Computational Statistical Methodologies and Modeling for Artificial Intelligence (Edge AI in Future Computing)

This book covers computational statistics-based approaches for Artificial Intelligence. The aim of this book is to provide comprehensive coverage of the fundamentals through the applications of the different kinds of mathematical modelling and statistical techniques and describing their applications in different Artificial Intelligence systems. The primary users of this book will include researchers, academicians, postgraduate students, and specialists in the areas of data science, mathematical modelling, and Artificial Intelligence. It will also serve as a valuable resource for many others in the fields of electrical, computer, and optical engineering. The key features of this book are: Presents development of several real-world problem applications and experimental research in the field of computational statistics and mathematical modelling for Artificial Intelligence Examines the evolution of fundamental research into industrialized research and the transformation of applied investigation into real-time applications Examines the applications involving analytical and statistical solutions, and provides foundational and advanced concepts for beginners and industry professionals Provides a dynamic perspective to the concept of computational statistics for analysis of data and applications in intelligent systems with an objective of ensuring sustainability issues for ease of different stakeholders in various fields Integrates recent methodologies and challenges by employing mathematical modeling and statistical techniques for Artificial Intelligence Cover Half Title Series Information Title Page Copyright Page Dedication Table of Contents Preface About the Editors List of Contributors Theme 1 Statistics and AI Methods With Applications 1 A Review of Computational Statistics and Artificial Intelligence Methodologies 1.1 Introduction 1.2 Current Methodologies 1.2.1 Related Work On Computational Statistics 1.2.2 Related Work in AI 1.2.3 A Comparison of CS and AI 1.3 Discussion and Conclusion References 2 An Improved Random Forest for Classification and Regression Using Dynamic Weighted Scheme 2.1 Introduction 2.1.1 Proposed Work 2.2 Random Forest 2.2.1 Random Forest as Classifier 2.2.2 Random Forest as Regressor 2.3 Proposed Method 2.3.1 Dynamic Weight Score Computation 2.4 Experimental Results 2.4.1 Hyperspectral Image Classification 2.4.1.1 Implementation Details and Performance Analysis 2.4.2 Regression Application: Soil Moisture Prediction in Hyperspectral Dataset 2.4.2.1 Implementation Details and Performance Analysis 2.4.3 Object and Digit Classification 2.4.3.1 Implementation Details and Performance Analysis 2.5 Conclusion Conflict of Interest Note References 3 Study of Computational Statistical Methodologies for Modelling the Evolution of COVID-19 in India During the Second Wave 3.1 Introduction 3.2 Related Work 3.3 Methodology 3.3.1 Preliminaries 3.3.2 Deterministic Approach 3.3.2.1 Proposed Model 1 3.3.2.2 Calculation of Basic Reproduction Number (R 0 ) 3.3.2.3 Stability Analysis 3.3.2.4 Data and Implementation 3.3.3 Stochastic Approach 3.3.3.1 Proposed Model 2 3.3.3.2 Data and Implementation 3.3.3.3 Results and Discussion 3.4 Results 3.4.1 Deterministic Approach 3.4.2 Stochastic Approach 3.5 Discussion 3.5.1 Deterministic Approach 3.5.2 Stochastic Approach 3.5.3 Comparison of Both Approaches 3.6 Conclusion References Theme 2 Machine Learning-Adopted Models 4 Distracted Driver Detection Using Image Segmentation and Transfer Learning 4.1 Introduction 4.2 Related Works 4.3 System Model 4.3.1 Image Preprocessing 4.3.2 Classification Function 4.3.3 Training Algorithm 4.4 Dataset and Exploratory Analysis 4.5 Result and Discussion 4.6 Conclusion References 5 Review Analysis of Ride-Sharing Applications Using Machine Learning Approaches: Bangladesh Perspective 5.1 Introduction 5.2 Related Work 5.3 Methodology 5.3.1 Data Description 5.3.2 Data Pre-Processing 5.3.3 Proposed Model Working Procedure 5.3.3.1 Machine Learning Models 5.3.3.2 Performance Measurement Unit 5.3.3.3 Accuracy 5.3.3.4 Precision 5.3.3.5 Recall 5.3.3.6 F1-Score 5.4 Result 5.4.1 Cross-Validation 5.5 Discussion 5.6 Conclusions Acknowledgments References 6 Nowcasting of Selected Imports and Exports of Bangladesh: Comparison Among Traditional Time Series Model and Machine ... 6.1 Introduction 6.2 Methodology 6.2.1 Data and Variables 6.2.2 Methods 6.2.2.1 ARIMA Model 6.2.2.2 Artificial Neural Network Procedure 6.2.2.3 Support Vector Regression Model 6.2.3 Evaluating Model Performance 6.3 Results 6.4 Conclusion Availability of Data Conflicting Interests Funding References Theme 3 Development of the Forecasting Component to the Decision Support Tools 7 An Intelligent Interview Bot for Candidate Assessment By Using Facial Expression Recognition and Speech Recognition System 7.1 Introduction 7.2 Related Work 7.3 Proposed Artificial Intelligence Chatbot 7.3.1 Facial Recognition Module 7.3.2 Automatic Speech Recognition 7.4 Results and Experimentation 7.5 Conclusion Note References 8 Analysis of Oversampling and Ensemble Learning Methods for Credit Card Fraud Detection 8.1 Introduction 8.2 Related Work 8.3 Proposed Approach 8.3.1 Ensemble Learning 8.4 Experiment Results 8.4.1 Dataset and Preprocessing 8.4.2 Evaluation Metrics Ensemble Learning 8.4.2.1 Ensemble of Logistic Regression and Random Forest 8.4.2.2 Ensemble of Logistic Regression and KNN 8.4.2.3 Ensemble of Logistic Regression, Random Forest, and KNN 8.4.2.4 Ensemble of Logistic Regression, Random Forest, KNN, and SVM 8.4.2.5 Ensemble of Logistic Regression, Random Forest, KNN, and Naïve Bayes 8.4.2.6 Ensemble of Logistic Regression, Random Forest, KNN, Naïve Bayes, and SVM 8.5 Conclusion Acknowledgements References 9 Combining News With Time Series for Stock Trend Prediction 9.1 Introduction 9.2 Related Work 9.3 Methodology 9.3.1 Time Series Prediction 9.3.2 Text Mining and Prediction 9.3.3 Ensembling Prediction Models 9.4 Experiment and Results 9.4.1 Inference From Graphs 9.5 Conclusion 9.6 Future Work References 10 Influencing Project Success Outcomes By Utilising Advanced Statistical Techniques and AI During the Project Initiating ... 10.1 Introduction: Background and Driving Forces 10.2 Data Collection 10.2.1 Quantitative Data Collection 10.2.2 Stratified Random Sampling 10.2.3 Qualitative Data Collection 10.3 Proposed Method 10.3.1 Stage One – Factor Analysis 10.3.2 Stage Two – Cluster Analysis 10.3.3 Stage Three – Alignment to Cynefin Framework 10.4 Cynefin and the Qualitative Dataset 10.5 Cynefin and the Quantitative Dataset 10.6 Complexity and Decision Assessment Matrix 10.7 Robotic Process Automation (RPA) 10.8 Limitations and Restrictions of the Proposal 10.9 Conclusion References Theme 4 Socio-Economic and Environmental Modelling 11 Computational Statistical Methods for Uncertainty Assessment in Geoscience 11.1 Introduction 11.2 Methods 11.2.1 Case Study Description 11.2.2 Bayesian Approximation of Interpretation Uncertainty 11.2.2.1 Selection of Important Variables 11.2.2.2 Bayesian Approximation 11.2.3 Conditional Indicator Simulation 11.2.3.1 Variogram Parameters 11.2.3.2 Simulation 11.2.4 Comparison of Intervals 11.3 Results 11.3.1 Uncertainty Assessment Using Bayesian Approximation 11.3.2 Uncertainty Assessment Using SIS 11.3.3 Comparison of Interpretation and Spatial Uncertainty 11.3.4 Discussion Conflict of Interest Acknowledgments Note References 12 A Comparison of Geocomputational Models for Validating Geospatial Distribution of Water Quality Index 12.1 Introduction 12.2 Application Domain: A Case Study in Cork Harbour 12.3 Methods and Materials 12.3.1 Data Obtaining Process 12.3.2 WQI Calculation 12.3.3 Prediction Techniques 12.3.3.1 Spatial Computational Methods 12.3.4 Model Performance Analysis 12.3.4.1 Cross-Validation (CV) Approaches 12.3.4.2 Prediction Uncertainty Analysis 12.3.4.3 Model Suitability Analysis 12.4 Results and Discussion 12.4.1 Descriptive Assessment of Water Quality 12.4.2 Assessing Water Quality Using WQI Models 12.4.3 Comparison of Geostatistical Perdition Models 12.4.4 Evaluation of Uncertainty of Geocomputational-Interpolation Models 12.4.5 Comparison of Model Suitability for the Prediction of WQIs 12.5 Conclusion Declaration of Competing Interest Acknowledgments Funding Information References 13 Mathematical Modeling for Socio-Economic Development: A Case From Palestine 13.1 Introduction: Background and Driving Forces 13.2 Methodology 13.3 Fixed Points and Stability for the System 13.4 Numerical Solution and Bifurcation 13.5 Conclusion References Theme 5 Healthcare and Mental Disorder Detection With AIs 14 A Computational Study Based On Tensor Decomposition Models Applied to Screen Autistic Children: High-Order SVD, ... 14.1 Introduction 14.2 Experimental Design 14.3 Methodology 14.3.1 Feature Extraction, Feature Ranking, and Classification 14.4 Experimental Results and Discussion 14.4.1 Results 14.5 Concluding Remarks References 15 Stress-Level Detection Using Smartphone Sensors 15.1 Introduction 15.2 Related Work 15.3 Proposed Methodology 15.3.1 Data Collection 15.3.2 Data Extraction 15.3.3 Exploratory Data Analysis 15.3.4 Proposed Model 15.4 Results and Discussion 15.5 Challenges and Future Directions 15.6 Conclusion Acknowledgments References 16 Antecedents and Inhibitors for Use of Primary Healthcare: A Case Study of Mohalla Clinics in Delhi 16.1 Introduction 16.2 Background 16.3 Related Work 16.4 Research Gap 16.5 Objectives 16.6 Methodology 16.6.1 Design of the Study 16.6.2 Sampling 16.6.3 Instrument Deployed 16.6.4 Statistical Analysis 16.7 Results and Discussion 16.7.1 Exploratory Factor Analysis 16.7.2 Chi-Square Testing for Association 16.8 Conclusion Acknowledgments Notes References Index