Artificial Intelligence and Machine Learning for COVID-19

Description

This book is dedicated to addressing the major challenges in fighting COVID-19 using artificial intelligence (AI) and machine learning (ML) – from cost and complexity to availability and accuracy. The aim of this book is to focus on both the design and implementation of AI-based approaches in proposed COVID-19 solutions that are enabled and supported by sensor networks, cloud computing, and 5G and beyond. This book presents research that contributes to the application of ML techniques to the problem of computer communication-assisted diagnosis of COVID-19 and similar diseases. The authors present the latest theoretical developments, real-world applications, and future perspectives on this topic. This book brings together a broad multidisciplinary community, aiming to integrate ideas, theories, models, and techniques from across different disciplines on intelligent solutions/systems, and to inform how cognitive systems in Next Generation Networks (NGN) should be designed, developed, and evaluated while exchanging and processing critical health information. Targeted readers are from varying disciplines who are interested in implementing the smart planet/environments vision via wireless/wired enabling technologies. Preface Contents Uncertainty Propagation and Salient Features Maps in Deep Learning Architectures for Supporting Covid-19 Diagnosis 1 Introduction 2 Methods and Materials 2.1 CNN-Inception 2.2 Uncertainty Propagation 2.3 Grad-CAM 3 Experimental Results and Models Comparison 3.1 Pneumonia Image 3.2 Covid-19 Image 3.3 Healthy Image 3.4 Numerical Outputs 4 Conclusions References A Review of Machine Learning Techniques to Detect and Treat COVID-19 Using EHR Data 1 Introduction 2 Methods 2.1 Search Strategy 2.2 Study Selection 3 Findings 3.1 SARS-CoV-2 Detection Models Using EHR Data 3.2 SARS-CoV-2 Prognostic Models Using EHR Data 4 Treating COVID-19 Using Machine Learning and EHR Data 4.1 Repurposing of Commercially Available Drugs and Vaccines for the Treatment of COVID-19 4.2 Development of Targeted Medical Therapy Techniques 5 EHR and Machine Learning in Studying Mutations in the Virus 6 Early Detection of Future Pandemics 7 Challenges and Future Direction 8 Conclusion 9 Limitations References Machine Learning-Based Emerging Technologies in the Post Pandemic Scenario 1 Introduction 2 Risk Factors during COVID-19 2.1 Why Risk Factors Matter? 2.2 How we learn about Risk Factors for severe disease? 3 Impacts of COVID-19 in major sectors 3.1 Medical Sector 3.2 Business Sector 3.3 Police Force 3.4 Educational Sector 4 Data Science methodologies to overcome impacts in major sectors 4.1 Medical Sector 4.2 Business Sector 4.3 Common People 4.4 Police Force 5 Proposed Method and Implementation 5.1 System Flow 6 Conclusion References Covid-19 Face Mask Detection Using Deep Learning Techniques 1 Introduction 2 Related Work 3 Methods and Methodology 4 Dataset Description 4.1 CNN—Convolutional Neural Network 5 Result and Analysis 5.1 Comparative Analysis 6 Conclusion References Computational Intelligence in Identification of Some FDA Approved Drug Compounds for Treatment of COVID-19 1 Introduction 2 Material and Methods 2.1 Retrieve of Drug Compounds and Target Proteins 2.2 Drug Likeness Properties 2.3 Molecular Docking and Dynamics 3 Results and Discussions 3.1 Drug-Likeness Properties 3.2 Molecular Docking Studies and Molecular Dynamic Simulations 4 Conclusion References Biomedical Data Driven COVID-19 Prediction Using Machine Learning Approach 1 Introduction 2 Literature Survey 3 Proposed Methodology 3.1 Feature Computation 3.2 Classification 4 Experimental Results 4.1 Comparative Study 5 Conclusion References Vaccination, Lock-Down, Measures and Time-Varying Reproduction Number Based Estimation and Control of COVID-19 Outbreak in Turkey 1 Introduction 2 SARS-CoV-2 Population Dynamics 2.1 Model Description 2.2 Time-Varying Parameter-Based Model Validation 3 Observer-Based Control of COVID-19 Outbreak 3.1 Nonlinear Model Predictive Control 3.2 Gradient-Based Nonlinear Observer Design 4 Experimental Results 4.1 Time-Varying Reproduction Number Scenarios and Estimation Results 4.2 Time-Varying Reproduction Number Based Control Results 5 Discussions and Conclusion References Diabetes Analysis with a Dataset Using Machine Learning 1 Introduction 2 Literature Review 2.1 Diabetes and Covid-19 2.2 Diabetes Prediction and AI Techniques 2.3 Logistic Regression 2.4 Decision Tree 2.5 XGBoost Algorithm 2.6 Support Vector Machine (SVM) 3 Exploring Data and Choosing Features 4 Experiment and Results 4.1 Logistic Regression 4.2 Decision Tree Classifier 4.3 XGBoost Algorithm 4.4 SVC (Support Vector Classifier) 5 Discussions 6 Conclusion Appendix References Impact of Covid-19 on Indian Agriculture 1 Introduction 2 Occupation 3 Annual Family Income 4 Livelihood 5 Food Supply 6 Coefficient of Concordance 7 Strategy to Improve Food Productivity 8 Use of Information Technology 9 Agricultural Knowledge and Information System (AKIS) 10 New Opportunities Exist for Raising AKIS Effectiveness 11 Strategy to Strengthen the Agricultural Sector Post-COVID-19 12 Conclusion References COVID-19 Patients Management and Triaging Using Machine Learning Techniques 1 Introduction 1.1 Related Works 2 Methodology 3 Experimental Results 4 Conclusion Appendix References Coordination of Covid-19 Vaccation: An Optimization Problem and Related Tools Derived from Telecommunications Systems 1 Introduction 2 Literature Review 3 Modelization and Introduction of the Vaccine Allocation Algorithm (VAA) 4 Artificial Intelligence Solutions Derived from Telecommunications Systems to Support the Optimization Process 5 Managing Data to Solve the Modelization Problem 6 Conclusion and Perspectives References