Machine Learning for Real World Applications (Transactions on Computer Systems and Networks)

Foreword
Preface
Acknowledgements
About This Book
Contents
Editors and Contributors
Abbreviation
1 Predictability of Metaverse Coins Using an Advanced Machine Learning Approach
	1.1 Introduction
	1.2 Data
	1.3 Proposed Ensemble Predictive Model
		1.3.1 BORUTA Algorithm
		1.3.2 The Residual-Driven RF Algorithm
	1.4 Results and Analysis
		1.4.1 Findings of the Boruta Algorithm
		1.4.2 Findings of Predictive Modeling
	1.5 Conclusions
	References
2 DriveHarmony: An AI-Based Safety Assistant Driving System
	2.1 Introduction
	2.2 Literature Survey
	2.3 Methodology
		2.3.1 Requirement Specification
		2.3.2 Design and Analysis
	2.4 Implementation
		2.4.1 Implementation of DrowsDet
		2.4.2 Implementation of AIsy
		2.4.3 Implementation of HarmonyCall
	2.5 Evaluation
		2.5.1 Black Box Testing
		2.5.2 Stationary Testing
		2.5.3 On-Road Testing
	2.6 Conclusion
	References
3 Effective Integration of Clustering and Classification or Regression Machine Learning Algorithms
	3.1 Introduction
	3.2 Clustering Algorithms
		3.2.1 Centroid-Based Algorithms
		3.2.2 Density-Based Clustering
		3.2.3 Distribution-Based Clustering
		3.2.4 Hierarchy Clustering
		3.2.5 Grid-Based Clustering
	3.3 Classification and Regression Algorithms
		3.3.1 Logistic Regression
		3.3.2 Support Vector Machines (SVM)
		3.3.3 Integrated Learning Algorithms
	3.4 Building Learning Model Using Sklearn
	3.5 Datasets
		3.5.1 Clustering + Classification using Sklearn
	3.6 Conclusions
	References
4 Design and Development of Machine Learning-Based Depression Identification Decision Support System
	4.1 Introduction
	4.2 Literature Review
	4.3 Material and Methods
	4.4 Experiment and Result Discussion
	4.5 Depression Identification Decision Support System
	4.6 Conclusion
	References
5 Machine Learning Algorithmic Model for Pairs Trading
	5.1 Introduction
		5.1.1 Pairs Trading
		5.1.2 Example of Pairs Trade
	5.2 Engle-Granger Procedure for Co-integration Testing
		5.2.1 Hedging and Cointegration
		5.2.2 Testing of Cointegration
		5.2.3 What is a Stationary Series?
		5.2.4 Dickey-Fuller and Augmented Dickey-Fuller Tests
		5.2.5 Algorithm for Pairs Trading
		5.2.6 Pairs Trading Between TestY and TestX Stocks
		5.2.7 Error Correction Model (ECM/ecm)
	5.3 Neural Network Approach to Pairs Trading Based on Co-integrated Spread
	5.4 Conclusion
	References
6 Evaluation of Machine Learning Models for Optimized Crop Recommendation
	6.1 Introduction
		6.1.1 Background
		6.1.2 Dataset Description
	6.2 Literature Survey
	6.3 Assumptions and Notations
		6.3.1 Data Assumptions
		6.3.2 Notations
		6.3.3 Data Reliability and Crop Suitability
		6.3.4 Hypothesis Analysis
	6.4 Process Flow Diagram
	6.5 Mathematical Model
		6.5.1 Random Forest
		6.5.2 Logistic Regression
		6.5.3 KNN Model
		6.5.4 Gradient Boosting
		6.5.5 Extra Trees
		6.5.6 Naive Bayes
	6.6 Numerical Illustration
		6.6.1 Sensitivity Analysis
		6.6.2 Observation
	6.7 Conclusion
	References
7 Application of Neural Network-Based Techniques to Network Intrusion Detection
	7.1 Introduction
	7.2 Related Work
	7.3 ANN-Based Techniques
		7.3.1 Radial Basis Function Network
		7.3.2 Self-Organizing Map (SOM)
		7.3.3 Sequential Minimal Optimization (SMO)
		7.3.4 LVQ 3
	7.4 The Proposed Design Model
	7.5 Experimentation
		7.5.1 Dataset
		7.5.2 Pre-processing of Data
		7.5.3 Confusion Matrix
		7.5.4 Cross-Validation
	7.6 Result Analysis
	7.7 Conclusion
	References
8 Smart Algorithm as a Machine Learning Application for Elderly People Safety Using Mobile Platforms
	8.1 Introduction
	8.2 Literature Review
	8.3 Technical Background
	8.4 Methodology
		8.4.1 Fishbone Diagram
		8.4.2 Requirements Modelling
		8.4.3 Performance
		8.4.4 System Flowchart
		8.4.5 Use Case Diagram
	8.5 Conclusions
	References
9 Machine Learning Based Parkinson’s Disease Detection Using Voice and Handwriting Analysis
	9.1 Introduction
	9.2 Literature Survey
	9.3 Methods for Analysis
		9.3.1 Data Set Analysis for Voice
	9.4 Algorithm Selection
		9.4.1 Logistic Regression
		9.4.2 K-Nearest Neighbor
		9.4.3 Random Forest
		9.4.4 XGBoost
	9.5 Flow Chart
		9.5.1 Handwriting Detection
	9.6 Methodology
		9.6.1 Histogram of Oriented Gradient
	9.7 Results
		9.7.1 For Handwriting Detection
		9.7.2 Detection of Parkinson Using Voice
		9.7.3 Detection of Parkinson Using Handwriting
	9.8 Future Work
	9.9 Conclusion
	References
10 CCTV AI-Based System with Custom Object Detection and Video Upscaling Model
	10.1 Introduction
	10.2 Review of Related Literature
		10.2.1 Theoretical Background
		10.2.2 Related Literature
		10.2.3 Related Systems
		10.2.4 Issues with Prior Systems
	10.3 Technical Background
		10.3.1 Object Detector
		10.3.2 Changes to Yolov5’s Source Code
		10.3.3 Video Upscaler
	10.4 Conclusion
	References
11 Forecasting the COVID-19 End in India Using Machine Learning and Population Density Clustering
	11.1 Introduction
		11.1.1 The TSVR
		11.1.2 The LDMR
		11.1.3 The ELM
	11.2 Experimental Setup and Analysis
	11.3 Zone-Based Prediction for Indian States
	11.4 Relationship Between Population Density and the Number of Infected Cases
	11.5 Conclusion
	References
12 A Machine Learning-Based Analysis of Internet Addiction Among Children and Adolescents During Covid-19 Lockdown
	12.1 Introduction
	12.2 Literature Review
	12.3 Methodology
		12.3.1 Data Set Description
		12.3.2 Implementation Procedure
		12.3.3 Feature Reduction
	12.4 Result and Discussion
		12.4.1 Classification Result
		12.4.2 Impact of Feature Reduction
	12.5 Conclusion
	References
13 Building Architectural Styles Classification Using Convolutional Neural Networks Models
	13.1 Introduction
	13.2 Literature Review
	13.3 Technical Background
		13.3.1 Input Image
		13.3.2 Convolution Layer
		13.3.3 Activation Layer
		13.3.4 Pooling Layer
		13.3.5 Flatten Layer
		13.3.6 Fully Connected Layer
	13.4 Experimental Work
		13.4.1 Dataset
		13.4.2 Experiments
		13.4.3 Discussion of Results
	13.5 Conclusions
	References
14 Development of Clinical Decision Support System Using Genetically Optimized Artificial Neural Network
	14.1 Introduction
	14.2 Related Work
	14.3 Material and Methods
		14.3.1 Dataset
		14.3.2 Artificial Neural Network
		14.3.3 Genetic Algorithm
	14.4 Methodology
	14.5 Result and Discussions
	14.6 Clinical Decision Support System
	14.7 Conclusion
	References
15 A Machine Learning Approach for Forecasting Energy Use in the Transportation Sector of the USA
	15.1 Introduction
	15.2 Data and Descriptive Statistics
	15.3 Methodology
	15.4 Results and Discussion
	15.5 Conclusions
	References