Artificial Intelligence, Internet of Things (IoT) and Smart Materials for Energy Applications (Smart Engineering Systems: Design and Applications)

Cover
Half Title
Series Page
Title Page
Copyright Page
Table of Contents
Preface
Editors
Contributors
Chapter 1 A Review of Automated Sleep Apnea Detection Using Deep Neural Network
	1.1 Introduction
	1.2 Materials and Methods
	1.3 Signal and Dataset
		1.3.1 Based on Pulse Oxygen Saturation Signal
		1.3.2 Based on Electrocardiogram (ECG)
		1.3.3 Based on Airflow (AF)
		1.3.4 Based on Sound
	1.4 Data Preprocessing
		1.4.1 Raw Signal
		1.4.2 Filtered Signal
		1.4.3 Signal Normalization
		1.4.4 Spectrogram
		1.4.5 Feature Analyses
	1.5 Performance Metrics
	1.6 Classifiers
		1.6.1 CNN
			1.6.1.1 D1CNN
			1.6.1.2 D2CNN
		1.6.2 RNN
			1.6.2.1 LSTM
			1.6.2.2 GRU
		1.6.3 Deep Vanilla Neural Network (DVNN)
			1.6.3.1 MHLNN
			1.6.3.2 SSAE
			1.6.3.3 DBN
		1.6.4 Combined DNN Approach
	1.7 Discussion
	1.8 Conclusion
	References
Chapter 2 Optimization of Tool Wear Rate Using Artificial
Intelligence–Based TLBO and Cuckoo Search Approach
	2.1 Introduction
	2.2 Artificial Intelligence
	2.3 Electric Discharge Machining (EDM)
	2.4 Analysis of Variance (ANOVA)
	2.5 Optimization
		2.5.1 Cuckoo Search Algorithm
		2.5.2 Teaching–Learning-Based Optimization
	2.6 Experimental Details and Results
	2.7 Conclusion
	References
Chapter 3 Lung Tumor Segmentation Using a 3D Densely Connected Convolutional Neural Network
	3.1 Introduction
	3.2 Literature Survey
		3.2.1 Traditional vs Deep Learning Approaches
		3.2.2 Lung Nodule Detection
		3.2.3 Lung Tumor Detection
	3.3 Related Work
		3.3.1 U-Net Segmentation Model
		3.3.2 DenseNet Model
	3.4 Proposed Methodology
		3.4.1 Dataset
			3.4.1.1 Dataset Description
			3.4.1.2 Data Preprocessing
		3.4.2 Segmentation Model
			3.4.2.1 Model Architecture
			3.4.2.2 Model Training
	3.5 Experimental Results
		3.5.1 Evaluation Criteria
		3.5.2 Results
	3.6 Discussion
	3.7 Conclusion and Future Scope
	Acknowledgment
	References
Chapter 4 Day-Ahead Solar Power Forecasting Using Artificial Neural
Network with Outlier Detection
	4.1 Introduction
	4.2 Literature Review
	4.3 Electrical Characteristics of a PV Module
		4.3.1 Correlation of Temperature and Irradiance to the Output Power of a PV Module
		4.3.2 Variation of Current and Voltage with Irradiance and Temperature
		4.3.3 Studied PV System and Data
		4.3.4 Data Pre-Processing
	4.4 Overview to ANN
	4.5 Methodology
		4.5.1 Interpolation for Imputation of Missing Values
		4.5.2 Exponential Smoothing for Imputation of Missing Values
		4.5.3 Design of ANN Structure
		4.5.4 Evaluation of the Forecasting Model
	4.6 Results and Discussion
	4.7 Conclusion
	Acknowledgement
	References
Chapter 5 Fuzzy-Inspired Three-Dimensional DWT and GLCM Framework for Pixel Characterization of Hyperspectral Images
	5.1 Introduction
	5.2 Experimentation
		5.2.1 3D DWT and 3D GLCM-Based Approach for Hyperspectral
Image Classification
			5.2.1.1 3D DWT Decomposition
			5.2.1.2 3D GLCM Feature Extraction
		5.2.2 Support Vector Machine (SVM)
			5.2.2.1 SVM for Nonlinear and Nonseparable Classes
		5.2.3 3D DWT and 3D GLCM-Based Hyperspectral Image
Classification Method
		5.2.4 Proposed Fuzzy-Inspired Image Classification Method
			5.2.4.1 Mixed Pixel Identification
			5.2.4.2 Fuzzicatfiion
			5.2.4.3 Membership Function
			5.2.4.4 Reclassification
			5.2.4.5 Fuzzy-Inspired Process
	5.3 Results and Discussion
		5.3.1 Results Obtained for Simple 3D DWT and GLCM Method
		5.3.2 Results Obtained for Fuzzy-Inspired 3D DWT and 3D GLCM Method
	5.4 Conclusion
	5.5 Scope
	References
Chapter 6 Painless Machine Learning Approach to Estimate Blood Glucose Level with Non-Invasive Devices
	6.1 Introduction
	6.2 Types of Glucose Monitoring Techniques
		6.2.1 Invasive Method for Glucose Measurement
		6.2.2 Non-Invasive Method for Glucose Measurement
	6.3 Painless Non-Invasive Glucometer Using Machine Learning Approach
	6.4 Results and Discussion
		6.4.1 Channel Estimation for Finding Glucose Level
		6.4.2 Model Validation
		6.4.3 Fast-Tree Regression Machine Learning Technique
	6.5 Conclusion
	References
Chapter 7 Artificial Intelligence and Machine Learning in
Biomedical Applications
	7.1 Introduction
		7.1.1 Innovations of Technology
	7.2 Challenges and Issues
		7.2.1 Data Collection
		7.2.2 Poor Quality of Data
		7.2.3 Interpretability
		7.2.4 Domain Complexity
		7.2.5 Feature Enrichment
		7.2.6 Temporal Modelling
		7.2.7 Balancing Model Accuracy and Interpretability
		7.2.8 Legal Issues
	7.3 Artificial Intelligence and Machine Learning Applications in Biomedical
		7.3.1 Precision Medicine
		7.3.2 Genetics-Based Solutions
		7.3.3 Drug Improvement and Discovery
		7.3.4 Prediction of Protein Structure
		7.3.5 Medical Image Recognition
		7.3.6 Health Monitoring and Wearables
		7.3.7 Minimally Invasive Surgery (MIS)
		7.3.8 Monitoring by Biosensor
	7.4 Success Elements for AI in Biomedical Engineering
		7.4.1 Assessment of Condition
		7.4.2 Managing Complications
		7.4.3 Patient-Care Assistance
		7.4.4 Medical Research
	7.5 Conclusion
	References
Chapter 8 The Use of Artificial Intelligence-Based Models for
Biomedical Application
	8.1 Introduction
	8.2 AI Methods and Applications
		8.2.1 Machine Learning (ML)
		8.2.2 Natural Language Processing (NLP)
		8.2.3 Neural Network (NN)
		8.2.4 Deep Learning (DL)
		8.2.5 Machine Vision/Computer Vision
	8.3 Robotic-Assisted Surgical Systems (RASS) and Computer-Assisted Surgery (CAS)
	8.4 Virtual Nurse Assistants (VNAs) for Healthcare
		8.4.1 Medication Management and Medication Error Reduction (MMMER)
		8.4.2 Improving Medical Safety
		8.4.3 Monitoring Medication Non-Adherence
		8.4.4 Clinical Trial Participation (CTP)
	8.5 Preliminary Diagnosis and Prediction (PDP)
		8.5.1 Diabetes Prediction
		8.5.2 Cancer Prediction
		8.5.3 Tuberculosis Diagnosis
		8.5.4 Psychiatric Diagnosis
	8.6 Medical Imaging and Image Diagnostics (MID)
		8.6.1 Medical Imaging with Deep Learning
		8.6.2 Image Diagnosis for Oncology
		8.6.3 Optical Coherence Tomography (OCT) Diagnosis
	8.7 Patient Health Monitoring (PHM)
		8.7.1 Heart Failure Monitoring
		8.7.2 Health Monitoring After Surgery
		8.7.3 Health Monitoring for Oncology Patients
	8.8 Additional Quantitative Methods Used in Biomedical Application
		8.8.1 Neural Network-Based ECG Anomaly Detection
		8.8.2 A Fuzzy Neural Network Model for Post-surgery Risk Prediction
		8.8.3 Heart Stroke Prediction with GUI Using Artificial Intelligence
	8.9 Key Elements for Successful Implementation of AI-Based Services in Healthcare
	8.10 Opportunities and Challenges
	8.11 Conclusion and Future Work
	Acknowledgment
	References
Chapter 9 Role of Artificial Intelligence in Transforming Agriculture
	9.1 Introduction
	9.2 Role of AI in Determining the Nature of the Soil and Recommending Suitable Plants
	9.3 Role of AI in Estimating the Water Requirement for the Crops and the Determining the Availability of Water in Water Bodies and the Expected Amount of Rain
	9.4 Role of IoT in Retrieving the Mineral Contents in the Soil Regularly and Alerting the Farmers to Add Suitable Minerals Whenever Required
	9.5 Use of IoT and CNN in Protecting Crops from Being Affected by Animals, Birds and Pests
	9.6 Role of IoT and Image Processing in Detecting the Diseases in Plants and Alerting the Farmers to Apply Pesticides to Save the Affected Plants and to Avoid Further Spreading of the Disease
	9.7 ML in Forecasting the Cost of the Agricultural Products and Recommending Suitable Season for Planting and Harvesting to Make Better Profits
		9.7.1 Crop Harvesting Using AI
		9.7.2 Agricultural Product Grading Using AI
	9.8 Conclusion
	References
Chapter 10 Internet of Things (IoT) and Artificial Intelligence for Smart
Communications
	10.1 Introduction
	10.2 Application Scenarios of IoT and AI
	10.3 Related Work
	10.4 IoT Road Map and Service Model
	10.5 IoT and AI Enabling Technologies
	10.6 Proposals for Enhancement of AI-IoT with Challenges
	10.7 Conclusions
	References
Chapter 11 Cyber-Security in the Internet of Things
	11.1 Introduction
		11.1.1 Cyber Threats in IoT
	11.2 Security Issues in IoT
		11.2.1 IoT Generic Architecture
		11.2.2 Reasons for Cyber-Attacks in IoT Network
	11.3 Potential Cyber-Attacks in IoT
	11.4 Need of Cyber-Security in IoT
		11.4.1 Need of Standardization
		11.4.2 Data Issues
	11.5 Mitigation Techniques
		11.5.1 Strong Authentication Solutions
		11.5.2 Access Control Mechanism
		11.5.3 Intrusion Detection System (IDS)
		11.5.4 Software-Defined Networking (SDN)
		11.5.5 Light-Weight Cryptography
	11.6 Conclusion
	References
Chapter 12 Smart Materials for Electrochemical Water Oxidation
	12.1 Introduction (Is There Any Alternative to Fossil Fuels?)
	12.2 Electrochemical Water Splitting
	12.3 Mechanism of Oxygen Evolution Reaction (OER) and Evaluation Parameters
		12.3.1 Overpotential (η)
		12.3.2 Tafel Slope (b)
		12.3.3 Electrochemical Active Surface Area (ECSA)
	12.4 Electrocatalysts for OER
		12.4.1 Metal Oxides
		12.4.2 Metal Sulfides
		12.4.3 Metal Phosphides
		12.4.4 Layered Double Hydroxide (LDH)
	12.5 Summary and Future Perspective
	Acknowledgments
	References
Chapter 13 Innovative Approach for Real-Time P–V Curve Identification:
Design-to-Application
	13.1 Introduction
	13.2 PV Module Characteristics and MPPT
	13.3 Experimental Prototype and System Parameters
		13.3.1 Boost Converter for MPPT
		13.3.2 Design of 40 W Boost Converter for MPPT
		13.3.3 Control Circuit Implementation
	13.4 Results and Discussion
		13.4.1 Boost Converter in an Open Loop
		13.4.2 Boost Converter in a Closed Loop
		13.4.3 Boost Converter for Capturing I–V/P–V Characteristics
		13.4.4 Boost Converter for MPPT
	13.5 Conclusions
	References
Chapter 14 Superhydrophobic Coatings of Silica NPs on Cover Glass of Solar Cells for Self-Cleaning Applications
	14.1 Introduction
	14.2 Experimental Section
		14.2.1 Materials
		14.2.2 Preparation of Superhydrophobic
		14.2.3 Characterization
	14.3 Result and Discussion
		14.3.1 Surface Structure and Wettability
		14.3.2 Durability of Superhydrophobic Coating
		14.3.3 Self-Cleaning Property
	14.4 Conclusion
	Highlights
	Acknowledgments
	References
Chapter 15 Carbonaceous Composites of Rare Earth Metal Chalcogenides: Synthesis, Properties and Supercapacitive Applications
	15.1 Introduction
	15.2 Principle and Mechanism of Supercapacitor
		15.2.1 Electric Double-Layer Capacitance (EDLC)
		15.2.2 Pseudocapacitor
	15.3 Factors Affecting Supercapacitor Performance
		15.3.1 Chemical Composition of Material
		15.3.2 Electrolyte
		15.3.3 Temperature
		15.3.4 Crystal Structure and Crystallinity
		15.3.5 Morphology
		15.3.6 Specific Surface Area and Pore Structure
		15.3.7 Thickness of the Electrode
	15.4 Rare Earth Metal Chalcogenides–Based Carbonaceous Composites
		15.4.1 Cerium Chalcogenides Composites
		15.4.2 Lanthanum Chalcogenides Composites
		15.4.3 Samarium Chalcogenide Composites
		15.4.4 Europium Chalcogenides Composites
		15.4.5 Dysprosium Chalcogenides Composites
	15.5 Summary and Conclusions
	Acknowledgement
	References
Chapter 16 Low-Stress Abrasion Response of Heat-Treated LM25–SiCp Composite
	16.1 Introduction
	16.2 Experiments
		16.2.1 Synthesis of the Materials
		16.2.2 Microstructure Analysis
		16.2.3 Evaluation of Densities and Hardnesses
		16.2.4 Low-Stress Abrasion
	16.3 Result and Discussion
		16.3.1 Microstructure Characterisation
		16.3.2 Density and Hardness Analysis
		16.3.3 Low-Stress Abrasion
		16.3.4 Abrasive Worn Surface
	16.4 Conclusions
	References
Chapter 17 Post-Annealing Influence on Structural, Surface and Optical Properties of Cu[sub(3)]BiS[sub(3)] Thin Films for Photovoltaic Solar Cells
	17.1 Introduction
	17.2 Experimental Section
		17.2.1 Resources
		17.2.2 Preparation of Cu[sub(3)]BiS[sub(3)] Precursor Solution
		17.2.3 Cu[sub(3)]BiS[sub(3)] Thin-Film Deposition
		17.2.4 Cu[sub(3)]BiS[sub(3)] Thin-Film Characterization
	17.3 Results and Discussion
		17.3.1 Structural Analysis
		17.3.2 Raman Spectroscopy
		17.3.3 Scanning Electron Microscopy
		17.3.4 Water Contact Angle Studies
		17.3.5 Optical Studies
	17.4 Conclusions
	Acknowledgements
	References
Chapter 18 Self-Cleaning Antireflection Coatings on Glass for Solar
Energy Applications
	18.1 Introduction
		18.1.1 Theoretical Aspects of Antireflection and Non-Wettability
			18.1.1.1 Antireflection
			18.1.1.2 Non-Wettability
		18.1.2 Fabrication Technique of Hydrophobic Antireflection Coatings
			18.1.2.1 Spin-Coating Technique
			18.1.2.2 Dip-Coating Technique
		18.1.3 Recent Progress towards the Self-Cleaning Antireflection Coatings
	18.2 Fabrication of Hydrophobic Antireflection Coating
		18.2.1 Materials
		18.2.2 Preparation of Sol and Deposition of Coating
	18.3 Results and Discussion
		18.3.1 Optical Performance of the Coating
		18.3.2 Structural Determination Using FTIR Spectroscopy
		18.3.3 Wetting Property of the Coating
	18.4 Conclusion
	References
Index