be beneficial in understanding the pandemic
• Analyses the various issues related to computing, AI apps, big data analytic techniques, and predictive scientifi skill gaps
• Explains some interesting and diverse types of challenges and data-driven healthcare applications
Author(s): Salah-ddine Krit, Vrijendra Singh, Mohamed Elhoseny, Yashbir Singh
Series: Smart and Intelligent Computing in Engineering
Publisher: CRC Press
Year: 2022
Language: English
Pages: 154
City: Boca Raton
Cover
Half Title
Series Information
Title Page
Copyright Page
Table of Contents
Preface
Editors
1 Role of Artificial Intelligence in COVID-19
1.1 Introduction
1.2 Background
1.3 Algorithms Used in Artificial Intelligence
1.3.1 Support Vector Machine (SVM)
1.3.2 Convoluted Neural Networks (CNN)
1.3.3 Decision Trees
1.3.4 K-Nearest Neighbours (KNN)
1.3.5 Logistic Regression
1.3.6 Linear Regression
1.4 Applications of AI for Fighting Covid-19
1.4.1 Issues and Challenges in AI COVID-19
1.5 Conclusion
References
2 Application of 3D Printing in COVID-19
2.1 Introduction
2.2 Types of Modeling
2.2.1 Fused Deposition Modeling (FDM)
2.2.2 Selective Laser Melting (SLM)
2.2.3 Electron-Beam Melting
2.2.4 Laminated Object Manufacturing (LOM)
2.2.5 Material Jetting (MJ)
2.2.6 Stereolithography (SLA)
2.2.7 Binder Jet
2.3 Components of a 3D Printer
2.4 Materials Used
2.5 Applications of 3D Printing in COVID-19
2.5.1 Nasopharyngeal (NP) Swab
2.5.2 Face Shield
2.5.3 Various Masks
2.5.3.1 N95 Masks
2.5.3.2 Snorkel Mask Adapter
2.5.3.3 3D Printed Mask Frames
2.5.3.4 Mask Extenders
2.5.3.5 Open-Source 3D Printed Ventilator Device
2.5.3.6 Hospital Respiratory Apparatus
2.5.3.7 3D Printed Isolation Wards
2.5.3.8 Contact-Free Devices
2.5.3.9 Drone Parts
2.5.3.10 3D Bioprinting
2.5.3.11 Antimicrobial Polymers in the COVID-19 Pandemic
2.6 Conclusion
References
3 Role of IoT and AI in COVID-19
3.1 Introduction
3.2 AI and IoT for Large- and Small-Scale COVID-19 Screening and Monitoring
3.2.1 Quarantine Tracking
3.2.2 IoT Q-Band
3.3 Clinical Decision Support System (CDSS)
3.3.1 Wearable, Cuffless Blood-Pressure Measuring Devices
3.4 Internet of Things Buttons for Real-Time Notifications in Hospital
3.5 IoT-Based Smart Helmet for COVID-19
3.6 Sanitization Using IoT and AI Technology
3.7 Ultraviolet Light Surface Disinfection Devices
3.8 Drones and Other Robots for Spraying Disinfectant
3.9 IoT-Enabled Smart City During COVID-19
3.10 Conclusion and Future Scope
References
4 Potential Contributions of AI Against COVID-19
4.1 Introduction
4.2 Current Strategy
4.2.1 Containment (“Epidemiological Avoidance”)
4.2.2 Testing Is Critical
4.3 Role of AI: From Diagnosis to Outcome Predictions
4.3.1 Isolation: Drone Delivery
4.3.2 Equipment: 3D Printing
4.3.3 Care: Intelligent Robot
4.3.4 Data: Internet of Things (IoT)
4.3.5 Model: Deep Reinforcement Learning
4.3.6 Drugs: Generative Design Algorithms
4.3.7 Radiology: CT Modalities
References
5 A Comparative Study of COVID-19 Data Analysis Using R Programming
5.1 Introduction
5.2 Objective
5.3 Methods
5.4 Results
5.5 Conclusion
5.6 Key Messages
References
6 COVID Cases Analysis: Dynamic Animated Plots Using R Programming
6.1 Introduction
6.2 Method
6.3 Results
6.3.1 Line Plot Animation
6.3.2 Bar Plot Animation
6.3.3 Bubble Plot Animation
6.4 Conclusion
References
7 Tracking and Analyzing COVID-19 Pandemic Using Twitter and Topic Modelling
7.1 Introduction
7.2 What Is Topic Modelling?
7.3 Related Work
7.4 Other Ways of Topic Analysis
7.5 How Can Twitter and Topic Modelling Be Used in Tackling COVID-19?
7.5.1 Role of Twitter
7.5.2 Twitter and Covid
7.5.3 How Can Topic Modelling Help?
7.6 How Does Topic Modelling Work?
7.6.1 Data Collection
7.6.2 Data Cleaning
7.6.3 Topic Modelling
7.7 Further Study
References
8 Artificial Neural Network Application to Analyze 3D Image Printing Using Artificial Intelligence in COVID-19
8.1 Introduction
8.1.1 Background
8.1.2 Problem Formula
8.1.3 Problem Limit
8.1.4 Direction
8.1.5 Divining Annual Research
8.2 Literature Review
8.2.1 Image Processing Substance
8.2.2 Counter-Propagation Neural Network
8.3 Discussion and Implementation
8.3.1 Case Analysis
8.3.2 Data Acquisition Method
8.3.3 Data Extraction
8.3.4 Data Normalization
8.3.5 Numeric Data Accumulation
8.3.6 Artificial Neural Network Structure
8.4 Analysis and Simulation
8.4.1 Sample Preparation
8.4.2 Learning Activity Simulation
8.4.3 Learn Rate Effect
8.4.4 Momentum Effect
8.4.5 Initial Value Reach Effect
8.4.6 Regional Composition Effects Towards JSB Sample
8.5 Conclusion
8.6 Exercises
References
9 The Evolution of Emerging Market (EM) Sovereign CDS Spreads During COVID-19
9.1 Introduction
9.2 Recent Literature
9.2.1 Local Risk Factors
9.2.2 Global and Local Risk Factors
9.3 Overview of Emerging Markets And COVID-19
9.4 Methodology
9.4.1 Stage 1 Estimate, January 2014–June 2019 (Table 9.1)
9.4.1.1 Data
9.4.1.2 Specification
9.4.1.3 Exposure to Global and Regional Risks and Fiscal Fundamentals in Emerging Markets
9.4.2 Second Estimation Phase, January–June 2020
9.4.2.1 Data
9.4.2.2 Specification
9.4.2.3 Residue Review, March 2020
9.5 Results
9.6 Conclusion
References
10 Prediction of COVID-19 Data Using Business Intelligence Tools
10.1 Introduction
10.2 Methodology
10.2.1 Dataset
10.2.2 BI Tool
10.2.3 Machine Learning Environment
10.2.4 Data Integration
10.2.5 Visualization of Historical Data
10.3 Results Interpretation
10.3.1 Results of Forecast Option
10.3.2 Results of the Prediction Models Using R
10.3.3 Results of the Prediction Models Using Python
10.4 Qualification of the Predictive Models
10.5 Conclusion
References
Index
