Оглавление
Группа авторов. Emerging Technologies for Healthcare
Table of Contents
Guide
List of Illustrations
List of Tables
Pages
Emerging Technologies for Healthcare. Internet of Things and Deep Learning Models
Preface
1. An Overview of IoT in Health Sectors
1.1 Introduction
1.2 Influence of IoT in Healthcare Systems
1.2.1 Health Monitoring
1.2.2 Smart Hospitals
1.2.3 Tracking Patients
1.2.4 Transparent Insurance Claims
1.2.5 Healthier Cities
1.2.6 Research in Health Sector
1.3 Popular IoT Healthcare Devices
1.3.1 Hearables
1.3.2 Moodables
1.3.3 Ingestible Sensors
1.3.4 Computer Vision
1.3.5 Charting in Healthcare
1.4 Benefits of IoT
1.4.1 Reduction in Cost
1.4.2 Quick Diagnosis and Improved Treatment
1.4.3 Management of Equipment and Medicines
1.4.4 Error Reduction
1.4.5 Data Assortment and Analysis
1.4.6 Tracking and Alerts
1.4.7 Remote Medical Assistance
1.5 Challenges of IoT
1.5.1 Privacy and Data Security
1.5.2 Multiple Devices and Protocols Integration
1.5.3 Huge Data and Accuracy
1.5.4 Underdeveloped
1.5.5 Updating the Software Regularly
1.5.6 Global Healthcare Regulations
1.5.7 Cost
1.6 Disadvantages of IoT
1.6.1 Privacy
1.6.2 Access by Unauthorized Persons
1.7 Applications of IoT
1.7.1 Monitoring of Patients Remotely
1.7.2 Management of Hospital Operations
1.7.3 Monitoring of Glucose
1.7.4 Sensor Connected Inhaler
1.7.5 Interoperability
1.7.6 Connected Contact Lens
1.7.7 Hearing Aid
1.7.8 Coagulation of Blood
1.7.9 Depression Detection
1.7.10 Detection of Cancer
1.7.11 Monitoring Parkinson Patient
1.7.12 Ingestible Sensors
1.7.13 Surgery by Robotic Devices
1.7.14 Hand Sanitizing
1.7.15 Efficient Drug Management
1.7.16 Smart Sole
1.7.17 Body Scanning
1.7.18 Medical Waste Management
1.7.19 Monitoring the Heart Rate
1.7.20 Robot Nurse
1.8 Global Smart Healthcare Market
1.9 Recent Trends and Discussions
1.10 Conclusion
References
2. IoT-Based Solutions for Smart Healthcare
2.1 Introduction
2.1.1 Process Flow of Smart Healthcare System
2.1.1.1 Data Source
2.1.1.2 Data Acquisition
2.1.1.3 Data Pre-Processing
2.1.1.4 Data Segmentation
2.1.1.5 Feature Extraction
2.1.1.6 Data Analytics
2.1.1.6.1 Descriptive Analytics
2.1.1.6.2 Diagnostic Analytics
2.1.1.6.3 Predictive Analytics
2.1.1.6.4 Prescriptive Analytics
2.2 IoT Smart Healthcare System
2.2.1 System Architecture
2.2.1.1 Stage 1: Perception Layer
2.2.1.2 Stage 2: Network Layer
2.2.1.3 Stage 3: Data Processing Layer
2.2.1.4 Stage 4: Application Layer
2.3 Locally and Cloud-Based IoT Architecture
2.3.1 System Architecture
2.3.1.1 Body Area Network (BAN)
2.3.1.2 Smart Server
2.3.1.3 Care Unit
2.4 Cloud Computing
2.4.1 Infrastructure as a Service (IaaS)
2.4.2 Platform as a Service (PaaS)
2.4.3 Software as a Service (SaaS)
2.4.4 Types of Cloud Computing
2.4.4.1 Public Cloud
2.4.4.2 Private Cloud
2.4.4.3 Hybrid Cloud
2.4.4.4 Community Cloud
2.5 Outbreak of Arduino Board
2.6 Applications of Smart Healthcare System
2.6.1 Disease Diagnosis and Treatment
2.6.2 Health Risk Monitoring
2.6.3 Voice Assistants
2.6.4 Smart Hospital
2.6.5 Assist in Research and Development
2.7 Smart Wearables and Apps
2.8 Deep Learning in Biomedical
2.8.1 Deep Learning
2.8.2 Deep Neural Network Architecture
2.8.3 Deep Learning in Bioinformatic
2.8.4 Deep Learning in Bioimaging
2.8.5 Deep Learning in Medical Imaging
2.8.6 Deep Learning in Human-Machine Interface
2.8.7 Deep Learning in Health Service Management
2.9 Conclusion
References
3. QLattice Environment and Feyn QGraph Models—A New Perspective Toward Deep Learning
3.1 Introduction
3.1.1 Machine Learning Models
3.2 Machine Learning Model Lifecycle
3.2.1 Steps in Machine Learning Lifecycle
3.2.1.1 Data Preparation
3.2.1.2 Building the Machine Learning Model
3.2.1.3 Model Training
3.2.1.4 Parameter Selection
3.2.1.5 Transfer Learning
3.2.1.6 Model Verification
3.2.1.7 Model Deployment
3.2.1.8 Monitoring
3.3 A Model Deployment in Keras
3.3.1 Pima Indian Diabetes Dataset
3.3.2 Multi-Layered Perceptron Implementation in Keras
3.3.3 Multi-Layered Perceptron Implementation With Dropout and Added Noise
3.4 QLattice Environment
3.4.1 Feyn Models
3.4.1.1 Semantic Types
3.4.1.2 Interactions
3.4.1.3 Generating QLattice
3.4.2 QLattice Workflow
3.4.2.1 Preparing the Data
3.4.2.2 Connecting to QLattice
3.4.2.3 Generating QGraphs
3.4.2.4 Fitting, Sorting, and Updating QGraphs
3.4.2.5 Model Evaluation
3.5 Using QLattice Environment and QGraph Models for COVID-19 Impact Prediction
References
4. Sensitive Healthcare Data: Privacy and Security Issues and Proposed Solutions
4.1 Introduction
4.1.1 Types of Technologies Used in Healthcare Industry
4.1.2 Technical Differences Between Security and Privacy
4.1.3 HIPAA Compliance
4.2 Medical Sensor Networks/Medical Internet of Things/Body Area Networks/WBANs
4.2.1 Security and Privacy Issues in WBANs/WMSNs/WMIOTs
4.3 Cloud Storage and Computing on Sensitive Healthcare Data
4.3.1 Security and Privacy in Cloud Computing and Storage for Sensitive Healthcare Data
4.4 Blockchain for Security and Privacy Enhancement in Sensitive Healthcare Data
4.5 Artificial Intelligence, Machine Learning, and Big Data in Healthcare and Its Efficacy in Security and Privacy of Sensitive Healthcare Data
4.5.1 Differential Privacy for Preserving Privacy of Big Medical Healthcare Data and for Its Analytics
4.6 Conclusion
References
5. Diabetes Prediction Model Based on Machine Learning
5.1 Introduction
5.2 Literature Review
5.3 Proposed Methodology
5.3.1 Data Accommodation
5.3.1.1 Data Collection
5.3.1.2 Data Preparation
5.3.2 Model Training
5.3.2.1 K Nearest Neighbor Classification Technique
5.3.2.2 Support Vector Machine
5.3.2.3 Random Forest Algorithm
5.3.2.4 Logistic Regression
5.3.3 Model Evaluation
5.3.4 User Interaction
5.3.4.1 User Inputs
5.3.4.2 Validation Using Classifier Model
5.3.4.3 Truth Probability
5.4 System Implementation
5.5 Conclusion
References
6. Lung Cancer Detection Using 3D CNN Based on Deep Learning
6.1 Introduction
6.2 Literature Review
6.3 Proposed Methodology. 6.3.1 Data Handling
6.3.1.1 Data Gathering
6.3.1.2 Data Pre-Processing
6.3.2 Data Visualization and Data Split. 6.3.2.1 Data Visualization
6.3.2.2 Data Split
6.3.3 Model Training. 6.3.3.1 Training Neural Network
6.3.3.2 Model Optimization
6.4 Results and Discussion
6.4.1 Gathering and Pre-Processing of Data. 6.4.1.1 Gathering and Handling Data
6.4.1.2 Pre-Processing of Data
6.4.2 Data Visualization
6.4.2.1 Resampling
6.4.2.2 3D Plotting Scan
6.4.2.3 Lung Segmentation
6.4.3 Training and Testing of Data in 3D Architecture
6.5 Conclusion
References
7. Pneumonia Detection Using CNN and ANN Based on Deep Learning Approach
7.1 Introduction
7.2 Literature Review
7.3 Proposed Methodology
7.3.1 Data Gathering. 7.3.1.1 Data Collection
7.3.1.2 Data Pre-Processing
7.3.1.3 Data Split
7.3.2 Model Training
7.3.2.1 Training of Convolutional Neural Network
7.3.2.2 Training of Artificial Neural Network
7.3.3 Model Fitting. 7.3.3.1 Fit Generator
7.3.3.2 Validation of Accuracy and Loss Plot
7.3.3.3 Testing and Prediction
7.4 System Implementation
7.4.1 Data Gathering, Pre-Processing, and Split. 7.4.1.1 Data Gathering
7.4.1.2 Data Pre-Processing
7.4.1.3 Data Split
7.4.2 Model Building
7.4.3 Model Fitting. 7.4.3.1 Fit Generator
7.4.3.2 Validation of Accuracy and Loss Plot
7.4.3.3 Testing and Prediction
7.5 Conclusion
References
8. Personality Prediction and Handwriting Recognition Using Machine Learning
8.1 Introduction to the System
8.1.1 Assumptions and Limitations. 8.1.1.1 Assumptions
8.1.1.2 Limitations
8.1.2 Practical Needs
8.1.3 Non-Functional Needs
8.1.4 Specifications for Hardware
8.1.5 Specifications for Applications
8.1.6 Targets
8.1.7 Outcomes
8.2 Literature Survey. 8.2.1 Computerized Human Behavior Identification Through Handwriting Samples [5]
8.2.2 Behavior Prediction Through Handwriting Analysis [14]
8.2.3 Handwriting Sample Analysis for a Finding of Personality Using Machine Learning Algorithms [15]
8.2.4 Personality Detection Using Handwriting Analysis [16]
8.2.5 Automatic Predict Personality Based on Structure of Handwriting [17]
8.2.6 Personality Identification Through Handwriting Analysis: A Review [6]
8.2.7 Text Independent Writer Identification Using Convolutional Neural Network [18]
8.2.8 Writer Identification Using Machine Learning Approaches [19]
8.2.9 Writer Identification from Handwritten Text Lines [20]
8.3 Theory. 8.3.1 Pre-Processing
8.3.2 Personality Analysis
8.3.3 Personality Characteristics
8.3.4 Writer Identification
8.3.5 Features Used
8.4 Algorithm To Be Used
Training of Artificial Neural Network Algorithm:
8.5 Proposed Methodology
8.5.1 System Flow
8.6 Algorithms vs. Accuracy
8.6.1 Implementation
8.7 Experimental Results
8.8 Conclusion
8.9 Conclusion and Future Scope
Acknowledgment
References
9. Risk Mitigation in Children With Autism Spectrum Disorder Using Brain Source Localization
9.1 Introduction
9.2 Risk Factors Related to Autism
9.2.1 Assistive Technologies for Autism
9.2.2 Functional Connectivity as a Biomarker for Autism
9.2.3 Early Intervention and Diagnosis
9.3 Materials and Methodology. 9.3.1 Subjects
9.3.2 Methods
9.3.3 Data Acquisition and Processing
9.3.4 sLORETA as a Diagnostic Tool
9.4 Results and Discussion
9.5 Conclusion and Future Scope
References
10. Predicting Chronic Kidney Disease Using Machine Learning
10.1 Introduction
10.2 Machine Learning Techniques for Prediction of Kidney Failure
10.2.1 Analysis and Empirical Learning
10.2.2 Supervised Learning
10.2.3 Unsupervised Learning
10.2.3.1 Understanding and Visualization
10.2.3.2 Odd Detection
10.2.3.3 Object Completion
10.2.3.4 Information Acquisition
10.2.3.5 Data Compression
10.2.3.6 Capital Market
10.2.4 Classification
10.2.4.1 Training Process
10.2.4.2 Testing Process
10.2.5 Decision Tree
10.2.6 Regression Analysis
10.2.6.1 Logistic Regression
10.2.6.2 Ordinal Logistic Regression
10.2.6.3 Estimating Parameters
10.2.6.4 Multivariate Regression
10.3 Data Sources
10.4 Data Analysis
10.5 Conclusion
10.6 Future Scope
References
11. Behavioral Modeling Using Deep Neural Network Framework for ASD Diagnosis and Prognosis
11.1 Introduction
11.2 Automated Diagnosis of ASD
11.2.1 Deep Learning
11.2.2 Deep Learning in ASD
11.2.3 Transfer Learning Approach
11.3 Purpose of the Chapter
11.4 Proposed Diagnosis System
11.5 Conclusion
References
12. Random Forest Application of Twitter Data Sentiment Analysis in Online Social Network Prediction
12.1 Introduction. 12.1.1 Motivation
12.1.2 Domain Introduction
12.2 Literature Survey
12.3 Proposed Methodology
12.4 Implementation
12.5 Conclusion
References
13. Remedy to COVID-19: Social Distancing Analyzer
13.1 Introduction
13.2 Literature Review
13.3 Proposed Methodology
13.3.1 Person Detection
13.3.1.1 Frame Creation
13.3.1.2 Contour Detection
13.3.1.3 Matching with COCO Model
13.3.2 Distance Calculation
13.3.2.1 Calculation of Centroid
13.3.2.2 Distance Among Adjacent Centroids
13.4 System Implementation
13.5 Conclusion
References
14. IoT-Enabled Vehicle Assistance System of Highway Resourcing for Smart Healthcare and Sustainability
14.1 Introduction
14.2 Related Work
14.2.1 Adoption of IoT in Vehicle to Ensure Driver Safety
14.2.2 IoT in Healthcare System
14.2.3 The Technology Used in Assistance Systems
14.2.3.1 Adaptive Cruise Control (ACC)
14.2.3.2 Lane Departure Warning
14.2.3.3 Parking Assistance
14.2.3.4 Collision Avoidance System
14.2.3.5 Driver Drowsiness Detection
14.2.3.6 Automotive Night Vision
14.3 Objectives, Context, and Ethical Approval
14.4 Technical Background. 14.4.1 IoT With Health
14.4.2 Machine-to-Machine (M2M) Communication
14.4.3 Device-to-Device (D2D) Communication
14.4.4 Wireless Sensor Network
14.4.5 Crowdsensing
14.5 IoT Infrastructural Components for Vehicle Assistance System
14.5.1 Communication Technology
14.5.2 Sensor Network
14.5.3 Infrastructural Component
14.5.4 Human Health Detection by Sensors
14.6 IoT-Enabled Vehicle Assistance System of Highway Resourcing for Smart Healthcare and Sustainability
14.7 Challenges in Implementation
14.8 Conclusion
References
15. Aids of Machine Learning for Additively Manufactured Bone Scaffold
15.1 Introduction
15.1.1 Bone Scaffold
15.1.2 Bone Grafting
15.1.3 Comparison Bone Grafting and Bone Scaffold
15.2 Research Background
15.3 Statement of Problem
15.4 Research Gap
15.5 Significance of Research
15.6 Outline of Research Methodology
15.6.1 Customized Design of Bone Scaffold
15.6.2 Manufacturing Methods and Biocompatible Material
15.6.2.1 Conventional Scaffold Fabrication
15.6.2.2 Additive Manufacturing
15.6.2.3 Application of Additive Manufacturing/3D Printing in Healthcare
15.6.2.4 Automated Process Monitoring in 3D Printing Using Supervised Machine Learning
15.7 Conclusion
References
Index
WILEY END USER LICENSE AGREEMENT
