Novel AI and data science advancements for sustainability in the era of COVID-19

Novel AI and data science advancements for sustainability in the era of COVID-19

Novel AI and Data Science Advancements for Sustainability in the Era of COVID-19 discusses how the role of recent technologies applied to health settings can help fight virus outbreaks. Moreover, it provides guidelines on how governments and institutions should prepare and quickly respond to drastic...

Descripción completa

Detalles Bibliográficos
Otros Autores: Chang, Victor, author (author)
Formato: Libro electrónico
Idioma:Inglés
Publicado: London, UK : Academic Press [2022]
Materias:
Artificial intelligence.
COVID-19 Pandemic, 2020- > Data processing.
Big data.
Ver en Biblioteca Universitat Ramon Llull:https://discovery.url.edu/permalink/34CSUC_URL/1im36ta/alma991009835436406719
Tabla de Contenidos:
  • Intro
  • Novel AI and Data Science Advancements for Sustainability in the Era of COVID-19
  • Copyright
  • Contents
  • Contributors
  • Chapter 1: Deep learning-based hybrid models for prediction of COVID-19 using chest X-ray
  • 1. Introduction
  • 2. Related work
  • 3. Modeling
  • 3.1. PCA-feature ensembles
  • 3.2. Optimally weighted majority voting
  • 3.3. Feature extraction
  • 3.4. Layer modification
  • 4. Experimental setup
  • 4.1. Baseline models
  • 4.1.1. VGG-16 (Simonyan &amp
  • Zisserman, 2015)
  • 4.1.2. ResNet 50 (He et al., 2016)
  • 4.1.3. Inception V3 (Szegedy et al., 2015)
  • 4.2. Dataset
  • 4.3. Data augmentation
  • 4.4. Other preprocessing
  • 4.5. Evaluation metrics
  • 4.5.1. Accuracy
  • 4.5.2. Precision
  • 4.5.3. Recall
  • 4.5.4. F-1 score
  • 4.6. Experimental details
  • 5. Results and discussion
  • 6. Conclusions
  • References
  • Chapter 2: Investigation of COVID-19 and scientific analysis big data analytics with the help of machine learning
  • 1. Introduction and background
  • 2. Literature review
  • 3. COVID-19 pandemic in the new era of big data analytics: Methodological innovations and future research directions
  • 3.1. Deep learning applications for COVID-19
  • 3.2. Big data analytics as a tool for fighting pandemics: A systematic review of literature
  • 4. Review of big data analytics, artificial intelligence and nature-inspired computing models towards accurate detection ...
  • 5. Significant applications of big data in COVID-19 pandemic
  • 6. Research problem
  • 7. Research questions
  • 8. Objectives
  • 9. Methodology
  • 9.1. Techniques
  • 10. Algorithm
  • 11. Conclusion
  • 11.1. Big data
  • 11.2. Machine learning
  • 11.3. COVID-19
  • Acknowledgment
  • References
  • Chapter 3: Designing a conceptual model in the artificial intelligence environment for the health care sector
  • 1. Introduction
  • 2. Background.
  • 3. Literature review
  • 4. Approach suggested for designing a conceptual model
  • 5. Selection of concepts in information and communication technology
  • 5.1. Artificial intelligence
  • 5.2. Role of artificial intelligence
  • 5.3. Machine learning
  • 5.4. Algorithms
  • 5.5. Data warehouse
  • 5.6. Virtual reality
  • 5.7. Cloud computing
  • 6. Databases related to classification of diseases, digital image code, and viruses taxonomy
  • 6.1. International Classification of Diseases (ICD)
  • 6.2. Digital Imaging and Communications in Medicine (DICOM)
  • 6.3. International Committee on the Taxonomy of Viruses (ICTV)
  • 7. Role of core team
  • 7.1. Medical research activities
  • 7.2. Virtual medical research center
  • 8. Overview of viruses
  • 8.1. Viruses
  • 8.2. Spreading vectors
  • 8.3. Human immunodeficiency viruses
  • 8.4. Role of immune system
  • 8.5. Parts of immune system
  • 8.6. Characteristics of immune system
  • 8.6.1. White blood cells
  • 8.6.2. Antibodies
  • 8.6.3. Complement system
  • 8.6.4. Lymphatic system
  • 8.6.5. Spleen
  • 8.6.6. Bone marrow
  • 8.6.7. Thymus
  • 8.7. Common disorders of the immune system
  • 8.8. Types of immunity
  • 8.9. Signs of the weakened immune system
  • 9. Covid-19
  • 9.1. Classification of Covid-19 symptoms
  • 10. Case illustration based on the healthcare sector in India
  • 10.1. Data in the centralized database
  • 11. Machine learning approach for analyzing the medical data
  • 11.1. Supervised learning
  • 11.2. Unsupervised learning
  • 12. Indian environment
  • 12.1. Less common symptoms
  • 12.2. Serious symptoms
  • 12.3. Rule-based machine learning
  • 12.4. Algorithms
  • 13. Academic research approach
  • 14. Developing a drug
  • 14.1. Role of bioinformatics in drug development
  • 14.2. Biological data
  • 14.3. Role of virtual reality in drug design
  • 15. Discussion
  • 16. Conclusion
  • References.
  • Chapter 4: Augmented reality, virtual reality and new age technologies demand escalates amid COVID-19
  • 1. Introduction
  • 2. Updates ways to minimize infections
  • 2.1. Vaccination for controlling the spread of Covid-19
  • 2.2. Drugs and nutrients for controlling the spread of Covid-19
  • 3. Background and literature review
  • 3.1. Interrelationship between AR and VR
  • 3.2. Software and hardware components of AR/VR applications
  • 4. Demand escalation of AR/VR due to COVID-19 pandemic
  • 4.1. AR/VR and other new technologies for social distancing and controlling the spread of COVID-19
  • 4.2. Use of AR/VR to support remote education and reduce the spread of COVID-19
  • 4.3. Limitations and health risks of AR/VR
  • 5. Conclusion
  • References
  • Chapter 5: Using interpretable machine learning identify factors contributing to COVID-19 cases in the United States
  • 1. Introduction
  • 1.1. Background of the study
  • 1.2. Problem statement
  • 1.3. Aim and objectives
  • 1.4. Research questions
  • 1.5. Significance of the study
  • 1.6. Structure of the study
  • 2. Related work
  • 2.1. Basic reproduction number (R0)
  • 2.2. Incubation period and symptoms
  • 2.3. Vaccine trials and availability
  • 2.4. Non-pharmaceutical interventions (NPIs)
  • 2.5. Disruptive technologies
  • 2.5.1. Artificial intelligence (AI) and machine learning (ML)
  • 2.5.2. Industry 4.0 and internet of medical things (IoMT)
  • 2.5.3. Virtual reality (VR), drones and autonomous robots
  • 2.6. Contact tracing
  • 3. Proposed approach
  • 3.1. Dataset description
  • 3.1.1. Smoothing weekend effect
  • 3.2. Feature engineering
  • 3.3. Correlation: Confirmed_cases vs other features
  • 4. Experiment and results
  • 4.1. Model building
  • 4.1.1. Random forest
  • Hyperparameters
  • Residuals and prediction error plot
  • Learning curve plot
  • 4.1.2. Light gradient boosting
  • Hyperparameters.
  • Residuals and prediction error plot
  • Learning curve plot
  • 4.1.3. Extreme gradient boosting
  • Hyperparameters
  • Residuals and prediction error plot
  • Learning curve plot
  • 4.2. Model interpretability
  • 4.2.1. Feature importance
  • Random forest
  • Light gradient boosting
  • Extreme gradient boosting
  • 4.2.2. SHAP interpretability
  • Random forest
  • Light gradient boosting
  • Extreme gradient boosting
  • 4.2.3. LIME interpretability
  • Random forest
  • Light gradient boosting
  • Extreme gradient boosting
  • 4.3. Model evaluation
  • 4.4. Model interpretability
  • 4.4.1. Confirmed cases in the last 14days
  • 4.4.2. Population and population density
  • 4.4.3. Basic reproduction rate
  • 4.4.4. Global mobility features
  • 5. Conclusion and future work
  • 5.1. Discussion and conclusion
  • 5.2. Contribution to knowledge
  • 5.3. Future recommendations
  • Credit authorship contribution statement
  • References
  • Chapter 6: Cloud-based data pipeline orchestration platform for COVID-19 evidence-based analytics
  • 1. Challenges in COVID-19 data handling
  • 1.1. Cloud- and AI-based data pipeline platform
  • 1.2. Chapter organization
  • 2. Background and related works
  • 2.1. OHDSI on AWS infrastructure
  • 2.2. Cloud-based health-care data management
  • 2.3. Cloud-based data processing pipelines
  • 3. OnTimeEvidence architecture and component implementation
  • 3.1. OHDSI components of OnTimeEvidence
  • 3.2. Access and authorization management
  • 3.3. COVID-19 literature selection and analysis
  • 3.4. Data processing using domain-specific topic model
  • 4. OnTimeEvidence COVID-19 case study
  • 4.1. Secure access
  • 4.2. System login and data request
  • 4.3. OnTimeEvidence analytics workspace
  • 5. Conclusion-What we have learnt?
  • References.
  • Chapter 7: Threat model and security analysis of video conferencing systems as a communication paradigm during the COVID-
  • 1. Introduction
  • 2. Background
  • 2.1. Privacy and security in COVID-19
  • 2.2. Threat modeling
  • 2.3. Video conferencing technology
  • 2.4. Growth of video conferencing tools in the COVID-19 era
  • 3. Assets of video conferencing tools
  • 4. Point of entry
  • 4.1. Peripheral equipment
  • 4.2. Device or application
  • 4.3. Conference session
  • 4.4. Communication medium
  • 4.5. Cloud data storage
  • 4.6. Application system server
  • 5. Attack model
  • 5.1. Users or potential attacker
  • 5.1.1. Participants
  • 5.1.2. Organization administrator
  • 5.1.3. System administrator
  • 5.2. Trust levels of system users
  • 5.3. Attacker's motives
  • 5.3.1. Financial gain
  • 5.3.2. Espionage
  • 5.3.3. Business rival
  • 5.3.4. FIG (Fun, Ideology, Grudge)
  • 6. Threats and vulnerabilities
  • 6.1. STRIDE threat modeling process
  • 6.2. More attacks and vulnerabilities
  • 7. Mitigation strategies
  • 8. Conclusion and future work
  • Acknowledgments
  • References
  • Chapter 8: Role of artificial intelligence in fast-track drug discovery and vaccine development for COVID-19
  • 1. Introduction
  • 2. Artificial intelligence in COVID-19
  • 3. Artificial intelligence in drug discovery
  • 4. Chemical structure input for data processing
  • 5. Artificial intelligence in repositioning approaches
  • 6. Artificial intelligence for accelerating computer modeling
  • 7. Artificial intelligence: De novo design of novel small molecules
  • 8. Artificial intelligence in protein structure prediction
  • 9. Artificial intelligence in vaccine development
  • 10. Summary
  • 11. Conclusions and future directions
  • References
  • Chapter 9: The economic impact of covid-19 and the role of AI
  • 1. Introduction
  • 2. Economic impact of Covid-19.
  • 3. Artificial intelligence (AI) as a solace to help mankind out.

Ejemplares similares