Modeling and Optimization of Signals Using Machine Learning Techniques

Chapter 1 Land Use and Land Cover Mapping of Remotely Sensed Data Using Fuzzy Set Theory-Related Algorithm
	1.1 Introduction
	1.1.1 Overview on Landsat 8
	1.2 Image Classification
	1.3 Unsupervised Classification
	1.4 Supervised Classification
	1.5 Overview of Fuzzy Sets
		1.5.1 Fuzzy C-Means Clustering
		1.5.2 Algorithm of Fuzzy C-Means
	1.6 Methodology
		1.6.1 Modified Fuzzy C-Means Technique
		1.6.2 Construction of a Fuzzy Inference System
		1.6.3 K-Means Algorithm
	1.7 Results and Discussion
		1.7.1 FCM Technique Results
		1.7.2 Modified FCM Technique Results
		1.7.3 K-Means Technique Results
	1.8 Conclusion
	References
Chapter 2 Role of AI in Mortality Prediction in Intensive Care Unit Patients
	2.1 Introduction
	2.2 Background
	2.3 Objectives
	2.4 Machine Learning and Mortality Prediction
		2.4.1 Model Selection
		2.4.2 Mortality Prediction for ICU Patients
		2.4.3 Datasets Generation and Preprocessing
			2.4.3.1 A > Inclusion Criteria
			2.4.3.2 B > Exclusion Criteria
		2.4.4 Structure of Datasets
	2.5 Discussions
	2.6 Conclusion
	2.7 Future Work
	2.8 Acknowledgments
	2.9 Funding
	2.10 Competing Interest
	References
Chapter 3 A Survey on Malware Detection Using Machine Learning
	3.1 Background
	3.2 Introduction
	3.3 Literature Survey
	3.4 Discussion
	3.5 Conclusion
	References
Chapter 4 EEG Data Analysis for IQ Test Using Machine Learning Approaches: A Survey
	Introduction
	4.1 Related Work
		4.1.1 Signal Pre-Processing, Filtering, and Feature Extraction
	4.2 Equations
		4.2.1 Alternating a Diffusion Map-Based Combination of Two FCN Datasets
		4.2.2 Information Examination
		4.2.3 Gaussian Kernel Function
	4.3 Classification
	4.4 Data Set
		4.4.1 Pre-Preparing
		4.4.2 EEG Data Producer
	4.5 Information Obtained by EEG Signals
		4.5.1 System Structure
		4.5.2 Numerical Examination
		4.5.3 EEG Circumference
	4.6 Discussion
		4.6.1 Comparison Between IQ Levels With Different Methods
	4.7 Conclusion
	References
Chapter 5 Machine Learning Methods in Radio Frequency and Microwave Domain
	5.1 Introduction
	5.2 Background on Machine Learning
		5.2.1 Clustering
		5.2.2 Principal Component Analysis
		5.2.3 Naïve Bayes Algorithms
		5.2.4 Support Vector Machines
		5.2.5 Artificial Neural Networks
	5.3 ML in RF Circuit Modeling and Synthesis
	5.4 Conclusion
	References
Chapter 6 A Survey: Emotion Detection Using Facial Reorganization Using Convolutional Neural Network (CNN) and Viola–Jones Algorithm
	6.1 Introduction
		6.1.1 Purpose
		6.1.2 Process Flow
	6.2 Review of Literature
	6.3 Report on Present Investigation
		6.3.1 Analysis of the Model
			6.3.1.1 Emotion Recognition
	6.4 Algorithms
		6.4.1 CNN
		6.4.2 Advantages
		6.4.3 Disadvantages
	6.5 Viola–Jones Algorithm
		6.5.1 Training
		6.5.2 Detection
	6.6 Diagram
		6.6.1 Working Diagram for Systems
		6.6.2 The Application’s Use Case Diagram
	6.7 Results and Discussion
	6.8 Limitations and Future Scope
	6.9 Summary and Conclusion
	References
Chapter 7 Power Quality Events Classification Using Digital Signal Processing and Machine Learning Techniques
	7.1 Introduction
	7.2 Methodology for the Identification of PQ Events
	7.3 Power Quality Problems Arising in the Modern Power System
		7.3.1 Sag
		7.3.2 Swell
		7.3.3 Overvoltage
		7.3.4 Undervoltage
		7.3.5 Impulsive Transient
		7.3.6 Oscillatory Transient
		7.3.7 Harmonics
	7.4 Digital Signal Processing-Based Feature Extraction of PQ Events
		7.4.1 Wavelet Transform-Based Feature Extraction
		7.4.2 Multiresolution Analysis
		7.4.3 Future Generation and Extraction
		7.4.4 Wavelet Energy
	7.5 Feature Selection and Optimization
		7.5.1 Genetic Algorithm
	7.6 Machine Learning-Based Classification of PQ Disturbances
		7.6.1 Support Vector Machine Classifier
		7.6.2 Artificial Neural Network Classifier
			7.6.2.1 Back-Propagation Neural Network
			7.6.2.2 Probabilistic Neural Network
		7.6.3 Performance Prediction of the ML Classifiers
	7.7 Summary and Conclusion
	References
Chapter 8 Hybridization of Artificial Neural Network with Spotted Hyena Optimization (SHO) Algorithm for Heart Disease Detection
	8.1 Introduction
		8.1.1 Objective of the Work
		8.1.2 Scope of the Project
	8.2 Literature Survey
		8.2.1 Problem Identification
	8.3 Proposed Methodology
		8.3.1 Different Kinds of Machine Learning Approaches
			8.3.1.1 Supervised Learning
			8.3.1.2 Unsupervised Learning
			8.3.1.3 Semi-Supervised Learning
			8.3.1.4 Reinforcement Learning
	8.4 Artificial Neural Network
		8.4.1 ANN Classification
			8.4.1.1 Input Layer
			8.4.1.2 Hidden Layer
			8.4.1.3 Output Layer
		8.4.2 Spotted Hyena Optimization
			8.4.2.1 Searching Behavior
			8.4.2.2 Encircling Behavior
			8.4.2.3 Hunting Behavior
			8.4.2.4 Attacking Behavior
		8.4.3 SHO-Based ANN
		8.4.4 Benefits of SHO in ANN
	8.5 Software Implementation Requirements
		8.5.1 Results and Discussion
	8.6 Conclusion
	References
Chapter 9 The Role of Artificial Intelligence, Machine Learning, and Deep Learning to Combat the Socio-Economic Impact of the Global COVID-19 Pandemic
	9.1 Introduction
	9.2 Discussions on the Coronavirus
		9.2.1 Coronavirus
		9.2.2 COVID-19
		9.2.3 Origin of COVID-19 and Its Symptoms
		9.2.4 Mode of Spreading
		9.2.5 Steps Taken by the Government to Prevent the Spread of COVID-19
	9.3 Bad Impacts of the Coronavirus
		9.3.1 Social Impact
			9.3.1.1 Mental Health and Psychological Impacts Due to COVID-19
			9.3.1.2 Impact on Internet Data Consumption Due to COVID-19
			9.3.1.3 Impact on Sports and Entertainment Due to COVID-19
		9.3.2 Economic Impact Due to COVID-19
			9.3.2.1 Impact on Transportation Due to COVID-19
			9.3.2.2 Impact on the Economy Due to COVID-19
			9 3.2.3 Impact on Agriculture Due to COVID-19
	9.4 Benefits Due to the Impact of COVID-19
		9.4.1 Health Benefits
			9.4.1.1 Cleaner Air
			9.4.1.2 Limited Smoking
			9.4.1.3 Drinking Alcohol is Down for a Few
			9.4.1.4 Time for Personal Healthcare
		9.4.2 Other Benefits Due to the Lockdown
	9.5 Role of Technology to Combat the Global Pandemic COVID-19
		9.5.1 Use of Different Technologies
			9.5.1.1 Computer Vision
			9.5.1.2 Three-Dimensional Printing
			9.5.1.3 Vehicular Ad Hoc Network (VANET)
			9.5.1.4 Blockchain
			9.5.1.5 Telehealth Technology
		9.5.2 Technological Devices
			9.5.2.1 Drones
			9.5.2.2 Robots
		9.5.3 Technological Applications
			9.5.3.1 Open-Source Technology
			9.5.3.2 Mobile Apps
			9.5.3.3 Video Conferencing
	9.6 The Role of Artificial Intelligence, Machine Learning, and Deep Learning in COVID-19
		9.6.1 Symbolic Rule-Based Method
		9.6.2 Probabilistic Method
		9.6.3 Evolutionary Computation Method
		9.6.4 Machine Learning Approach
		9.6.5 Deep Learning Approach
	9.7 Related Studies
	9.8 Conclusion
	References
Chapter 10 A Review on Smart Bin Management Systems
	10.1 Introduction
		10.1.1 Internet of Things (IoT)
	10.2 Related Work
	10.3 Challenges, Solution, and Issues
	10.4 Advantages
	Conclusion
	References
Chapter 11 Unlocking Machine Learning: 10 Innovative Avenues to Grasp Complex Concepts
	11.1 Regression
		11.1.1 General Approach
		11.1.2 Different Regression Models
	11.2 Classification
		11.2.1 Definition
		11.2.2 Example
		11.2.3 Day-to-Day Example
			11.2.3.1 Optical Character Recognition (OCR)
			11.2.3.2 Face Recognition
			11.2.3.3 Recognition of Speech
			11.2.3.4 Medical Findings
			11.2.3.5 Extraction of Acquaintance
			11.2.3.6 Compression
			11.2.3.7 Additional Examples
		11.2.4 Discriminant
		11.2.5 Algorithms
	11.3 Clustering
		11.3.1 Data Examples Using Natural Clusters
	11.4 Clustering (k-means)
		11.4.1 Outline
		11.4.2 Example
			11.4.2.1 Problem
			11.4.2.2 Solution
		11.4.3 Some Methods for Initialization
		11.4.4 Disadvantages
		11.4.5 Use Case: Image Compression and Segmentation
			11.4.5.1 Segmentation of Images
			11.4.5.2 Compression of Data
	11.5 Reduction of Dimensionality
		11.5.1 Introduction
			11.5.1.1 Feature Selection
			11.5.1.2 Feature Extraction
			11.5.1.3 Error Measures
		11.5.2 Benefits of Reducing Dimensionality
		11.5.3 Subset Selection
			11.5.3.1 Selecting Forward
			11.5.3.2 Remarks
			11.5.3.3 Selection in Reverse
	11.6 The Ensemble Method
		11.6.1 Random Forest
		11.6.2 Algorithm
		11.6.3 Benefits and Drawbacks
			11.6.3.1 Benefits
			11.6.3.2 Drawbacks
		11.6.4 Deep Learning and Neural Networks
			11.6.4.1 Definition
			11.6.4.2 Remarks
		11.6.5 Applications
		11.6.6 Artificial Neural Network
			11.6.6.1 Biological Motivation
	11.7 Transfer of Learning
	11.8 Learning Through Reinforcement
	11.9 Processing of Natural Languages
	11.10 Word Embeddings
	11.11 Conclusion
	References
Chapter 12 Recognition Attendance System Ensuring COVID-19 Security
	12.1 Introduction
	12.2 Literature Survey
	12.3 Software Requirements
		12.3.1 Operating System - Windows 7 and Above
		12.3.2 IDE-Visual Studio Code
		12.3.3 Programming Languages: Python, HTML, CSS, JS, and PHP
	12.4 Hardware Requirements
		12.4.1 Three Processors and Above
		12.4.2 RAM - 2GB (Minimum Capacity)
		12.4.3 MLX90614 IR (Infrared) Sensor for Temperature Measurement
		12.4.4 Pi Camera
		12.4.5 Raspberry Pi
		12.4.6 OLED Display
	12.5 Methodology
	12.6 Building the Database
	12.7 Pi Camera for Extracting Face Features
	12.8 Real-Time Testing on Raspberry Pi
	12.9 Contactless Body Temperature Monitoring
		12.9.1 MLX90614 Interfaced with the Raspberry Pi
	12.10 Raspberry-Pi Setting Up an SMTP Email
	12.11 Uploading to the Database
	12.12 Updating the Website
	12.13 Report Generation
	12.14 Result
	12.15 Discussion
	12.16 Conclusion
	References
Chapter 13 Real-Time Industrial Noise Cancellation for the Extraction of Human Voice
	13.1 Introduction
	13.2 Literature Survey
	13.3 Methodology
		13.3.1 Design of Processing System
		13.3.2 The NLMS Algorithm
		13.3.3 Design of the System at the Machine End
		13.3.4 Design of the System at the User End
	13.4 Experimental Results
		13.4.1 Time Domain Analysis of the Signals
		13.4.2 Frequency Domain Analysis of the Signals
		13.4.3 Performance of the Algorithm on Hardware
	13.5 Conclusion
	References
Chapter 14 Machine Learning-Based Water Monitoring System Using IoT
	14.1 Introduction
	14.2 Smart Water Monitoring System
	14.3 Sensors and Hardware
		14.3.1 Machine Learning Algorithm
	14.4 PowerBI Reports
		14.4.1 Reading of Data from the Sensors
		14.4.2 Handling of Data by the Controller
		14.4.3 Storage and Processing of Data in the Cloud
		14.4.4 Training of Machine Data Models
		14.4.5 Water Flow Controller Based on the Machine Learning Output
		14.4.6 Analysis of the Water Data Reports
	14.5 Conclusion
	References
Chapter 15 Design and Modelling of an Automated Driving Inspector Powered by Arduino and Raspberry Pi
	15.1 Introduction
	15.2 Literature Survey
		15.2.1 Objectives
		15.2.2 Preliminaries Used
		15.2.3 Method Proposed
	15.3 Results
	15.4 Conclusion
	References
Chapter 16 Kalman Filter-Based Seizure Prediction Using Concatenated Serial-Parallel Block Technique
	16.1 Introduction
	16.2 Prior Work
	16.3 Proposed Method
		16.3.1 Phase 1
		16.3.2 Phase 2
		16.3.3 Phase 3
	16.4 Serial-Parallel Block Concatenation Approach
		16.4.1 PDF Method
	16.5 Algorithm
	16.6 Kalman Filter
	16.7 Results and Discussion
	16.8 Conclusion
	References
Chapter 17 Current Advancements in Steganography: A Review
	17.1 Introduction
	17.2 Evaluation Parameters
	17.3 Types of Steganography
		17.3.1 Host
		17.3.2 Domain
	17.4 Traditional Steganographic Techniques
		17.4.1 Least Significant Bit (LSB) Steganography
		17.4.2 Pixel-Value Differencing (PVD)
		17.4.3 Edge-Based Embedding (EBE)
		17.4.4 Random Pixel Embedding (RPE)
		17.4.5 Pixel Mapping Method (PMM)
	17.5 CNN-Based Steganographic Techniques
	17.6 GAN-Based Steganographic Techniques
	17.7 Steganalysis
	17.8 Applications
	17.9 Dataset Used for Steganography
		17.9.1 BOSS
		17.9.2 Pascal VOC
		17.9.3 ImageNet
		17.9.4 COCO
		17.9.5 MNIST
	17.10 Conclusion
	References
Chapter 18 Human Emotion Recognition Intelligence System Using Machine Learning
	18.1 Introduction
	18.2 Literature Review
	18.3 Problem Statement
	18.4 Methodology
	18.5 Results
	18.6 Applications
	18.7 Conclusion
	18.8 Future Work
	References
Chapter 19 Computing in Cognitive Science Using Ensemble Learning
	19.1 Introduction
	19.2 Recognition of Human Activities
	19.3 Methodology
		19.3.1 Dataset Organization
		19.3.2 Handling the Multiclass Imbalanced Dataset with a Skewed Data Distribution
	19.4 Applying the Boosting-Based Ensemble Learning
		19.4.1 Ensemble Learning
			19.4.1.1 Development of Ensemble Learning
			19.4.1.2 Computational Justification of Ensemble Learning
		19.4.2 Boosting Methods
			19.4.2.1 Justification for the Use of the Boosting Method
			19.4.2.2 Boosting Algorithms
			19.4.2.3 Boosting and Ensemble Learning
	19.5 Human Activity Features Computability
		19.5.1 Activity Recognition and Behaviors Analysis
			19.5.1.1 Boosting and Activity Recognition
			19.5.1.2 Ensemble Learning and Human Behaviors
		19.5.2 Data Processing and Feature Mapping
			19.5.2.1 Imbalanced Skewed Distributed Data Processing
			19.5.2.2 Feature Vector Mapping
	19.6 Conclusion
	References
About the Editors
Index
Also of Interest