Evolving Role of AI and IoMT in the Healthcare Market

About the Book
Contents
About the Editors
Chapter 1: A Study of Time Series Forecasting Techniques for COVID-19 Trends
	1.1 Introduction
	1.2 Data Source
	1.3 Exploratory Data Analysis
		1.3.1 Pearson´s Correlation Coefficient
		1.3.2 Autocorrelation
	1.4 Data Cleaning and Preparation
		1.4.1 NaN
		1.4.2 Missing Values
	1.5 Forecasting Models
		1.5.1 Baseline Models
			1.5.1.1 Mean-Based Forecasting
				1.5.1.1.1 Theory
				1.5.1.1.2 Application to Data (Fig. 1.3)
				1.5.1.1.3 Remarks
			1.5.1.2 Naïve Forecasting
				1.5.1.2.1 Theory
				1.5.1.2.2 Application to Data (Fig. 1.4)
				1.5.1.2.3 Remarks
			1.5.1.3 Drift-Based Forecasting
				1.5.1.3.1 Theory
				1.5.1.3.2 Application to Data (Fig. 1.5)
				1.5.1.3.3 Remarks
		1.5.2 Exponential Smoothing Models
			1.5.2.1 Single Exponential Smoothing
				1.5.2.1.1 Theory
				1.5.2.1.2 Application to Data (Fig. 1.6)
				1.5.2.1.3 Remarks
			1.5.2.2 Double Exponential Smoothing
				1.5.2.2.1 Double Exponential Smoothing: Additive Trend
					Theory
					Application to Data (Figs. 1.7 and 1.8)
					Remarks
				1.5.2.2.2 Double Exponential Smoothing: Multiplicative Trend
					Theory
					Application to Data (Figs. 1.9 and 1.10)
					Remarks
			1.5.2.3 Triple Exponential Smoothing
		1.5.3 ARIMA
			1.5.3.1 Theory
			1.5.3.2 Application to Data (Fig. 1.11)
			1.5.3.3 Remarks
		1.5.4 LSTM
			1.5.4.1 Theory
			1.5.4.2 Application to Data (Fig. 1.12)
			1.5.4.3 Remarks
	1.6 Evaluation and Comparison of Forecasting Models
		1.6.1 Performance Metrics
		1.6.2 Model Evaluation and Comparison
			1.6.2.1 Time Series 1: India: Total Cases
			1.6.2.2 Time Series 2: India: New Cases
			1.6.2.3 Time Series 3: China: Total Cases
			1.6.2.4 Time Series 4: China: New Cases
			1.6.2.5 Time Series 5: United States: Total Cases
			1.6.2.6 Time Series 6: United States: New Cases
	1.7 Limitations
		1.7.1 Limitations in Data
		1.7.2 Limitations in Modelling
	1.8 Conclusion
	References
Chapter 2: EEG Analysis Using Bio-Inspired Metaheuristic Approach
	2.1 Introduction
	2.2 Generalized System Model for Neurological Disease Detection
	2.3 Metaheuristic Approaches
	2.4 Application of BI Approaches in Neurological Disease Detection
		2.4.1 Alzheimer´s Disease Detection Using BI
		2.4.2 Autism Disease Detection Using BI
		2.4.3 Parkinson Disease Detection Using BI
		2.4.4 Epilepsy Disease Detection Using BI
	2.5 Conclusion
	References
Chapter 3: Secure Recommendation System for Healthcare Applications Using Artificial Intelligence
	3.1 Introduction
	3.2 Secure Recommendation System
		3.2.1 Cloud Users with Different Interests
		3.2.2 Trusted Third Party
		3.2.3 Cloud Service Provider
		3.2.4 Cloud Users with the Same Interest
	3.3 Tag Matching Mechanism
		3.3.1 Setup
		3.3.2 Key Generation
		3.3.3 Communication Key Generation
		3.3.4 Encryption
		3.3.5 Decryption
	3.4 Security Analysis
		3.4.1 Impersonation Attack
		3.4.2 Replay Attack
		3.4.3 Man in the Middle Attack
		3.4.4 Eavesdropping
		3.4.5 DDoS Attack
	3.5 Experimental Analysis
		3.5.1 Phase of Key Computation
		3.5.2 Phase of Encryption
		3.5.3 Phase of Decryption
		3.5.4 Communication Complexity
	3.6 Conclusions and Future Works
	References
Chapter 4: IoT Based Healthcare: A Review
	4.1 Introduction
	4.2 Literature Review
	4.3 Applications of IoT in Healthcare
		4.3.1 IoT Based Diabetes Management
		4.3.2 IoT Devices for Asthma Management
		4.3.3 IoT for Mental Health
		4.3.4 IoT Role in Pandemic Situation
		4.3.5 IoT for Sleep Disorder
	4.4 Working of IOT Devices
	4.5 Role of Cloud in IoT Based Healthcare
	4.6 Benefits and Challenges
	4.7 Conclusion and Future Scope
	References
Chapter 5: Diagnosing Alzheimer´s Disease Using Deep Learning Techniques
	5.1 Introduction
	5.2 Brain Structure
		5.2.1 Cerebral Cortex
		5.2.2 Corpus Callosum
		5.2.3 Cerebellum
		5.2.4 Brain Stem
		5.2.5 Limbic System
		5.2.6 Amygdala
		5.2.7 Hippocampus
		5.2.8 Thalamus
		5.2.9 Hypothalamus
	5.3 Alzheimer Disease-Introduction
		5.3.1 Some Statistics
		5.3.2 Impairments in Alzheimer Disease
	5.4 Alzheimer´s Disease Vs. Dementia Vs. Normal Aging
		5.4.1 Stages of Alzheimer
	5.5 Different Procedure to Find Alzheimer Disease
		5.5.1 Image Capturing
		5.5.2 Cerebrospinal Fluid (CSF) Procedure
		5.5.3 Deep Learning Techniques
			5.5.3.1 Activation Function
				5.5.3.1.1 Step Function
				5.5.3.1.2 Sigmoid Function
				5.5.3.1.3 Tanh Function
				5.5.3.1.4 ReLU Function
				5.5.3.1.5 Neural Networks
				5.5.3.1.6 Convolutional Neural Networks (CNN)
				5.5.3.1.7 Pooling
				5.5.3.1.8 Recurrent Neural Networks (RNN)
	5.6 Deep Learning Methods Comparison
	5.7 Conclusion
	References
Chapter 6: Artificial Intelligence and Blockchain: The Future of Healthcare
	6.1 Introduction
		6.1.1 Introduction to Artificial Intelligence
		6.1.2 How Does Artificial Intelligence Work?
		6.1.3 Uses of A.I.
			6.1.3.1 Narrow A.I.
			6.1.3.2 Artificial A.I.
		6.1.4 Components of Artificial Intelligence
		6.1.5 Artificial Intelligence and Healthcare
			6.1.5.1 Various Areas of Expertise in Medicine Have Demonstrated an Improvement in Studies on A.I.
				6.1.5.1.1 Radiology
				6.1.5.1.2 Psychiatry
				6.1.5.1.3 Screening
				6.1.5.1.4 Disease Diagnosis
				6.1.5.1.5 Telehealth
				6.1.5.1.6 Electronic Health Record
				6.1.5.1.7 Primary Care
				6.1.5.1.8 Drug Interaction
				6.1.5.1.9 Robo Dentist
				6.1.5.1.10 AI Doctors
				6.1.5.1.11 Non-adherence
	6.2 Introduction to Blockchain
		6.2.1 Features of Blockchain
			6.2.1.1 Accuracy of Chain
			6.2.1.2 Cost Reductions
			6.2.1.3 Decentralization
			6.2.1.4 Private Transactions
			6.2.1.5 Efficient Transactions
			6.2.1.6 Transparency
			6.2.1.7 Secure Transactions
		6.2.2 Types of Blockchain
			6.2.2.1 Public Blockchain
			6.2.2.2 Sidechains
			6.2.2.3 Proprietary Blockchain
			6.2.2.4 Hybrid Blockchain
		6.2.3 Uses of Blockchain
			6.2.3.1 Cryptocurrency
			6.2.3.2 Financial Services
			6.2.3.3 Domain Names
			6.2.3.4 Video Games
		6.2.4 Blockchain and Healthcare
		6.2.5 Companies Installed Blockchain
			6.2.5.1 BurstIQ
			6.2.5.2 Medical Chain
			6.2.5.3 Factom
			6.2.5.4 Guardtime
		6.2.6 Medical Records and Health Plans
			6.2.6.1 Simply Vital Health
			6.2.6.2 Robomed
			6.2.6.3 Coral Health
			6.2.6.4 Patientory
		6.2.7 Supply Chain Management Associated with Blockchain
			6.2.7.1 Blockpharma
			6.2.7.2 Chronicled
			6.2.7.3 Tierion
			6.2.7.4 CDC
		6.2.8 Medical Credential Tracking
			6.2.8.1 Drug Trials
			6.2.8.2 Payment Through Crypto
			6.2.8.3 Access of Medical Records
	6.3 Conclusion
	References
Chapter 7: Role of Artificial Intelligence for Skin Cancer Detection
	7.1 Introduction
	7.2 Related Works
		7.2.1 Detection and Analysis of the Type of Skin Cancer
		7.2.2 HCI: Human-Computer Interaction
	7.3 Comparison Table (Tables 7.1 and 7.2)
	7.4 Conclusion
	References
Chapter 8: Evolving IoT and Green IoT in Healthcare Perspective
	8.1 Introduction
		8.1.1 Genesis of IoT
	8.2 Advantages of IoT
		8.2.1 Information
		8.2.2 Tracking
		8.2.3 Time
		8.2.4 Money
	8.3 Challenges of IoT Implementation
		8.3.1 Technology
			8.3.1.1 Security
			8.3.1.2 Connectivity
			8.3.1.3 Compatibility and Longevity
			8.3.1.4 Standards
			8.3.1.5 Intelligent Analysis
	8.4 Application of IoT
		8.4.1 Digital Ceiling
	8.5 Architecture of IoT
		8.5.1 Physical Device and Controllers (The Things of IoT)
		8.5.2 Connectivity (Communication and Processing Unit)
		8.5.3 Edge Computing
		8.5.4 Data Accumulation (Storage)
		8.5.5 Data Abstraction (Aggregation Access)
		8.5.6 Application (Reporting, Analytics, Control)
		8.5.7 Collaboration Process (Involving Process of People and Business)
	8.6 IoT in Healthcare Domain
		8.6.1 Future Success of IoT in Healthcare
	8.7 Application of Healthcare IoT
		8.7.1 U-Healthcare IoT
		8.7.2 Automatic/Controller Wheelchair
		8.7.3 WBAN
	8.8 Green IoT
	8.9 Energy Efficient Approaches for Enabling Green IOT
		8.9.1 Industrial Automation
			8.9.1.1 Smart Industrial Plants
			8.9.1.2 Smart Plant Monitoring
		8.9.2 Health and Living
			8.9.2.1 Real-Time Following
			8.9.2.2 Smart Information Assortment
		8.9.3 Habitat Monitoring
			8.9.3.1 Smart Animal
			8.9.3.2 Smart Building
		8.9.4 Energy
		8.9.5 Transportation
			8.9.5.1 Smart Parking
			8.9.5.2 Smart Traffic
	8.10 Green IoT Association in Healthcare
		8.10.1 Existing WBAN Technologies
		8.10.2 Existing Solar Energy Harvesting of IoT
			8.10.2.1 Green Energy Wireless Charging
			8.10.2.2 Photovoltaic Cell Energy Harvesting
	8.11 Conclusion
	8.12 Future Scope
	References
Chapter 9: A Review in Wavelet Transforms Based Medical Image Fusion
	9.1 Introduction
	9.2 Wavelet Transform
		9.2.1 Discrete Wavelet Transform (DWT)
		9.2.2 Multiresolution Analysis
	9.3 Wavelet and Bio Inspired Computation Based Fusion
	9.4 Result and Discussions
	9.5 Conclusion
	References
Chapter 10: Cloud-Based Intelligent Internet of Medical Things Applications for Healthcare Systems
	10.1 Introduction
		10.1.1 Smart Ambulance
		10.1.2 Managing Hospitals Medical Record
		10.1.3 Digital Consultation
		10.1.4 Virtual Nurse
		10.1.5 Prediction for the Risk of Coronary Heart Disease
		10.1.6 Human Sitting Posture Recognition System
	10.2 Conclusion
	References
Chapter 11: Development of Intelligent Approach to Detect Retinal Microaneurysm
	11.1 Introduction
		11.1.1 Diabetic Retinopathy Stages
		11.1.2 Techniques of Fundus Imaging
			11.1.2.1 Red-Free Fundus Photography
			11.1.2.2 Colour Fundus Imaging
			11.1.2.3 Fundus Autofluorescence
		11.1.3 Retinal Imaging
		11.1.4 Modalities of Retina Fundus Imaging
			11.1.4.1 Standard View
			11.1.4.2 Ultra-Wide Field
			11.1.4.3 Smartphone-Based Images
	11.2 Related Works
	11.3 Methodology
		11.3.1 Pre-Processing
		11.3.2 Mapping of Images to Text
		11.3.3 MA Detection Using Multi Sieving Convolution Neural Networks
		11.3.4 Probabilistic Neural Networks
	11.4 Result and Discussion
		11.4.1 Findings
	11.5 Conclusion and Future Work
	References
Chapter 12: Automatic Brain Tumor Detection Using Machine Learning and Mixed Supervision
	12.1 Introduction
	12.2 Preliminary Discussion
		12.2.1 Why Do We Choose MRI for Detecting Brain Tumors
		12.2.2 Methods
			12.2.2.1 Manual Segmentation
			12.2.2.2 Semi-Automatic Segmentation
			12.2.2.3 Fully Automatic Segmentation
		12.2.3 Problem Statement
		12.2.4 Image Segmentation Techniques
			12.2.4.1 Threshold Feature-Based Segmentation
			12.2.4.2 Region-Based Segmentation
			12.2.4.3 Feature-Based Clustering
			12.2.4.4 Edge-Based Segmentation
	12.3 Methodology
		12.3.1 Preprocessing
		12.3.2 Enhancement
		12.3.3 Skull Stripping
		12.3.4 Feature Extraction
		12.3.5 Tumor Classification Using KNN
	12.4 Results
	12.5 Conclusion
	References
Chapter 13: Architecture for Multisensor Fusion and Integration for Diabetes Monitoring
	13.1 Introduction to Wireless Sensor Network
		13.1.1 Architecture
		13.1.2 Characteristics
	13.2 Wireless Sensor Network in Health Care
		13.2.1 Open Problems
	13.3 Glucose Monitoring
		13.3.1 Requirement
		13.3.2 Existing Architecture
	13.4 Error Correction and Prediction
	13.5 Results and Discussion
	13.6 Scope for Future Work
	References
Index