Оглавление
Группа авторов. Advanced Healthcare Systems
Table of Contents
List of Illustrations
List of Tables
Guide
Pages
Advanced Healthcare Systems. Empowering Physicians with IoT-Enabled Technologies
Preface
1. Internet of Medical Things—State-of-the-Art
1.1 Introduction
1.2 Historical Evolution of IoT to IoMT
1.2.1 IoT and IoMT—Market Size
1.3 Smart Wearable Technology
1.3.1 Consumer Fitness Smart Wearables
1.3.2 Clinical-Grade Wearables
1.4 Smart Pills
1.5 Reduction of Hospital-Acquired Infections
1.5.1 Navigation Apps for Hospitals
1.6 In-Home Segment
1.7 Community Segment
1.8 Telehealth and Remote Patient Monitoring
1.9 IoMT in Healthcare Logistics and Asset Management
1.10 IoMT Use in Monitoring During COVID-19
1.11 Conclusion
References
2. Issues and Challenges Related to Privacy and Security in Healthcare Using IoT, Fog, and Cloud Computing
2.1 Introduction
2.2 Related Works
2.3 Architecture
2.3.1 Device Layer
2.3.2 Fog Layer
2.3.3 Cloud Layer
2.4 Issues and Challenges
2.5 Conclusion
References
3. Study of Thyroid Disease Using Machine Learning
3.1 Introduction
3.2 Related Works
3.3 Thyroid Functioning
3.4 Category of Thyroid Cancer
3.5 Machine Learning Approach Toward the Detection of Thyroid Cancer
3.5.1 Decision Tree Algorithm
3.5.2 Support Vector Machines
3.5.3 Random Forest
3.5.4 Logistic Regression
3.5.5 Naïve Bayes
3.6 Conclusion
References
4. A Review of Various Security and Privacy Innovations for IoT Applications in Healthcare
4.1 Introduction. 4.1.1 Introduction to IoT
4.1.2 Introduction to Vulnerability, Attack, and Threat
4.2 IoT in Healthcare
4.2.1 Confidentiality
4.2.2 Integrity
4.2.3 Authorization
4.2.4 Availability
4.3 Review of Security and Privacy Innovations for IoT Applications in Healthcare, Smart Cities, and Smart Homes
4.4 Conclusion
References
5. Methods of Lung Segmentation Based on CT Images
5.1 Introduction
5.2 Semi-Automated Algorithm for Lung Segmentation
5.2.1 Algorithm for Tracking to Lung Edge
5.2.2 Outlining the Region of Interest in CT Images
5.2.2.1 Locating the Region of Interest
5.2.2.2 Seed Pixels and Searching Outline
5.3 Automated Method for Lung Segmentation
5.3.1 Knowledge-Based Automatic Model for Segmentation
5.3.2 Automatic Method for Segmenting the Lung CT Image
5.4 Advantages of Automatic Lung Segmentation Over Manual and Semi-Automatic Methods
5.5 Conclusion
References
6. Handling Unbalanced Data in Clinical Images
6.1 Introduction
6.2 Handling Imbalance Data
6.2.1 Cluster-Based Under-Sampling Technique
6.2.2 Bootstrap Aggregation (Bagging)
6.3 Conclusion
References
7. IoT-Based Health Monitoring System for Speech-Impaired People Using Assistive Wearable Accelerometer
7.1 Introduction
7.2 Literature Survey
7.3 Procedure
7.4 Results
7.5 Conclusion
References
8. Smart IoT Devices for the Elderly and People with Disabilities
8.1 Introduction
8.2 Need for IoT Devices
8.3 Where Are the IoT Devices Used?
8.3.1 Home Automation
8.3.2 Smart Appliances
8.3.3 Healthcare
8.4 Devices in Home Automation. 8.4.1 Automatic Lights Control
8.4.2 Automated Home Safety and Security
8.5 Smart Appliances
8.5.1 Smart Oven
8.5.2 Smart Assistant
8.5.3 Smart Washers and Dryers
8.5.4 Smart Coffee Machines
8.5.5 Smart Refrigerator
8.6 Healthcare
8.6.1 Smart Watches
8.6.2 Smart Thermometer
8.6.3 Smart Blood Pressure Monitor
8.6.4 Smart Glucose Monitors
8.6.5 Smart Insulin Pump
8.6.6 Smart Wearable Asthma Monitor
8.6.7 Assisted Vision Smart Glasses
8.6.8 Finger Reader
8.6.9 Braille Smart Watch
8.6.10 Smart Wand
8.6.11 Taptilo Braille Device
8.6.12 Smart Hearing Aid
8.6.13 E-Alarm
8.6.14 Spoon Feeding Robot
8.6.15 Automated Wheel Chair
8.7 Conclusion
References
9. IoT-Based Health Monitoring and Tracking System for Soldiers
9.1 Introduction
9.2 Literature Survey
9.3 System Requirements
9.3.1 Software Requirement Specification
9.3.2 Functional Requirements
9.4 System Design
9.4.1 Features
9.4.1.1 On-Chip Flash Memory
9.4.1.2 On-Chip Static RAM
9.4.2 Pin Control Block
9.4.3 UARTs
9.4.3.1 Features
9.4.4 System Control
9.4.4.1 Crystal Oscillator
9.4.4.2 Phase-Locked Loop
9.4.4.3 Reset and Wake-Up Timer
9.4.4.4 Brown Out Detector
9.4.4.5 Code Security
9.4.4.6 External Interrupt Inputs
9.4.4.7 Memory Mapping Control
9.4.4.8 Power Control
9.4.5 Real Monitor
9.4.5.1 GPS Module
9.4.6 Temperature Sensor
9.4.7 Power Supply
9.4.8 Regulator
9.4.9 LCD
9.4.10 Heart Rate Sensor
9.5 Implementation
9.5.1 Algorithm
9.5.2 Hardware Implementation
9.5.3 Software Implementation
9.6 Results and Discussions
9.6.1 Heart Rate
9.6.2 Temperature Sensor
9.6.3 Panic Button
9.6.4 GPS Receiver
9.7 Conclusion
References
10. Cloud-IoT Secured Prediction System for Processing and Analysis of Healthcare Data Using Machine Learning Techniques
10.1 Introduction
10.2 Literature Survey
10.3 Medical Data Classification
10.3.1 Structured Data
10.3.2 Semi-Structured Data
10.4 Data Analysis
10.4.1 Descriptive Analysis
10.4.2 Diagnostic Analysis
10.4.3 Predictive Analysis
10.4.4 Prescriptive Analysis
10.5 ML Methods Used in Healthcare
10.5.1 Supervised Learning Technique
10.5.2 Unsupervised Learning
10.5.3 Semi-Supervised Learning
10.5.4 Reinforcement Learning
10.6 Probability Distributions
10.6.1 Discrete Probability Distributions
10.6.1.1 Bernoulli Distribution
10.6.1.2 Uniform Distribution
10.6.1.3 Binomial Distribution
10.6.1.4 Normal Distribution
10.6.1.5 Poisson Distribution
10.6.1.6 Exponential Distribution
10.7 Evaluation Metrics
10.7.1 Classification Accuracy
10.7.2 Confusion Matrix
10.7.3 Logarithmic Loss
10.7.4 Receiver Operating Characteristic Curve, or ROC Curve
10.7.5 Area Under Curve (AUC)
10.7.6 Precision
10.7.7 Recall
10.7.8 F1 Score
10.7.9 Mean Absolute Error
10.7.10 Mean Squared Error
10.7.11 Root Mean Squared Error
10.7.12 Root Mean Squared Logarithmic Error
10.7.13 R-Squared/Adjusted R-Squared
10.7.14 Adjusted R-Squared
10.8 Proposed Methodology
10.8.1 Neural Network
10.8.2 Triangular Membership Function
10.8.3 Data Collection
10.8.4 Secured Data Storage
10.8.5 Data Retrieval and Merging
10.8.6 Data Aggregation
10.8.7 Data Partition
10.8.8 Fuzzy Rules for Prediction of Heart Disease
10.8.9 Fuzzy Rules for Prediction of Diabetes
10.8.10 Disease Prediction With Severity and Diagnosis
10.9 Experimental Results
10.10 Conclusion
References
11. CloudIoT-Driven Healthcare: Review, Architecture, Security Implications, and Open Research Issues
11.1 Introduction
11.2 Background Elements
11.2.1 Security Comparison Between Traditional and IoT Networks
11.3 Secure Protocols and Enabling Technologies for CloudIoT Healthcare Applications
11.3.1 Security Protocols
11.3.2 Enabling Technologies
11.4 CloudIoT Health System Framework
11.4.1 Data Perception/Acquisition
11.4.2 Data Transmission/Communication
11.4.3 Cloud Storage and Warehouse
11.4.4 Data Flow in Healthcare Architecture – A Conceptual Framework
11.4.5 Design Considerations
11.5 Security Challenges and Vulnerabilities
11.5.1 Security Characteristics and Objectives
11.5.1.1 Confidentiality
11.5.1.2 Integrity
11.5.1.3 Availability
11.5.1.4 Identification and Authentication
11.5.1.5 Privacy
11.5.1.6 Light Weight Solutions
11.5.1.7 Heterogeneity
11.5.1.8 Policies
11.5.2 Security Vulnerabilities
11.5.2.1 IoT Threats and Vulnerabilities
11.5.2.1.1 Perception Level Threats
11.5.2.1.2 Network Level Threats
11.5.2.1.3 Application Level treats
11.5.2.2 Cloud-Based Threats
11.6 Security Countermeasures and Considerations. 11.6.1 Security Countermeasures
11.6.1.1 Security Awareness and Survey
11.6.1.2 Security Architecture and Framework
11.6.1.3 Key Management
11.6.1.4 Authentication
11.6.1.5 Trust
11.6.1.6 Cryptography
11.6.1.7 Device Security
11.6.1.8 Identity Management
11.6.1.9 Risk-Based Security/Risk Assessment
11.6.1.10 Block Chain-Based Security
11.6.1.11 Automata-Based Security
11.6.2 Security Considerations
11.7 Open Research Issues and Security Challenges
11.7.1 Security Architecture
11.7.2 Resource Constraints
11.7.3 Heterogeneous Data and Devices
11.7.4 Protocol Interoperability
11.7.5 Trust Management and Governance
11.7.6 Fault Tolerance
11.7.7 Next-Generation 5G Protocol
11.8 Discussion and Analysis
11.9 Conclusion
References
12. A Novel Usage of Artificial Intelligence and Internet of Things in RemoteBased Healthcare Applications
12.1 Introduction Machine Learning
12.2 Importance of Machine Learning
12.2.1 ML vs. Classical Algorithms
12.2.2 Learning Supervised
12.2.3 Unsupervised Learning
12.2.4 Network for Neuralism. 12.2.4.1 Definition of the Neural Network
12.2.4.2 Neural Network Elements
12.3 Procedure. 12.3.1 Dataset and Seizure Identification
12.3.2 System
12.4 Feature Extraction
12.5 Experimental Methods
12.5.1 Stepwise Feature Optimization
12.5.2 Post-Classification Validation
12.5.3 Fusion of Classification Methods
12.6 Experiments
12.7 Framework for EEG Signal Classification
12.8 Detection of the Preictal State
12.9 Determination of the Seizure Prediction Horizon
12.10 Dynamic Classification Over Time
12.11 Conclusion
References
13. Use of Machine Learning in Healthcare
13.1 Introduction
13.2 Uses of Machine Learning in Pharma and Medicine
13.2.1 Distinguish Illnesses and Examination
13.2.2 Drug Discovery and Manufacturing
13.2.3 Scientific Imaging Analysis
13.2.4 Twisted Therapy
13.2.5 AI to Know-Based Social Change
13.2.6 Perception Wellness Realisms
13.2.7 Logical Preliminary and Exploration
13.2.8 Publicly Supported Perceptions Collection
13.2.9 Better Radiotherapy
13.2.10 Incidence Forecast
13.3 The Ongoing Preferences of ML in Human Services
13.4 The Morals of the Use of Calculations in Medicinal Services
13.5 Opportunities in Healthcare Quality Improvement
13.5.1 Variation in Care
13.5.2 Inappropriate Care
13.5.3 Prevents Care–Associated Injurious and Death for Carefrontation
13.5.4 The Fact That People Are Unable to do What They Know Works
13.5.5 A Waste
13.6 A Team-Based Care Approach Reduces Waste
13.7 Conclusion
References
14. Methods of MRI Brain Tumor Segmentation
14.1 Introduction
14.2 Generative and Descriptive Models
14.2.1 Region-Based Segmentation
14.2.2 Generative Model With Weighted Aggregation
14.3 Conclusion
References
15. Early Detection of Type 2 Diabetes Mellitus Using Deep Neural Network–Based Model
15.1 Introduction
15.2 Data Set
15.2.1 Data Insights
15.3 Feature Engineering
15.4 Framework for Early Detection of Disease
15.4.1 Deep Neural Network
15.5 Result
15.6 Conclusion
References
16. A Comprehensive Analysis on Masked Face Detection Algorithms
16.1 Introduction
16.2 Literature Review
16.3 Implementation Approach
16.3.1 Feature Extraction
16.3.2 Image Processing
16.3.3 Image Acquisition
16.3.4 Classification
16.3.5 MobileNetV2
16.3.6 Deep Learning Architecture
16.3.7 LeNet-5, AlexNet, and ResNet-50
16.3.8 Data Collection
16.3.9 Development of Model
16.3.10 Training of Model
16.3.11 Model Testing
16.4 Observation and Analysis
16.4.1 CNN Algorithm
16.4.2 SSDNETV2 Algorithm
16.4.3 SVM
16.5 Conclusion
References
17. IoT-Based Automated Healthcare System
17.1 Introduction
17.1.1 Software-Defined Network
17.1.2 Network Function Virtualization
17.1.3 Sensor Used in IoT Devices
17.2 SDN-Based IoT Framework
17.3 Literature Survey
17.4 Architecture of SDN-IoT for Healthcare System
17.5 Challenges
17.6 Conclusion
References
Index
WILEY END USER LICENSE AGREEMENT
