Biomedical Signal Processing for Healthcare Applications

Cover
Half Title
Series Page
Title Page
Copyright Page
Table of Contents
Preface
Acknowledgements
Editors
Contributors
Chapter 1 Automatic Sleep EEG Classification with Ensemble Learning Using Graph Modularity
	1.1 Introduction
	1.2 Related Work
	1.3 Electroencephalography (EEG)
		1.3.1 Waves in EEG
		1.3.2 Types of Sleep
			1.3.2.1 Sleep Cycle Stages
			1.3.2.2 Physiological Changes between NREM and REM
			1.3.2.3 Sleep Period over Life Span
			1.3.2.4 Disorders in NREM and REM Sleep
	1.4 The EEG Dataset
		1.4.1 ISRUC-Sleep Database
		1.4.2 Sleep-EDF Database
	1.5 Graph Modularity
	1.6 Ensemble Techniques
	1.7 Methodology
		1.7.1 Transforming the Statistical Features to Undirected Weighted Graph
		1.7.2 Transformation of Statistical Features to Undirected Weighted Graph
	1.8 Experimental Results
	1.9 Conclusion
	References
Chapter 2 Recognition of Distress Phase Situation in Human Emotion EEG Physiological Signals
	2.1 Introduction
	2.2 Literature Review
	2.3 Materials and Methods
		2.3.1 Acquisition of Dataset
		2.3.2 Emotion Representation Modeling
		2.3.3 Preprocessing and Transformation of the Physiological Signals
		2.3.4 Feature Extraction Techniques
			2.3.4.1 Histogram of Oriented Gradient
			2.3.4.2 Local Binary Pattern
			2.3.4.3 Histogram of Images
	2.4 Classification Algorithm for Emotion Recognition
	2.5 Experimental Models
	2.6 Results and Discussion
	2.7 Conclusion
	References
Chapter 3 Analysis and Classification of Heart Abnormalities
	3.1 Introduction and Background Information
	3.2 Anatomy and Physiology, Biomechanics and Electrophysiology of the Heart
	3.3 Introduction of ECG Signals
	3.4 Various Heart-Related Abnormalities
	3.5 Heart Abnormalities in Women
	3.6 Summary
	References
Chapter 4 Diagnosis of Parkinson’s Disease Using Deep Learning Approaches: A Review
	4.1 Introduction
	4.2 Objective of the Review
	4.3 Literature Review
	4.4 Deep Learning Framework
		4.4.1 Data Acquisition
		4.4.2 Preprocessing
		4.4.3 Feature Selection
		4.4.4 Classification
			4.4.4.1 Convolution Neural Network (CNN)
			4.4.4.2 Deep Belief Network (DBN)
			4.4.4.3 Deep Neural Network (DNN)
	4.5 Challenges and Opportunities
	4.6 Conclusion
	References
Chapter 5 Classifying Phonological Categories and Imagined Words from EEG Signal
	5.1 Introduction
	5.2 Methodology
		5.2.1 Dataset
		5.2.2 Wavelet Decomposition
		5.2.3 Empirical Mode Decomposition
		5.2.4 Channel Selection
		5.2.5 Feature Extraction
		5.2.6 Classifiers
		5.2.7 Cross Validation
	5.3 Result
		5.3.1 Binary Classification Results
		5.3.2 Multiclass Classification Results
	5.4 Discussion and Conclusion
	References
Chapter 6 Blood Pressure Monitoring Using Photoplethysmogram and Electrocardiogram Signals
	6.1 Introduction
	6.2 Physiological Models
		6.2.1 BP Estimation Based on Pulse Transit Time
	6.3 Pulse Arrival Time Instead of Pulse Transit Time
		6.3.1 Performance Comparison: PAT vs. PTT
	6.4 BP Estimation Approaches Based on PPG and ECG
		6.4.1 Estimation Based on Manual Features
		6.4.2 End-to-End Estimation Based on LSTM Networks
	6.5 Conclusion
	References
Chapter 7 Investigation of the Efficacy of Acupuncture Using Electromyographic Signals
	7.1 Introduction
	7.2 Electromyography Sensor
		7.2.1 Materials and Components
		7.2.2 EMG Circuit
		7.2.3 Signal and Data Acquisition
	7.3 Test Procedures
	7.4 Results and Discussion
	7.5 Hypothesis
	7.6 Conclusion
	Appendix: Code Listing for EMG Sensor to Extract Data
	References
Chapter 8 Appliance Control System for Physically Challenged and Elderly Persons through Hand Gesture-Based Sign Language
	8.1 Introduction
		8.1.1 Disability – A Public Health Issue
		8.1.2 Disability Statistics in India
		8.1.3 Barriers to Healthcare
	8.2 Literature Survey
	8.3 Preferable Techniques
		8.3.1 Device-Based Techniques
		8.3.2 Visual-Based Techniques
		8.3.3 Device-versus Visual-Based Techniques
	8.4 Existing System
	8.5 Proposed Methodology
		8.5.1 Data Glove-Based System
			8.5.1.1 Objective
			8.5.1.2 Theme
			8.5.1.3 Summary
			8.5.1.4 System Description
			8.5.1.5 Learning Mode
			8.5.1.6 Operational Mode
			8.5.1.7 System Architecture
			8.5.1.8 Raspberry Pi
			8.5.1.9 Data Glove
			8.5.1.10 Flex Sensor
			8.5.1.11 Accelerometer Sensor
			8.5.1.12 Features
			8.5.1.13 General Description
			8.5.1.14 System Flow
			8.5.1.15 System Functionality
		8.5.2 Camera-Based System
			8.5.2.1 Phase I – Capturing Input Hand Gesture
			8.5.2.2 Phase II – Recognition of Input Hand Gesture
			8.5.2.3 Phase III – Appliance Control
	8.6 Conclusion
	8.7 Future Scope
	8.8 Applications
	References
Chapter 9 Computer-Aided Drug Designing – Modality of Diagnostic System
	9.1 Introduction
		9.1.1 Disease Selection
		9.1.2 Target Identification and Validation
		9.1.3 Lead Optimization
		9.1.4 Preclinical Trials
		9.1.5 Clinical trails
	9.2 Working of Computer-Aided Drug Designing (CADD)
	9.3 Factors Affecting Drug-Designing Process
	9.4 Approaches of Computer-Aided Drug Designing (CADD)
		9.4.1 Structure-Based Drug Design (SBDD)
		9.4.2 Homology Modeling
			9.4.2.1 Template Recognition
			9.4.2.2 Target Alignment
			9.4.2.3 Construction of Target Molecule
			9.4.2.4 Optimization
			9.4.2.5 Model Optimization
			9.4.2.6 Evaluation
		9.4.3 Ligand-Based Drug Design
	9.5 Virtual Screening
		9.5.1 Structure-Based Virtual Screening (SBVS)
		9.5.2 Ligand Based Virtual Screening (LBVS)
	9.6 Molecular Docking
	9.7 Challenges in Computer-Aided Drug Design
	9.8 Molecular Property Diagnostic Suite (MPDS)
		9.8.1 Salient Features of the MPDS Tool for Tuberculosis
	9.9 Structure of MPDSTB
		9.9.1 Data Library
		9.9.2 Data Processing
		9.9.3 Data Analysis
		9.9.4 Screening
		9.9.5 Visualization
	9.10 Application of Computer-Aided Drug Designing
	9.11 Conclusion
	References
Chapter 10 Diagnosing Chest-Related Abnormalities Using Medical Image Processing through Convolutional Neural Network
	10.1 Introduction
	10.2 Medical Image Processing
	10.3 Applications
		10.3.1 Chest X-Ray
		10.3.2 Endoscopy
		10.3.3 Magnetic Resonance Imaging MRI
		10.3.4 Microscope
	10.4 Method
		10.4.1 Neuron
		10.4.2 Neural Network Model
		10.4.3 Deep Neural Network
		10.4.4 Framework
		10.4.5 Supervised Learning
		10.4.6 Convolutional Neural Network
	10.5 Methodology
		10.5.1 Dataset Description
		10.5.2 Abnormalities
		10.5.3 Pre-processing
		10.5.4 Modeling
		10.5.5 Evaluation
		10.5.6 Results
	10.6 Conclusion
	References
Chapter 11 Recent Trends in Healthcare System for Diagnosis of Three Diseases Using Health Informatics
	11.1 Introduction
		11.1.1 Machine Learning and Healthcare
		11.1.2 Objective of This Study
	11.2 Literature Survey
	11.3 Materials and Methods
		11.3.1 ML Algorithms Description
			11.3.1.1 Support Vector Machine (SVM)
			11.3.1.2 K-Nearest Neighbor (k-NN)
			11.3.1.3 Multilayer Perceptron (MLP)
			11.3.1.4 Naïve Bayes (NB)
			11.3.1.5 Decision Tree (DT)
			11.3.1.6 Ensemble Techniques
		11.3.2 Evaluating ML Model’s Efficiency
	11.4 Proposed System for Disease Classification Task
		11.4.1 Disease Classification for Chronic Kidney Disease Prediction
			11.4.1.1 Dataset Used and Preprocessing
			11.4.1.2 Detailed Description of Classifiers
		11.4.2 Disease Classification for Heart Disease
			11.4.2.1 Dataset Used
		11.4.3 Disease Classification System for Liver Disease
			11.4.3.1 Dataset Used and Preprocessing
	11.5 Experimental Results
		11.5.1 Analysis for CKD Detection
		11.5.2 Analysis for CVD Detection
		11.5.3 Analysis for Liver Disease Detection
	11.6 Conclusions
	References
Chapter 12 Nursing Care System Based on Internet of Medical Things (IoMT) through Integrating Non-Invasive Blood Sugar (BS) and Blood Pressure (BP) Combined Monitoring
	12.1 Introduction
	12.2 Review of Existing Literature
		12.2.1 The Conventional Way of Glucose Monitoring
		12.2.2 Minimally Invasive Glucose Monitoring
		12.2.3 Noninvasive Way of Glucose Monitoring
	12.3 Importance of Continuous Monitoring Blood Sugar (BS) and Blood Pressure (BP)
	12.4 Measurement of Blood Pressure (BP) and Blood Sugar (BS)
		12.4.1 Mean of the Blood Pressure Measurement (MBP)
	12.5 Methodology Detailing Stepwise Activities and Subactivities
		12.5.1 Algorithm for Clinical Care System
		12.5.2 Flowchart to Show Relationship between BS and BP
	12.6 Architecture of the Proposed Design
		12.6.1 Device-Level Architecture in Application of Internet of Medical Things (IoMT)
		12.6.2 Intelligent Rule-Based System
		12.6.3 Cloud-Based Architecture of the Proposed Device
		12.6.4 Output-Based Design of Proposed Approach
	12.7 Output-Based Sample Standard Diet Analysis
	12.8 Likely Impacts of the Proposed Device
	12.9 Parameters Effecting the Research
	12.10 Conclusion
	Acknowledgements
	References
Chapter 13 Eye Disease Detection from Retinal Fundus Image Using CNN
	13.1 Introduction
		13.1.1 Retinal Fundus Images
		13.1.2 Machine Learning
		13.1.3 Deep Learning
		13.1.4 Convolutional Neural Network
	13.2 Dataset Description
	13.3 Experimental Results and Discussions
		13.3.1 Data Augmentation
	13.4 Conclusion
	Acknowledgments
	References
Index