Data Analysis and Related Applications, Volume 1

Konstantinos N. Zafeiris is Associate Professor of Demography within the Department of History and Ethnology at the Democritus University of Thrace, Greece.Christos H. Skiadas was the Founder and Director of Data Analysis and Forecasting and Former Vice-Rector at the Technical University of Crete, Greece.Yiannis Dimotikalis is Assistant Professor of Quantitative Methods within the Department of Management Science and Technology at the Hellenic Mediterranean University, Greece.Alex Karagrigoriou is Professor of Probability and Statistics, Director of the Laboratory of Statistics and Data Analysis and Actuarial-Financial Mathematics at the University of the Aegean, Greece.Christiana Karagrigoriou-Vonta is a (socio) linguist, translator and subtitler. She works as a freelance translator and editor of scientific texts and provides postproduction services (subtitling) for private companies and broadcasting corporations.

• Preface xviiKonstantinos N. ZAFEIRIS, Yiannis DIMOTIKALIS, Christos H. SKIADAS, Alex KARAGRIGORIOU and Christiana KARAGRIGORIOU-VONTAPart 1 1Chapter 1. Performance of Evaluation of Diagnosis of Various Thyroid Diseases Using Machine Learning Techniques 3Burcu Bektas GÜNEŞ, Evren BURSUK and Rüya ŞAMLI1.1. Introduction 31.2. Data understanding 51.3. Modeling 61.4. Findings 81.5. Conclusion 101.6. References 10Chapter 2. Exploring Chronic Diseases’ Spatial Patterns: Thyroid Cancer in Sicilian Volcanic Areas 13Francesca BITONTI and Angelo MAZZA2.1. Introduction 142.2. Epidemiological data and territory 162.3. Methodology 182.3.1. Spatial inhomogeneity and spatial dependence 182.3.2. Standardized incidence ratio (SIR) 192.3.3. Local Moran’s I statistic 212.4. Spatial distribution of TC in eastern Sicily 222.4.1. SIR geographical variation 222.4.2. Estimate of the spatial attraction 242.5. Conclusion 252.6. References 26Chapter 3. Analysis of Blockchain-based Databases in Web Applications 31Orhun Ceng BOZO and Rüya ŞAMLI3.1. Introduction 313.2. Background 323.2.1. Blockchain 323.2.2. Blockchain types 323.2.3. Blockchain-based web applications 333.2.4. Blockchain consensus algorithms 333.2.5. Other consensus algorithms 343.3. Analysis stack 343.3.1. Art Shop web application 343.3.2. SQL-based application 343.3.3. NoSQL-based application 353.3.4. Blockchain-based application 353.4. Analysis 363.4.1. Adding records 363.4.2. Query 383.4.3. Functionality 393.4.4. Security 393.5. Conclusion 413.6. References 41Chapter 4. Optimization and Asymptotic Analysis of Insurance Models 43Ekaterina BULINSKAYA4.1. Introduction 434.2. Discrete-time model with reinsurance and bank loans 444.2.1. Model description 444.2.2. Optimization problem 454.2.3. Model stability 464.3. Continuous-time insurance model with dividends 484.3.1. Model description 484.3.2. Optimal barrier strategy 494.3.3. Special form of claim distribution 504.3.4. Numerical analysis 544.4. Conclusion and further research directions 554.5. References 56Chapter 5. Statistical Analysis of Traffic Volume in the 25 de Abril Bridge 57Frederico CAEIRO, Ayana MATEUS and Conceicao VEIGA de ALMEIDA5.1. Introduction 575.2. Data 585.3. Methodology 605.3.1. Main limit results 605.3.2. Block maxima method 615.3.3. Largest order statistics method 625.3.4. Estimation of other tail parameters 635.4. Results and conclusion 635.5. Acknowledgements 655.6. References 65Chapter 6. Predicting the Risk of Gestational Diabetes Mellitus through Nearest Neighbor Classification 67Louisa TESTA, Mark A. CARUANA, Maria KONTORINAKI and Charles SAVONA-VENTURA6.1. Introduction 676.2. Nearest neighbor methods 696.2.1. Background of the NN methods 696.2.2. The k-nearest neighbors method 706.2.3. The fixed-radius NN method 706.2.4. The kernel-NN method 716.2.5. Algorithms of the three considered NN methods 726.2.6. Parameter and distance metric selection 746.3. Experimental results 756.3.1. Dataset description 756.3.2. Variable selection and data splitting 756.3.3. Results 766.3.4. A discussion and comparison of results 786.4. Conclusion 796.5. References 79Chapter 7. Political Trust in National Institutions: The Significance of Items’ Level of Measurement in the Validation of Constructs 81Anastasia CHARALAMPI, Eva TSOUPAROPOULOU, Joanna TSIGANOU and Catherine MICHALOPOULOU7.1. Introduction 827.2. Methods 837.2.1. Participants 837.2.2. Instrument 847.2.3. Statistical analyses 857.3. Results 877.3.1. EFA results 877.3.2. CFA results 887.3.3. Scale construction and assessment 917.4. Conclusion 947.5. Funding 957.6. References 95Chapter 8. The State of the Art in Flexible Regression Models for Univariate Bounded Responses 99Agnese Maria DI BRISCO, Roberto ASCARI, Sonia MIGLIORATI and Andrea ONGARO8.1. Introduction 1008.2. Regression model for bounded responses 1018.2.1. Augmentation 1028.2.2. Main distributions on the bounded support 1038.2.3. Inference and fit 1068.3. Case studies 1078.3.1. Stress data 1078.3.2. Reading data 1108.4. References 112Chapter 9. Simulation Studies for a Special Mixture Regression Model with Multivariate Responses on the Simplex 115Agnese Maria DI BRISCO, Roberto ASCARI, Sonia MIGLIORATI and Andrea ONGARO9.1. Introduction 1159.2. Dirichlet and EFD distributions 1169.3. Dirichlet and EFD regression models 1189.3.1. Inference and fit 1189.4. Simulation studies 1199.4.1. Comments 1249.5. References 131Part 2 133Chapter 10. Numerical Studies of Implied Volatility Expansions Under the Gatheral Model 135Marko DIMITROV, Mohammed ALBUHAYRI, Ying NI and Anatoliy MALYARENKO10.1. Introduction 13510.2. Asymptotic expansions of implied volatility 13710.3. Performance of the asymptotic expansions 13910.4. Calibration using the asymptotic expansions 14110.4.1. A partial calibration procedure 14210.4.2. Calibration to synthetic and market data 14310.5. Conclusion and future work 14710.6. References 148Chapter 11. Performance Persistence of Polish Mutual Funds: Mobility Measures 149Dariusz FILIP11.1. Introduction 14911.2. Literature review 15011.3. Dataset and empirical design 15311.4. Empirical results 15511.5. Monthly perspective 15611.6. Quarterly perspective 15711.7. Yearly perspective 15811.8. Conclusion 15911.9. References 159Chapter 12. Invariant Description for a Batch Version of the UCB Strategy with Unknown Control Horizon 163Sergey GARBAR12.1. Introduction 16312.2. UCB strategy 16512.3. Batch version of the strategy 16512.4. Invariant description with a unit control horizon 16612.5. Simulation results 16912.6. Conclusion 17012.7. Affiliations 17112.8. References 171Chapter 13. A New Non-monotonic Link Function for Beta Regressions 173Gloria GHENO13.1. Introduction 17413.2. Model 17513.3. Estimation 17813.4. Comparison 17913.5. Conclusion 18413.6. References 184Chapter 14. A Method of Big Data Collection and Normalizatio nfor Electronic Engineering Applications 187Naveenbalaji GOWTHAMAN and Viranjay M. SRIVASTAVA14.1. Introduction 18714.2. Machine learning (ML) in electronic engineering 18914.2.1. Data acquisition 19014.2.2. Accessing the data repositories 19114.2.3. Data storage and management 19214.3. Electronic engineering applications – data science 19314.4. Conclusion and future work 19514.5. References 195Chapter 15. Stochastic Runge–Kutta Solvers Based on Markov Jump Processes and Applications to Non-autonomous Systems of Differential Equations 199Flavius GUIAŞ15.1. Introduction 19915.2. Description of the method 20115.2.1. The direct simulation method 20115.2.2. Picard iterations 20115.2.3. Runge–Kutta steps 20215.3. Numerical examples 20315.3.1. The Lorenz system 20315.3.2. A combustion model 20415.4. Conclusion 20615.5. References 206Chapter 16. Interpreting a Topological Measure of Complexity for Decision Boundaries 207Alan HYLTON, Ian LIM, Michael MOY and Robert SHORT16.1. Introduction 20716.2. Persistent homology 20916.3. Methodology 21316.3.1. Neural networks and binary classification 21316.3.2. Persistent homology of a decision boundary 21316.3.3. Procedure 21416.4. Experiments and results 21516.4.1. Three-dimensional binary classification 21516.4.2. Data divided by a hyperplane 21716.5. Conclusion and discussion 21916.6. References 220Chapter 17. The Minimum Renyi’s Pseudodistance Estimators for Generalized Linear Models 223María JAENADA and Leandro PARDO17.1. Introduction 22317.2. The minimum RP estimators for the GLM model: asymptotic distribution 22517.3. Example: Poisson regression model 23017.3.1. Real data application 23017.4. Conclusion 23217.5. Acknowledgments 23217.6. Appendix 23217.6.1. Proof of Theorem 1 23217.7. References 234Chapter 18. Data Analysis based on Entropies and Measures of Divergence 237Christos MESELIDIS, Alex KARAGRIGORIOU and Takis PAPAIOANNOU18.1. Introduction 23718.2. Divergence measures 23818.3. Tests of fit based on Φ−divergence measures 24118.4. Simulations 24618.5. References 254Part 3 259Chapter 19. Geographically Weighted Regression for Official Land Prices and their Temporal Variation in Tokyo 261Yuta KANNO and Takayuki SHIOHAMA19.1. Introduction 26119.2. Models and methodology 26319.3. Data analysis 26619.3.1. Data 26619.3.2. Results 26819.4. Conclusion 27219.5. Acknowledgments 27319.6. References 273Chapter 20. Software Cost Estimation Using Machine Learning Algorithms 275Sukran EBREN KARA and Rüya ŞAMLI20.1. Introduction 27520.2. Methodology 27620.2.1. Dataset 27620.2.2. Model 27720.2.3. Evaluating the performance of the model 27820.3. Results and discussion 27920.4. Conclusion 28220.5. References 283Chapter 21. Monte Carlo Accuracy Evaluation of Laser Cutting Machine 285Samuel KOSOLAPOV21.1. Introduction 28621.2. Mathematical model of a pintograph 28621.3. Monte Carlo simulator 29121.4. Simulation results 29421.5. Conclusion 29521.6. Acknowledgments 29521.7. References 295Chapter 22. Using Parameters of Piecewise Approximation by Exponents for Epidemiological Time Series Data Analysis 297Samuel KOSOLAPOV22.1. Introduction 29822.2. Deriving equations for moving exponent parameters 29822.3. Validation of derived equations by using synthetic data 30022.4. Using derived equations to analyze real-life Covid-19 data 30222.5. Conclusion 30522.6. References 306Chapter 23. The Correlation Between Oxygen Consumption and Excretion of Carbon Dioxide in the Human Respiratory Cycle 307Anatoly KOVALENKO, Konstantin LEBEDINSKII and Verangelina MOLOSHNEVA23.1. Introduction 30823.2. Respiratory function physiology: ventilation–perfusion ratio 30923.3. The basic principle of operation of artificial lung ventilation devices: patient monitoring parameters 31023.4. The algorithm for monitoring the carbon emissions and oxygen consumption 31223.5. Results 31423.6. Conclusion 31623.7. References 316Part 4 317Chapter 24. Approximate Bayesian Inference Using the Mean-Field Distribution 319Antonin DELLA NOCE and Paul-Henry COURNÈDE24.1. Introduction 31924.2. Inference problem in a symmetric population system 32124.2.1. Example of a symmetric system describing plant competition 32124.2.2. Inference problem of the Schneider system, in a more general setting 32324.3. Properties of the mean-field distribution 32524.4. Mean-field approximated inference 32724.4.1. Case of systems admitting a mean-field limit 32724.5. Conclusion 33024.6. References 330Chapter 25. Pricing Financial Derivatives in the Hull–White Model Using Cubature Methods on Wiener Space 333Hossein NOHROUZIAN, Anatoliy MALYARENKO and Ying NI25.1. Introduction and outline 33325.2. Cubature formulae on Wiener space 33525.2.1. A simple example of classical Monte Carlo estimates 33525.2.2. Modern Monte Carlo estimates via cubature method 33625.2.3. An application in the Black–Scholes SDE 33825.2.4. Trajectories of the cubature formula of degree 5 on Wiener space 33925.2.5. Trajectories of price process given in equation [25.7] 34025.2.6. An application on path-dependent derivatives 34125.2.7. Trinomial tree (model) via cubature formulae of degree 5 34225.3. Interest-rate models and Hull–White one-factor model 34325.3.1. Equilibrium models 34325.3.2. No-arbitrage models 34425.3.3. Forward rate models 34525.3.4. Hull–White one-factor model 34525.3.5. Discretization of the Hull–White model via Euler scheme 34625.3.6. Hull–White model for bond prices 34625.4. The Hull–White model via cubature method 34925.4.1. Simulating SDE [25.15] and ODE [25.24] 35025.4.2. The Hull–White interest-rate tree via iterated cubature formulae: some examples 35325.5. Discussion and future works 35425.6. References 355Chapter 26. Differences in the Structure of Infectious Morbidity of the Population during the First and Second Half of 2020 in St. Petersburg 359Vasilii OREL, Olga NOSYREVA, Tatiana BULDAKOVA, Natalya GUREVA, Viktoria SMIRNOVA, Andrey KIM and Lubov SHARAFUTDINOVA26.1. Introduction 36026.2. Materials and methods 36026.2.1. Characteristics of the territory of the district 36026.2.2. Demographic characteristics of the area 36026.2.3. Characteristics of the district medical service 36126.2.4. The procedure for collecting primary information on cases of diseases of the population with a new coronavirus infection 36126.3. Results of the analysis of the incidence of acute respiratory viral infectious diseases, new coronavirus infection Covid-19 and community-acquired pneumonia 36226.4. Conclusion 36726.5. References 368Chapter 27. High Speed and Secured Network Connectivity for Higher Education Institutions Using Software Defined Networks 371Lincoln S. PETER and Viranjay M. SRIVASTAVA27.1. Introduction 37227.2. Existing model review 37327.3. Selection of a suitable model 37427.4. Conclusion and future recommendations 37627.5. References 376Chapter 28. Reliability of a Double Redundant System Under the Full Repair Scenario 379Vladimir RYKOV and Nika IVANOVA28.1. Introduction 37928.2. Problem statement, assumptions and notations 38128.3. Reliability function 38428.4. Time-dependent system state probabilities 38628.4.1. General representation of t.d.s.p.s 38628.4.2. T.d.s.p.s in a separate regeneration period 38728.5. Steady-state probabilities 39228.6. Conclusion 39328.7. References 393Chapter 29. Predicting Changes in Depression Levels Following the European Economic Downturn of 2008 395Eleni SERAFETINIDOU and Georgia VERROPOULOU29.1. Introduction 39629.1.1. Aims of the study 39829.2. Data and methods 39829.2.1. Sample 39829.2.2. Measures 39829.3. Results 40029.3.1. Descriptive findings 40029.3.2. Non-respondents compared to respondents at baseline (wave 2) 40329.3.3. Descriptive findings for respondents – analysis by gender 40529.3.4. Findings regarding decreasing depression levels – analysis for the total sample and by gender 40829.3.5. Findings regarding increasing depression levels – analysis for the total sample and by gender 41029.4. Discussion 41329.5. Conclusion 41429.6. Acknowledgments 41529.7. References 415List of Authors 419Index 425Summary of Volume 2 429