Applied Intelligent Decision Making in Machine Learning - Applied Intelligent Decision Making in Machine Learning -

: Data Stream Mining for Big Data Introduction Research Issues in Data Stream Mining Filtering and Counting in a Data Stream Bloom Filters Counting the Frequency of Items in a Stream Count Unique Items in a Data Stream Sampling from Data Streams Concept Drift Detection in Data Streams Causes of Concept Drift Handling Concept Drift CUSUM Algorithm The Higia Algorithm Dynamic Weighted Majority Algorithm Discussion References Introduction Literature Review Materials and Methods Overall ML Model Development Process Data Collection Iris Dataset Soybean Aphid Dataset Weed Species Dataset Shape Features Extraction Data Cleaning Feature Selection Filter Methods Wrapper Methods Embedded Methods Relief Algorithms Data Splitting The ML Methods Linear Discriminant Analysis k-Nearest Neighbor Evaluation of ML Methods Confusion Matrix Accuracy Precision Recall F-score Results and Discussion Results of Evaluated Features from the Dataset Selected Features from the Dataset Dataset Test of Normality for Model Selection Soybean Aphid Identification Features Ranking The LDA Model and Evaluation Weed Species Classification Features Ranking The kNN Model and Evaluation Comparison of Results with the Standard Iris Data Conclusions Acknowledgments References : A Multi-Stage Hybrid Model for Odia Compound Character Recognition Introduction General OCR Stages Structural Similarity Projection Profile and Kendall Rank Correlation Coefficient Matching Local Frequency Descriptor General Regression Neural Network (GRNN)Proposed Method Experiments Dataset Creation Experimental Setup Results and Discussion Conclusion and Future Scope References : Development of Hybrid Computational Approaches for Landslide Susceptibility Mapping Using Remotely Sensed Data in East Sikkim, India Introduction Study Materials and Methodology Area of Research Study MULTI-COLINEARITY ASSESSMENT (MCT)Affecting Factors Landslide Inventory Map (LIM)Methodology Hybrid Biogeography-Based Optimization Hybridization with Differential Evolution The DE/BBO Algorithm Local-DE/BBO Self-Adaptive DE/BBO Validation of Models Shortly Structured Methodology Results and Discussion Importance of the Conditioning Factors on the Occurrences of Landslides Application of Hybrid Biogeography-Based Optimization for Landslide Susceptibility Assessment Conclusion References : Domain-Specific Journal Recommendation Using a Feed Forward Neural Network Introduction Literature Survey Content-Based Recommendation System for Domain-Specific Papers Scraping and Data Integration (Challenges and Solutions for Data Collection)Limitations on the Size of the Query Results Fixed Limits Pagination Dynamic Contents Access Limitations Masked URL Parameters Robot Recognition and Reverse Turing Tests Changing the Content of Request Headers Selecting Appropriate Cookie Settings Requests and Different Time Intervals Altering the IP Address Data Curation The Complexity of the Integration Operation Phase 1: Identifying Candidate Journals Phase 2: Ranking Candidate Journals Experimental Results and Discussions Configurations Result Analysis Conclusion and Future Work References : Forecasting Air Quality in India through an Ensemble Clustering Technique Introduction Related Works Air Quality Prediction Ensemble Modeling Variants of Ensemble Models Ensemble Clustering Dataset Descriptions Methodology Final Cluster Labeling METIS Function METIS Algorithm Phases Advantages EXPERIMENTAL RESULTS Silhouette Coefficient Calinski-Harabasz Index Davies-Bouldin Index Conclusion References : An Intelligence-Based Health Biomarker Identification System Using Microarray Analysis Introduction Existing Knowledge Classification Model Approaches for Feature Selection Shuffled Frog-Leaping Algorithm and Particle Swarm Optimization (SFLA-PSO)The Advantage of SFLA Algorithm for BSFLA-PSO Experimental Result Analysis Dataset Considered for This Experiment Normalization Details of Classifiers Used in This Experimental Study and Evaluation Metrics Result Analysis Performance of Proposed BSFLA-PSO with Prostate Dataset Performance of Proposed BSFLA-PSO with Leukemia Dataset Performance of Proposed BSFLA-PSO with ALL/AML Dataset Performance of Proposed BSFLA-PSO with ADCA Lung Dataset Performance of Proposed BSFLA-PSO with CNS Dataset Conclusion References : Extraction of Medical Entities Using a Matrix-Based Pattern-Matching Method Introduction Background Methodology Dataset Proposed Method Text Pre-Processing Trained Matrix Formation Test Matrix Formation Pattern Matching Pruning Non-Medical Concepts System Evaluation Results and Discussion Conclusions and Future Work Acknowledgments References : Supporting Environmental Decision Making Application of Machine Learning Techniques to Australia’s Emissions Introduction Data and Methodology Data Methodology Decision Trees Random Forests Extreme Gradient Boosting Support Vector Regression Data Division and the Experimental Environment Optimization of Hyperparameters Parameter Tuning for the DT, RF, and XGBoost Algorithms Parameter Tuning for the SVR Algorithm Performance Metrics Results and Discussion Development and Validation of the DT Model Development and Validation of the RF Model Development and Validation of the XGBoost Model Development and Validation of the SVR Model Performance Evaluation of Model Concluding Remarks References : Prediction Analysis of Exchange Rate Forecasting Using Deep Learning-Based Neural Network Models Introduction Methodology Performance Measure Data Preparation Results and Simulations For Sliding Window Size 7 For Sliding Window Size 10 For Sliding Window Size 13 Conclusion References : Optimal Selection of Features Using Teaching-Learning-Based Optimization Algorithm for Classification Introduction Related Work Basic Technology Proposed Model Result Analysis Conclusion References : An Enhanced Image Dehazing Procedure Using CLAHE and a Guided Filter Introduction Literature Survey White Balance (WB)CLAHE GF Proposed Methodology Dataset Collection and Analysis Image Quality Assessment Criteria Peak Signal-to-Noise Ratio and Mean Squared Error Entropy Structural Similarity Index Contrast Gain Experimental Results and Discussion Conclusion and Future Scope References