Artificial Intelligence of Health-Enabled Spaces (AIoH) has made a number of revolutionary advances in clinical studies that we are aware of. Among these advances, intelligent and medical services are gaining a great deal of interest. Nowadays, AI-powered technologies are not only used in saving lives, but also in our daily life activities in diagnosing, controlling, and even tracking of COVID-19 patients. These AI-powered solutions are expected to communicate with cellular networks smoothly in the next-generation networks (5G/6G and beyond) for more effective/critical medical applications. This will open the door for other interesting research areas. This book focuses on the development and analysis of Artificial Intelligence (AI) model applications across multiple disciplines. AI-based Deep Learning models, fuzzy and hybrid intelligent systems, and intrinsic explainable models are also presented in this book. Some of the fields considered in this smart health-oriented book include AI applications in electrical engineering, biomedical engineering, environmental engineering, computer engineering, education, cyber security, chemistry, pharmacy, molecular biology, and tourism.
This book is dedicated to addressing the major challenges in fighting diseases and psychological issues using AI. These challenges vary from cost and complexity to availability and accuracy. The aim of this book is hence to focus on both the design and implementation aspects of AI-based approaches in the proposed health-related solutions.
Machine Learning-based approaches are very useful in medical fields for identifying different kinds of illnesses and other medical problems that are difficult to diagnose. It includes cancers which can be difficult to identify at early stages, and also certain genetic factors. There are various examples such as IBM Watson Genomics which uses various methods based on cognitive computing using the genome, which is primarily based on gene sequencing, allowing a fast analysis. Computer Vision is a technique based on machine learning and Deep Learning that is useful in diagnosing diseases using medical imaging. Computer Vision is helpful in segmenting and classifying medical images. Medical images are analysed accurately with the help of computer vision. As Machine Learning techniques are growing, IoT- enabled gadgets are being used for diagnosing medical issues through proper analysis of these medical images.
Targeted readers are from varying disciplines who are interested in implementing the smart planet/environments vision via intelligent enabling technologies.
Author(s): Fadi Al-Turjman
Publisher: CRC Press
Year: 2023
Language: English
Pages: 203
Cover
Half Title
Title Page
Copyright Page
Table of Contents
About the Editor
List of Contributors
1 IoT and Machine Learning-Based Smart Healthcare System for Monitoring Patients
1.1 Introduction
1.2 Literature Survey
1.3 IoT Implementation Model
1.3.1 Communication Protocol for a Smart Healthcare System
1.4 Machine Learning-Based Application for Different Medical Fields
1.4.1 Identifying Diseases and Diagnoses
1.4.2 Drug Manufacture and Identification
1.4.3 Computer Vision-Based Identification of Medical Imaging
1.4.4 Personalized Medicine
1.4.5 Machine Learning-Based Behavioural Modification
1.4.6 Maintaining Health Records Intelligently
1.4.7 Research Work and Clinical Trials
1.4.8 Data Collection
1.4.9 Advancements in Radiotherapy
1.4.10 Making Predictions
1.5 Challenges Faced By 5G With IoT and Machine Learning Techniques
1.6 Future Possibilities for Smart Healthcare Using the IoT and Machine Learning
1.6.1 Recovery at Home
1.6.2 Peace of Mind
1.6.3 Independent Fitness Monitoring
1.6.4 Medicines at the Right Time
1.7 Conclusions and Future Scope
References
2 Detection and Diagnosis of COVID-19 From Chest X-Ray Images Using Deep Learning
2.1 Introduction
2.2 Related Studies
2.3 Method
2.3.1 Dataset
2.3.2 CNNs for Transfer Learning
2.3.2.1 Approach 1: Pre-Trained Model
2.3.2.2 Approach 2: Development of a Model
2.3.3 Performance Metrics
2.4 Results
2.5 Conclusion
References
3 Analysing the Stages of Diabetic Retinopathy Using Deep Learning Techniques
3.1 Introduction
3.2 Methodology
3.3 Modelling and Analysis
3.3.1 Network Architecture and Implementation
3.3.2 Training Method for the Model
3.4 Results
3.4.1 Dataset
3.4.2 Classification Report for the Model
3.4.3 Confusion Matrix
3.5 Discussion
3.6 Conclusions
3.7 Future Scope
References
4 COVID-19 Detection Based On Deep Learning Feature Extraction and AdaBoost Ensemble Classifier
4.1 Introduction
4.1.1 Related Works
4.1.2 Contributions
4.2 COVID-19 Detection
4.2.1 Dataset
4.2.2 Transfer Learning
4.2.3 ResNet
4.2.4 VGG16
4.2.5 AdaBoost Ensemble Classifier
4.3 Preprocessing and Training
4.3.1 Preprocessing
4.3.2 Training
4.4 Results and Discussion
4.5 Conclusions
Acknowledgements
References
5 Deep Learning and Transfer Learning Models for Detection of COVID-19
5.1 Introduction
5.1.1 Literature Search
5.2 Deep Learning (DL)
5.2.1 Transfer Learning (TL)
5.2.1.1 AlexNet
5.2.1.2 VGGNet
5.2.1.3 GoogleNet (Inception and EfficientNet)
5.2.1.4 ResNet
5.2.2 Performance Evaluation
5.2.2.1 Accuracy
5.2.2.2 Sensitivity
5.2.2.3 Specificity
5.2.2.4 Receiver Operating Characteristics (ROC)
5.2.2.5 Area Under the Curve (AUC)
5.2.2.6 F1-Score Or F Measure
5.3 COVID-19 and Pneumonia
5.3.1 Pandemics and Epidemics of the Coronaviridae Family
5.3.1.1 SARS-COV-2 Pandemic
5.3.1.2 MERS-CoV Epidemic
5.3.1.3 SARS-COV-1 Epidemic
5.3.2 Molecular Diagnosis of Coronavirus
5.4 Radiology
5.4.1 X-Ray
5.4.2 CT Scans
5.4.3 Lung Ultrasound
5.4.4 Radiological Datasets
5.4.4.1 COVID-19 X-Ray Images Uploaded By J Paul Cohen
5.4.4.2 COVID-19 Radiography Dataset
5.4.4.3 COVIDx Dataset
5.4.4.4 HCV-UFPR COVID-19 Dataset
5.4.4.5 COVIDx-US
5.4.4.6 SARS-CoV-2 CT Scan Dataset
5.4.4.7 Radiological Society of North America (RSNA) Dataset
5.4.4.8 Chest X-Ray Kermany Et Al. [50]
5.4.4.9 ChestX-Ray8 Uploaded By Wang Et Al. [51]
5.5 Application of Deep Learning Models for the Detection of COVID-19
5.5.1 Binary Classification
5.5.2 Ternary Classification
5.6 Concluding Remarks
5.6.1 Conclusions
5.6.2 Open Research Issues
References
Chapter 6 Industry 4.0 Challenges and Applications in the Healthcare Industry With Emerging Technologies
6.1 Introduction
6.2 Literature Review
6.3 Self-Determination Medicine: A Healthcare Model That Could Be Delivered By 5G Wireless Technology
6.4 IoT and Big Data: A Revolution in the Biomedical Industry
6.4.1 IoT and Big Data Technology for Personalized Medicine
6.4.2 IoT and Big Data Technology for Next-Generation Healthcare
6.5 Role of Artificial Intelligence in Healthcare
6.5.1 Virtual Nurses for Monitoring Patients
6.5.2 Development of Precision Medicine
6.5.3 Digital Consultation Chatbots
6.6 Data Mining: A New Hope in the Healthcare System
6.6.1 Intelligent Heart Disease Prediction System
6.6.2 Diagnosis and Prognosis of Cancer Disease
6.6.3 Customer Relationship Management (CRM) Systems
6.6.4 Avoidance and Early Detection of Various Frauds in the Healthcare Industry
6.7 Introduction of Cyber-Physical Systems to the Healthcare Industry
6.8 Opportunities and Challenges in Healthcare Systems
6.9 Conclusions and Future Scope
References
Chapter 7 Cyber-Security Countermeasures and Vulnerabilities to Prevent Social-Engineering Attacks
7.1 Introduction
7.1.1 AI Techniques Against Cyber-Security Risks
7.1.2 Describing Social Engineering
7.2 The Role of Social Engineering in Cyber Theft
7.3 Social Engineering Approach
7.4 Preventative Steps Against Social Engineering
7.5 Conclusions
References
Chapter 8 Development of a COVID-19 Tracking System
8.1 Introduction
8.2 Related Works
8.3 Methodology
8.3.1 The Dataset
8.3.2 COVID-19 Detection
8.3.3 Functional Requirements
8.3.4 Class Diagram
8.3.5 Hardware and Software Requirements
8.4 Results and Implementation
8.5 Conclusion
Acknowledgements
References
9 An Overview of Autonomous Perception for a Robotic Arm
9.1 Introduction
9.2 Overview
9.2.1 Artificial Neural Networks
9.2.2 Convolutional Neural Network
9.2.3 Recurrent Neural Network
9.3 Grasp Representation
9.3.1 Object Detection
9.3.1.1 Analytical Approach
9.3.1.2 Empirical Approach
9.3.1.3 Empirical Grasp Approach
9.4 Conclusions
Acknowledgements
References
Chapter 10 Artificial Intelligence-Based Methods for SARS-CoV-2 Detection With CRISPR Systems
10.1 Introduction
10.2 CRISPR Overview
10.3 COVID-19 Diagnostic Tools Based On Cas12
10.4 COVID-19 Diagnostic Tools Based On Cas13
10.5 Application of Artificial Intelligence for SARS-CoV-2 Detection Using CRISPR-Based Methods
10.6 Conclusions
References
Index
