Smart Healthcare Analytics in IoT Enabled Environment (Intelligent Systems Reference Library, 178)

✍ Scribed by Prasant Kumar Pattnaik (editor), Suneeta Mohanty (editor), Satarupa Mohanty (editor)

• Publisher: Springer
• Year: 2020
• Tongue: English
• Leaves: 256
• Category: Library

✦ Synopsis

This book addresses various aspects of how smart healthcare can be used to detect and analyze diseases, the underlying methodologies, and related security concerns. Healthcare is a multidisciplinary field that involves a range of factors like the financial system, social factors, health technologies, and organizational structures that affect the healthcare provided to individuals, families, institutions, organizations, and populations. The goals of healthcare services include patient safety, timeliness, effectiveness, efficiency, and equity. Smart healthcare consists of m-health, e-health, electronic resource management, smart and intelligent home services, and medical devices. The Internet of Things (IoT) is a system comprising real-world things that interact and communicate with each other via networking technologies. The wide range of potential applications of IoT includes healthcare services. IoT-enabled healthcare technologies are suitable for remote health monitoring, including rehabilitation, assisted ambient living, etc. In turn, healthcare analytics can be applied to the data gathered from different areas to improve healthcare at minimum expense.

✦ Table of Contents

Preface
About This Book
Key Features
Contents
About the Editors
1 Smart Healthcare Analytics: An Overview
1.1 Introduction
1.1.1 Internet of Things (IoT)
1.1.2 IoT for Healthcare
1.2 Benefits of Smart Healthcare
1.2.1 Real-Time Reporting and Monitoring
1.2.2 Affordability and End-to-End Connectivity
1.2.3 Data Assortment and Analysis
1.2.4 Remote Medical Assistance
1.3 Challenges of Smart Healthcare
1.3.1 Data Security and Privacy Threats
1.3.2 Multiple Devices and Protocols Integration
1.3.3 Data Overload and Accuracy
1.3.4 Internet Disruptions
1.4 Applications of Smart Healthcare
1.4.1 Glucose-Level Monitoring
1.4.2 Electrocardiogram (ECG) Monitoring
1.4.3 Blood Pressure Monitoring
1.4.4 Wearable Devices
1.5 Conclusion
References
2 Mobile Communications and Computing: A Broad Review with a Focus on Smart Healthcare
2.1 Introduction
2.2 Mobile Communications
2.2.1 Common Mobile Wireless Networks
2.3 Research Areas in Mobile Communications
2.3.1 Network-Specific Research Directions
2.3.2 Generic Research Directions
2.4 Mobile Computing
2.5 Research Areas in Mobile Computing
2.6 IoT in Smart Healthcare
2.6.1 IoT-Based Healthcare Applications
2.6.2 Representative Research Projects on IoT-Based Healthcare
2.6.3 IoT in Healthcare: Open Research Issues
2.7 Conclusion
References
3 A State of the Art: Future Possibility of 5G with IoT and Other Challenges
3.1 Introduction
3.2 Fifth Generation (5G)
3.3 10 Things that Have 5G Networks Than 4G
3.4 5G NR (New Radio) and How It Works
3.5 Spectrum in 5G
3.6 Direct Device-to-Device (D2D) Communication
3.7 Nodes and Antenna Transmission
3.8 Application Scenario
3.9 Requirements for 5G Mobile Communications
3.10 5G Security and Challenges
3.11 Promising Technologies for the 5G
3.12 Geographical Condensation of Transmitting Stations and Networks
3.13 Multiple Dense Antennas
3.14 Millimeter Waves
3.15 Optical Communication
3.16 Comparison of 1G to 5G Mobile Technology
3.17 Reasons Why You Don’t yet Have 5G
3.17.1 5G Networks Are Limited in Range
3.17.2 Some Cities Aren’t on Board
3.17.3 Testing Is Crucial
3.17.4 Spectrum Needs to Be Purchased
3.17.5 It’s Expensive to Roll Out 5G
3.18 IoT Healthcare System Architecture
3.18.1 IoT Challenges in Healthcare
3.19 Conclusion
References
4 Design Model of Smart “Anganwadi Center” for Health Monitoring
4.1 Introduction
4.2 Related Work
4.3 IoT Platform
4.4 Proposed Work
4.4.1 Working Principle
4.4.2 Hardware Required
4.5 Simulation and Result
4.6 Conclusion
References
5 Secured Smart Hospital Cabin Door Knocker Using Internet of Things (IoT)
5.1 Introduction
5.2 Related Work
5.3 Proposed Model
5.4 Module Description
5.4.1 User Hardware Module
5.4.2 Processing Module
5.5 Implementation Technologies
5.5.1 Face Detection and Face Recognition
5.5.2 Base 64 Algorithm
5.6 System Implementation
5.7 Results and Discussion
5.7.1 Computational Time
5.7.2 Results
5.8 Conclusion and Future Work
References
6 Effective Fusion Technique Using FCM Based Segmentation Approach to Analyze Alzheimer’s Disease
6.1 Introduction
6.2 Review Works
6.3 Methodology
6.3.1 Fuzzy Logic Approach
6.3.2 Expert Knowledge
6.3.3 Fusion Rule Using PCA Based Weighted Averaging
6.4 Experimental Results
6.5 Conclusion
References
7 Application of Machine Learning in Various Fields of Medical Science
7.1 Introduction
7.1.1 KNN (K Nearest Neighbor Classifier)
7.1.2 Genetic Algorithm
7.1.3 Regularized Logistic Regression
7.1.4 Semi-supervised Learning
7.1.5 Principal Components Analysis
7.1.6 Support Vector Machine
7.1.7 Random Forest Classifier
7.2 Application of Machine Learning in Heart Diseases
7.2.1 Case Study-1 to Classify Heart Diseases Using a Machine Learning Approach
7.2.2 Case Study-2 to Predict Cardiac Arrest in Critically Ill Patients from Machine Learning Score Achieved from the Variability of Heart Rate
7.3 Application of Machine Learning Algorithms in Diagnosing Diseases of Brain
7.3.1 Case Study 1: Alzheimer’s Disease
7.3.2 Case Study 2: Detecting Parkinson’s Disease from Progressive Supranuclear Palsy
7.4 A Brief Approach of Medical Sciences in Other Fields
7.5 Conclusion
References
8 Removal of High-Density Impulsive Noise in Giemsa Stained Blood Smear Image Using Probabilistic Decision Based Average Trimmed Filter
8.1 Introduction
8.2 Proposed Algorithm
8.2.1 Proposed Average Trimmed Filter
8.2.2 Proposed Patch Else Average Trimmed Filter
8.2.3 Proposed Probabilistic Decision Based Average Trimmed Filter
8.3 Simulation Results and Discussion
8.4 Conclusion
References
9 Feature Selection: Role in Designing Smart Healthcare Models
9.1 Introduction
9.1.1 Necessity of Feature Selection
9.2 Classes of Feature Selection
9.2.1 Brief of Filter Methods
9.2.2 Wrapper Methods
9.2.3 Filter Methods Versus Wrapper Methods
9.2.4 Embedded Methods
9.3 Feature Transformation
9.3.1 Scaling
9.3.2 Linear Discriminant Analysis
9.3.3 Principal Component Analysis
9.3.4 SVM
9.3.5 Random Projection
9.3.6 Neural Networks
9.4 Related Works
9.5 Our Experiment
9.5.1 Workflow Diagram
9.5.2 Data Set Description
9.5.3 Results
9.6 Conclusion and Future Work
References
10 Deep Learning-Based Scene Image Detection and Segmentation with Speech Synthesis in Real Time
10.1 Introduction
10.2 Related Work
10.3 The Model
10.4 Experiment
10.5 Results
10.6 Conclusion
References
11 Study of Different Filter Bank Approaches in Motor-Imagery EEG Signal Classification
11.1 Introduction
11.2 Background
11.2.1 Common Spatial Pattern
11.2.2 Filter Bank
11.2.3 Mixture Bagging Classifier
11.2.4 Differential Evolution
11.3 Proposed Approach
11.3.1 Temporal Sliding Window
11.3.2 Proposed DE-based Error Minimization
11.4 System Preparation
11.4.1 Dataset
11.4.2 Resources
11.5 Experimental Discussion
11.6 Conclusion
References
12 A Stacked Denoising Autoencoder Compression Sampling Method for Compressing Microscopic Images
12.1 Introduction
12.2 Review Work
12.3 Stacked Denoising Autoencoder Compression Sampling (SDA-CS) Approach
12.4 Experiments and Results
12.4.1 Datasets
12.4.2 Evaluation Metrics
12.5 Discussion
12.6 Conclusion
References
13 IoT in Healthcare: A Big Data Perspective
13.1 Introduction
13.2 Big Data Framework
13.3 Methodology
13.3.1 Random Forest Technique
13.4 Experimental Setup and Dataset Description
13.4.1 EEG DataSet
13.5 Results and Analysis
13.6 Conclusion
References
14 Stimuli Effect of the Human Brain Using EEG SPM Dataset
14.1 Introduction
14.2 Review of Related Works
14.3 Relation Between Electroencephalography (EEG) and Magnetoencephalography (MEG)
14.4 Applications of EEG
14.4.1 Depth of Anaesthesia
14.4.2 Biometric Systems
14.4.3 Physically Challenged
14.4.4 Epilepsy
14.4.5 Alzheimer
14.4.6 Brain Death
14.4.7 Coma
14.5 Challenges
14.6 Visual Stimuli Analysis
14.6.1 EEG Data Preprocessing
14.6.2 Visualising the Data
14.6.3 Artifact Removal
14.6.4 Locating the Response Source
14.7 Conclusion
References
15 Securing the Internet of Things: Current and Future State of the Art
15.1 Introduction
15.2 Concepts and Basic Characteristics of Internet of Things
15.3 IoT Architecture
15.4 Security Features and Security Requirements of an IoT System
15.5 Security Threats in an IoT System: Current and Future Scenario
15.6 Security of IoT Enabled Healthcare System
15.7 Security Mechanisms in an IoT System: Current State of the Art
15.8 Current Research Trends Related to IoT Security
15.9 Security Issues and Challenges
15.10 Conclusion
References