Applied Machine Learning and Data Analytics : 5th International Conference, AMLDA 2022, Reynosa, Tamaulipas, Mexico, December 22–23, 2022, Revised Selected Papers

This book constitutes the refereed proceedings of the 5th International Conference on Applied Machine Learning and Data Analytics, AMLDA 2022, held in Reynosa, Tamaulipas, Mexico, during December 22–23, 2022. The 16 full papers and 4 short papers included in this book were carefully reviewed and selected from 89 submissions. They were organized in topical sections as follows: Machine learning, Healthcare and medical imaging informatics; biometrics; forensics; precision agriculture; risk management; robotics and satellite imaging. Preface 6 Organization 7 Contents 10 Deep Learning Methods to Automate Embryo Classification and Evaluation 12 1 Introduction 12 1.1 About IVF 12 1.2 IVF Procedure 13 1.3 Embryo Development 13 1.4 Importance of Embryo Grading 14 2 Material and Methods 15 2.1 Image Datasets 15 2.2 Embryo Development Stages 15 2.3 Supervised Learning Algorithms 15 3 Methodology 17 3.1 Convolutional Neural Network 17 3.2 Region Based Convolutional Neural Network 18 3.3 Mask R-CNN 19 3.4 Deep Convolutional Neural Network Architectures 19 4 Comparative Analysis 20 5 Conclusion 21 References 22 Univariate Feature Fitness Measures for Classification Problems: An Empirical Assessment 24 1 Introduction 24 2 Related Works 25 3 Feature Fitness Measures 26 3.1 Chi-Square 27 3.2 Analysis of Variance (ANOVA) 27 3.3 Mutual Information 28 3.4 Symmetrical Uncertainty 29 3.5 Fisher Score 29 3.6 Gini Index 29 3.7 ReliefF 30 3.8 Correlation Estimation 30 4 Experimental Results 31 5 Conclusion 35 References 35 Securing Advanced Metering Infrastructure Using Blockchain for Effective Energy Trading 38 1 Introduction 38 2 Related Works 39 2.1 Blockchain in the Energy Sector 41 2.2 Blockchain-Based Smart Grid 42 2.3 Ethereum Transaction and Fee System 44 2.4 Virtual Smart Grid Deployed on EVM 44 3 SM-DSO Interaction Implementation with Blockchain 45 4 Proposed Method 47 5 Cost Analysis 48 6 Conclusion 48 References s 48 Keratoconus Classification Using Feature Selection and Machine Learning Approach 50 1 Introduction 50 2 Related Works 52 3 Methodology 54 3.1 Dataset 55 3.2 Feature Selection 55 3.3 Classification 57 3.4 SVM 58 4 Experimental Parameters 58 5 Conclusion 60 References 61 Semantic Segmentation of the Lung to Examine the Effect of COVID-19 Using UNET Model 63 1 Introduction 63 2 Literature Review 65 3 Methodology 66 3.1 Overview 66 3.2 U-Net Architecture 66 3.3 Data Pre-Processing 67 3.4 Metrics for Model Segmentation 68 3.5 Model Structure 70 3.6 Model Parameters 70 4 Results 71 5 Conclusion and Future Work 73 References 73 SMDKGG: A Socially Aware Metadata Driven Knowledge Graph Generation for Disaster Tweets 75 1 Introduction 76 2 Related Works 77 3 Proposed Architecture 78 3.1 Performance Evaluation and Result 83 4 Conclusion 86 References 87 Brain MRI Image Classification Using Deep Learning 89 1 Introduction 89 2 Related Work 91 3 Methodology 93 3.1 Flow Diagram and Working 93 3.2 Data Collection 93 3.3 Data Pre-processing 94 3.4 Architecture Study 94 3.5 Architecture Deployment 94 3.6 Result Analysis and Re-Iteration for Improvement 95 4 Experimental Result Analysis 98 5 Conclusions 99 References 99 A Real-Time Face Recognition Attendance Using Machine Learning 102 1 Introduction 102 1.1 General Introduction 102 2 Problem Statement 104 3 Related Work 105 4 Methodology 106 4.1 Background Knowledge 106 4.2 Face Detection 107 4.3 Face Recognition 108 4.4 System Architecture 108 4.5 Working Principle of the System 109 4.6 Proposed System Requirements 111 5 System Analysis and Design 113 6 Experiment and Result Analysis 114 6.1 Machine Learning Approach 114 6.2 Results 115 7 Conclusions and Future Works 116 References 116 Towards Abalone Differentiation Through Machine Learning 119 1 Introduction 119 2 Using Machine Learning 120 3 Methodology 121 4 Experiments and Results 122 4.1 Data Collection 123 4.2 Data Description and Preprocessing 123 4.3 Feature Selection 124 4.4 Data Balancing and Sampling 125 4.5 Model Training and Testing 126 4.6 Classification Results 127 5 Conclusions 128 References 128 Better Qualitative Searching for Effecting the Performance of Machine Translation 130 1 Introduction 130 2 Related Work 131 3 Overview of NLP Technologies 132 3.1 Machine Translation 132 3.2 Sentiment Analysis 136 3.3 Punctuation Restoration 137 3.4 Named Entity Recognition 138 4 Conclusion 139 References 139 RU-Net: A Novel Approach for Gastro-Intestinal Tract Image Segmentation Using Convolutional Neural Network 142 1 Introduction 142 2 Related Works 143 2.1 Region Based Convolutional Neural Networks (RCNN's) 143 2.2 U-Net Type Architectures 144 2.3 Mask R-CNN 144 3 RU-Net Model 147 4 Experimentation and Results 148 5 Conclusion 151 References 151 A Credit Card Fraud Detection Model Using Machine Learning Methods with a Hybrid of Undersampling and Oversampling for Handling Imbalanced Datasets for High Scores 153 1 Introduction 153 2 Related Works 155 2.1 Machine Learning Approaches 155 2.2 Sampling Methods 156 2.3 Evaluation Performance for Imbalanced Data 157 3 Experimental Setup and Methods 157 3.1 The Overall Framework Model for Credit Card Fraud Detection 157 3.2 Hybrid of Undersampling and Oversampling 158 3.3 Data Insights and Dataset 159 3.4 Feature Selection 159 3.5 Model Evaluation Using Performance Metrics 160 4 Results and Discussions 161 5 Conclusion and Future Work 163 References 164 Implementation of YOLOv7 for Pest Detection 167 1 Introduction 167 2 Related Works 168 3 Methodology 169 3.1 Dataset 169 3.2 YOLOv7 Model Architecture 170 4 Results and Discussions 171 5 Conclusions 175 References 176 Online Grocery Shopping: - Key Factors to Understand Shopping Behavior from Data Analytics Perspective 177 1 Introduction 177 2 Review of Literature 179 3 Research Methodology 182 4 Analysis and Findings 182 5 Conclusion 186 6 Managerial Implications 187 7 Limitations and Future Research 187 References 187 A Novel Approach: Semantic Web Enabled Subject Searching for Union Catalogue 190 1 Introduction 190 2 Literature Review 192 3 Problem Statement 192 4 Objectives 194 5 Analysis of Existing Data 194 6 Research Methodology 194 7 Suggested Structure 196 7.1 Basics to Construct GujCat Ontology Elements Based on DDC and Book Attributes 196 7.2 Construction of Book Ontology 197 7.3 Basics to Build and Evaluate Outcome from Ontology 197 8 Conclusion and Future Work 200 References 200 How People in South America is Facing Monkeypox Outbreak? 202 1 Introduction 202 2 Monkeypox Global Situation Overview 203 2.1 Monkeypox Spreading in South America 205 3 Methodology 206 3.1 Data Collection 207 3.2 Data Pre-processing 208 3.3 Data Analysis 208 4 Results 209 4.1 Data Exploration 209 4.2 Sentiment Analysis Polarity 210 5 Conclusions and Future Work 210 References 211 Multilevel Classification of Satellite Images Using Pretrained AlexNet Architecture 213 1 Introduction 213 2 Proposed Method 214 2.1 Filtering 214 2.2 AlexNet 215 2.3 Performance Analysis 216 3 Conculsion 218 References 219 Handwriting Recognition for Predicting Gender and Handedness Using Deep Learning 221 1 Introduction 221 2 Related Work 223 3 Proposed Approach 224 4 Experiments and Results 225 4.1 Datasets 225 4.2 Results 226 5 Conclusion 231 References 232 Retrieval of Weighted Lexicons Based on Supervised Learning Method 233 1 Introduction 233 2 Preliminaries 235 2.1 POS Tagging 235 2.2 Logistic Regression 235 2.3 Distance from a Point to a Linear Decision Boundary 235 3 Method 236 4 Experimentation and Results 238 4.1 Evaluating the Weighted Lexicon 239 5 Conclusions 240 References 241 Performance Evaluation of Smart Flower Optimization Algorithm Over Industrial Non-convex Constrained Optimization Problems 242 1 Introduction 242 2 Related Work 243 3 Smart Flower Optimization Algorithm (SFOA) 244 4 Experiment Analysis 245 5 Conclusion 248 References 248 Author Index 251