Intelligent computing . Volume 2 Proceedings of the 2021 Computing Conference / / edited by Kohei Arai

• Pubblicazione: Cham, Switzerland : , : Springer, , [2021]; ©2021
• Descrizione fisica: 1 online resource (1269 pages)
• Disciplina: 006.3
• Soggetto topico: Computational intelligence
• Persona (resp. second.): AraiKohei
• Nota di contenuto: Intro -- Editor's Preface -- Contents -- Balanced Weighted Label Propagation -- 1 Introduction -- 1.1 Contributions -- 2 Related Work -- 3 Proposed Approach -- 3.1 Resolution Limit -- 4 Experiment -- 4.1 Datasets and Setup -- 4.2 Results and Discussion -- 5 Conclusion -- References -- Analysis of the Vegetation Index Dynamics on the Base of Fuzzy Time Series Model -- 1 Introduction -- 2 Problem Definition -- 3 Fuzzy Modeling of NDVI Dynamics -- 4 Conclusion -- References -- Application of Data-Driven Fault Diagnosis Design Techniques to a Wind Turbine Test-Rig -- 1 Introduction -- 2 Wind Turbine System Description -- 3 Data-Driven Methods for Fault Diagnosis -- 3.1 Fault Estimators via Artificial Intelligence Tools -- 4 Simulation and Experimental Tests -- 4.1 Simulated Results -- 4.2 Hardware-in-the-Loop Experiments -- 5 Conclusion -- References -- Mathematical Model to Support Decision-Making to Ensure the Efficiency and Stability of Economic Development of the Republic of Kazakhstan -- 1 Introduction -- 2 Problem Statement and Its Mathematical Model -- 3 Method and Algorithm for Solving the Problem -- 4 Conclusion -- References -- Automated Data Processing of Bank Statements for Cash Balance Forecasting -- 1 Introduction -- 2 Terminology and Notation -- 3 Data Description -- 4 Account Balance Data Challenges -- 4.1 Reconstruction Challenges -- 4.2 Forecasting Challenges -- 5 Data Description -- 5.1 Conventional Approaches to Financial Forecasting -- 5.2 Machine Learning Approaches to Financial Forecasting -- 6 Experimental Comparison -- 6.1 Dataset Description -- 6.2 Experimental Results -- 7 Conclusions and Further Work -- References -- Top of the Pops: A Novel Whitelist Generation Scheme for Data Exfiltration Detection -- 1 Introduction -- 2 Related Work -- 3 Proposed Scheme -- 3.1 Feature Computation -- 3.2 Whitelist Candidate Computation. ; 3.3 Whitelist Candidate Expansion -- 4 Evaluation -- 4.1 Threat Model -- 4.2 Data Set and Experiment Configuration -- 4.3 Feature Evaluation -- 4.4 Whitelist Evaluation -- 4.5 Detection Efficiency Evaluation -- 4.6 Performance Evaluation -- 5 Conclusion -- References -- Analyzing Co-occurrence Networks of Emojis on Twitter -- 1 Introduction -- 2 Related Work -- 3 Data Collection -- 3.1 Topics -- 3.2 Collection Methodology -- 3.3 Search Terms -- 4 Constructing Emoji Co-occurrence Network -- 5 Results -- 5.1 Eigenvectors -- 5.2 Dating -- 5.3 Music -- 5.4 US Politics -- 5.5 Olympics -- 5.6 Epidemics -- 5.7 Control Dataset -- 5.8 Data -- 6 Conclusion -- 7 Future Work -- References -- Development of an Oceanographic Databank Based on Ontological Interactive Documents -- 1 Introduction -- 2 State of the Art -- 3 The Method of Recursive Reduction -- 3.1 Reduction Operator -- 3.2 Applicability Function -- 3.3 Transformation Function -- 4 Ontological Interactive Documents -- 4.1 Ontological Presentation Templates -- 4.2 Ontological Descriptors for Software Integration -- 5 Oceanographic Data Processing -- 5.1 Scientific Reports -- 5.2 Measurement Result Files -- 6 Oceanographic Databank Software System -- 6.1 Ontology-Based User Interface -- 7 Conclusions -- References -- Analyzing Societal Bias of California Police Stops Through Lens of Data Science -- 1 Introduction -- 2 Related Work -- 3 Experimental Setup -- 4 Analysis -- 4.1 Analysis of Stops Through Visualizations -- 4.2 Assessing Racial Discrimination in Traffic Stop Decisions Using Statistical Analysis -- 5 Conclusion -- References -- Automated Metadata Harmonization Using Entity Resolution and Contextual Embedding -- 1 Introduction -- 2 Related Studies -- 3 System Design -- 3.1 Framework Overview -- 3.2 Implementation -- 4 Experimentation -- 5 Limitations -- 6 Conclusion -- References. ; Data Segmentation via t-SNE, DBSCAN, and Random Forest -- 1 Introduction -- 2 Methods -- 2.1 The Algorithm -- 2.2 Cluster Profiles -- 2.3 Generalizing Segments -- 2.4 Software -- 3 Empirical Results -- 3.1 Iris Data Set -- 3.2 Instagram Data -- 3.3 MNIST Case Study -- 3.4 Generalization Performance -- 4 Conclusion and Future Work -- A Matching Clusters for Generalization Analysis -- References -- GeoTree: A Data Structure for Constant Time Geospatial Search Enabling a Real-Time Property Index -- 1 Introduction -- 2 Background -- 2.1 Naive Geospatial Search -- 2.2 GeoHash -- 2.3 Efficiency Improvement Attempts -- 3 GeoTree -- 3.1 High-Level Description -- 3.2 GeoTree Data Nodes -- 3.3 Subtree Data Caching -- 3.4 Retrieval of the Subtree Data -- 3.5 Memory Requirement of the Data Structure -- 3.6 Technical Implementation -- 3.7 Time Complexity -- 3.8 Comparison with the Prefix Tree (Trie) -- 4 Real-World Performance -- 4.1 Application: House Price Index Algorithm -- 4.2 Performance Results -- 4.3 Correlation -- 4.4 Scalability Testing -- 4.5 Discussion of Results -- 5 Conclusion -- References -- Prediction Interval of Future Waiting Times of the Two-Parameter Exponential Distribution Under Multiply Type II Censoring -- 1 Introduction -- 2 The General Weighted Moments Estimation of the Scale Parameter of the One-Parameter Exponential Distribution -- 3 Intervals of Future Waiting Time -- 4 Example -- 5 Discussion -- References -- Predictive Models as Early Warning Systems: A Bayesian Classification Model to Identify At-Risk Students of Programming -- 1 Introduction -- 2 Related Work -- 2.1 Predictors of Student Performance -- 2.2 Predictive Data Mining Modelling for Student Performance in Computing Education -- 2.3 Predictive Modelling with Naive Bayes Classification -- 2.4 Early Warning Systems (EWS) in Education -- 3 Research Methodology. ; 3.1 Description of the Course and Data Sources -- 3.2 Instruments and Assessments -- 3.3 Predictive Model -- 4 Data Analysis and Results -- 5 Discussion -- 6 Conclusions, Limitations and Future Work of the Study -- References -- Youden's J and the Bi Error Method -- 1 Introduction -- 2 Methods -- 3 Results -- 4 Discussion -- 4.1 On the Choice of Hypothesized -- 4.2 Normal Distribution -- 4.3 F Distribution -- 5 Conclusion -- A Simulation Results -- References -- A New Proposal of Parametric Similarity Measures with Application in Decision Making -- 1 Introduction -- 2 Preliminaries and Generalization of Equality Index -- 3 Two Classes of Parametric Equality Indices -- 4 Parametric Similarity Measures for Fuzzy Vectors -- 4.1 Ordered Weighted Aggregation (OWA) Operators -- 4.2 A New Proposal -- 5 Application -- 6 Conclusions -- References -- The Challenges of Using Big Data in the Consumer Credit Sector -- 1 Introduction -- 2 Alternative Data in Credit Scoring -- 2.1 Psychometric Information -- 2.2 Social Networks -- 2.3 Peer-to-Peer Lending -- 3 Privacy and Ethics -- 3.1 Equifax Data Breach -- 3.2 Ethical Aspects of the Equifax Data Breach -- 4 Information Sharing -- 4.1 Regulations -- 4.2 Discrimination and Manipulation -- 5 Discussion -- References -- New Engine to Promote Big Data Industry Upgrade -- 1 Introduction -- 2 Big Data Industry Upgrade and Construction Goals and Key Breakthroughs -- 3 Realization of Big Data Industrialization -- 3.1 Industrialization Core Construction-"General Big Data Platform+" Model -- 3.2 Establish a Data Connection -- 3.3 The Realization Path of Big Data Industrialization -- 4 The Realization of the Big Data Industry Chain -- 4.1 Core Construction of the Industrial Chain -- 4.2 Framework and Map of the Industry Chain -- 4.3 The Transformation and Upgrading Path of the Industrial Chain -- 5 Conclusions and Prospects. ; References -- Using Correlation and Network Analysis for Researching Intellectual Competence -- 1 Introduction -- 1.1 Research Questions -- 1.2 Purpose of the Study -- 2 Study Participants -- 3 Research Methods -- 3.1 Methodology for Diagnosing Conceptual Abilities. "Conceptual Synthesis" [14] -- 3.2 Methods for Identifying Metacognitive Abilities -- 3.3 The Author's Method of Diagnostics of Intentional Abilities "Mood" -- 3.4 Author's Methodology for Assessing Intellectual Competence "Interpretation" -- 3.5 Research Techniques -- 4 Results -- 4.1 Correlation Analysis -- 4.2 Network Analysis -- 5 Findings -- 6 Conclusion -- 7 Future Work -- References -- A Disease Similarity Technique Using Biological Process Functional Annotations -- 1 Introduction -- 2 Background and Related Work -- 3 Methods and Techniques -- 3.1 Gene Ontology and Biological Process Annotations -- 3.2 Biological Process Jaccard Score -- 4 Evaluation and Results -- 4.1 Experiment 1 - Phenotype Jaccard Score and BP-Weight Correlation -- 4.2 Experiment 2 - Correlation Between Shared Chemicals and BP-Weight -- 4.3 Experiment 3 - Comparing Diseases Without Genes in Common -- 4.4 Experiment 4 - Correlation Between Shared Chemicals and BP-Weight for a Given Disease -- 4.5 Experiment 5 - Comparing Diseases with Genes in Common -- 4.6 Experiment 6 - Comparing Diseases with High BP-Weights -- 5 Analysis of Results and Discussion -- 6 Conclusion -- References -- Impact of Types of Change on Software Defect Prediction -- 1 Introduction -- 2 Related Work -- 3 Data Collection -- 3.1 Churn Data Extraction -- 3.2 Churn Metrics Construction -- 4 Experiments and Results -- 4.1 Experiment I -- 4.2 Experiment II -- 5 Conclusion -- References -- Analyzing Music Genre Popularity -- 1 Introduction -- 2 Related Work -- 3 Data Description and Collection -- 3.1 Gathering Data. ; 3.2 Cleaning and Formatting Data.
• Titolo autorizzato: Intelligent Computing
• ISBN: 3-030-80126-8
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9910491025303321
• Lo trovi qui: Univ. Federico II
• Serie: Lecture notes in networks and systems ; ; 284.