http://emap.fgv.br/linhas-de-pesquisa#934Data ScienceEduardo Fonseca Mendes, Flávio Codeço Coelho, Jorge Poco, Moacyr Alvim Horta Barbosa da Silva, Renato Rocha Souza, Rodrigo dos Santos Targino, Yuri Fahham Saporito
The objective of this line of research is the exploration and development of objects and research problems through methods originated from the statistical learning of machines (Machine Learning) and its applications in the analysis of structured and unstructured data. This range of empirical objects encompasses numerical, categorical and textual data, images, graphs, time series, among others. It also includes the development of algorithms, languages and methodologies for manipulating these complex databases, in tasks such as classification, regression, learning, identification of clusters, recommendation systems, optimization, extraction and representation of knowledge, modeling knowledge domains, data mining, text mining, visualization, sentiment analysis, high-dimensional data analysis, cryptography.
Publicações recentesAutoaritra Dasgupta, Jorge Poco, Bernice Rogowitz, Kyungsik Han, Enrico Bertini, Claudio T. Silva. The Effect Of Color Scales On Climate Scientists’ Objective And Subjective Performance In Spatial Data Analysis Tasks. IEEE Transactions On Visualization And Computer Graphics, 2020.Germain Garcia, Jaqueline Silveira, Jorge Poco, Afonso Paiva, Marcelo Batista Nery, Claudio T. Silva, Sergio Adorno, Luis Gustavo Nonato. Crimanalyzer: Understanding Crime Patterns In São Paulo. IEEE Transactions On Visualization And Computer Graphics, 2020.Maxime Lenormand, Horacio Samaniego, Júlio César Chaves, Vinícius da Fonseca Vieira, Moacyr Alvim Horta Barbosa da Silva, Alexandre Gonçalves Evsukoff. Entropy As A Measure Of Attractiveness And Socioeconomic Complexity In Rio De Janeiro Metropolitan Area. Entropy, 22, 2020.Maurício Barcellos Almeida, Renato Rocha Souza, L. M. O. Machado. What Researchers Are Currently Saying About Ontologies: A Review Of Recent Web Of Science Articles.. Knowledge Organization, 47, 2020.
http://emap.fgv.br/linhas-de-pesquisa#935Control and OptimizationMaría Soledad Aronna, Roger Behling, Vincent Gérard Yannick Guigues
The Optimal Control Theory studies Optimization problems whose state variables are subject to differential equations (ordinary or partial) whose dynamics depend on a control variable, while Stochastic Optimization is focused on the study of optimization problems involving uncertainties modeled by a stochastic process. A stochastic optimization problem is usually formulated using conditional risk measures.
Publicações recentesFranco Rampazzo, Monica Motta, M. Soledad Aronna. A Higher-order Maximum Principle For Impulsive Optimal Control Problems. SIAM Journal On Control And Optimization, 58, 2020.R. Behling, L. R. Santos, J. Y. Bello Cruz. On The Circumcentered-reflection Method For The Convex Feasibility Problem. Numerical Algorithms, 1, 2020.María Soledad Aronna, J. F. Bonnans, A. Kröner. Optimal Control of PDEs in a Complex Space Setting: Application to the Schrödinger Equation. SIAM Journal On Control And Optimization, 57, 2019.Roger Behling, A. Fischer, K. Schönefeld, N. Strasdat. A Special complementarity function revisited. Optimization, 68, 2019.
http://emap.fgv.br/linhas-de-pesquisa#936EpidemiologyClaudio José Struchiner, Eduardo Massad, Flávio Codeço Coelho, María Soledad Aronna, Moacyr Alvim Horta Barbosa da Silva
Mathematical epidemiology is an applied mathematics subject with more than a century of tradition, which incorporates ideas and methods from different branches of mathematics in the representation and analysis of its objects of study.
At EMAp, the Mathematical Epidemiology group studies how information on how communicable diseases can be treated from a quantitative point of view, differently from the classic statistical techniques well known in the medical field. In addition, the projects require a basic understanding of biological assumptions and the mathematical models that underlie infection models and the tools available today to extract biological information from these models.
Publicações recentesJessica Gliozzo, Paolo Perlasca, Marco Mesiti, Elena Casiraghi, Viviana Vallacchi, Elisabetta Vergani, Marco Frasca, Giuliano Grossi, Alessandro Petrini, Matteo Re, Alberto Paccanaro, Giorgio Valentini. Network Modeling Of Patients' Biomolecular Profiles For Clinical Phenotype/outcome Prediction. Scientific Reports, 10, 2020.Joanna C. Dawes, Philip Webster, Barbara Iadarola, Claudia Garcia Diaz, Marian Dore, Bruce J. Bolt, Hamlata Dewchand, Gopuraja Dharmalingam, Alex P. Mclatchie, Jakub Kaczor, Juan J. Caceres, Alberto Paccanaro, Laurence Game, Simona Parrinello, Anthony G. Uren. LUMI-PCR: An Illumina Platform Ligation-mediated Pcr Protocol For Integration Site Cloning, Provides Molecular Quantitation Of Integration Sites. Mobile DNA, 11, 2020.Ana Kurauchi, C. J. Struchiner, Annelies Wilder-smith, E. Massad. Modelling The Effect Of A Dengue Vaccine On Reducing The Evolution Of Resistance Against Antibiotic Due To Misuse In Dengue Cases. Theoretical Biology And Medical Modelling, 17, 2020.Weeberb J. Requia, Edson Kenji Kondo, Matthew D. Adams, Diane R. Gold, Claudio José Struchiner. Risk Of The Brazilian Health Care System Over 5572 Municipalities To Exceed Health Care Capacity Due To The 2019 Novel Coronavirus (Covid-19). Science Of The Total Environment, 730, 2020.
http://emap.fgv.br/linhas-de-pesquisa#944StatisticsClaudio José Struchiner, Eduardo Fonseca Mendes, Flávio Codeço Coelho, Rodrigo dos Santos Targino, Vincent Gérard Yannick Guigues
In general, this line of research is divided into theoretical, methodological and applied aspects involving data analysis. In particular, EMAp researchers are interested in the following areas of Statistics: Estimation of time series in high dimension; Modeling of non-linear time series; Non-parametric tests; Monte Carlo simulation for Bayesian inference; Statistical inference for risk-averse or neutral risk stochastic optimization problems (central limit theorems, hypothesis tests, non-asymptotic confidence intervals); Nonparametric hypothesis testing using convex optimization techniques.
Publicações recentesMilan Merkle, Yuri Fahham Saporito, Rodrigo dos Santos Targino. Bayesian approach for parameter estimation of continuous-time stochastic volatility models using Fourier transform methods. Statistics & Probability Letters, 156, 2020.Eduardo Mendes, Christopher K. Carter, David Gunawan, Robert Kohn. A Flexible Particle Markov Chain Monte Carlo method. Statistics And Computing, 2020.
http://emap.fgv.br/linhas-de-pesquisa#945Finance and RiskEduardo Fonseca Mendes, Flávio Codeço Coelho, Hugo A. de la Cruz Cancino, Rodrigo dos Santos Targino, Vincent Gérard Yannick Guigues, Yuri Fahham Saporito
In this line of research, mathematical models and methods are studied with a focus on applications in problems of Finance, Economics and Actuarial Sciences. For applications in Finance and Economics, research projects are usually based on techniques involving Stochastic Calculation and/or Partial Differential Equations, whereas applications in Actuarial Sciences, such as Reserves calculation, tend to use statistical regression models or time series.
Publicações recentesMilan Merkle, Yuri Fahham Saporito, Rodrigo dos Santos Targino. Bayesian approach for parameter estimation of continuous-time stochastic volatility models using Fourier transform methods. Statistics & Probability Letters, 156, 2020.Yuri Fahham Saporito, X. Yang, J. P. Zubelli. The calibration of stochastic local-volatility models: An inverse problem perspective. Computers and Mathematics with Applications, 77, 2019.
http://emap.fgv.br/linhas-de-pesquisa#946Stochastic ModelsHugo A. de la Cruz Cancino, Yuri Fahham Saporito
This line of research began worldwide with the development of Probability and the formal construction of the Brownian Movement in the early 20th century. This is probably one of the areas of mathematics with the most applications in the real world. From a theoretical point of view, we are interested in the study of Stochastic Differential Equations and the incorporation of path-dependence in several aspects of the theory.
In addition, another aspect of this line is the numerical resolution of differential equations, in particular random (RDEs) and stochastic (EDEs). The theory of EDEs and RDEs are themes, at the crossroads of differential equations and stochastic processes, with a wide variety of applications in the modeling of phenomena and practical situations in which the quantities of interest are subject to random disturbances. Since obtaining solutions to these equations is rarely possible, much attention is paid to the construction and study of approximation methods, with good qualitative properties, for their integration and simulation.
Publicações recentesHugo de la Cruz, Jimenez, J. C. Exact Pathwise Simulation Of Multi-dimensional Ornstein-Uhlenbeck Processes. Journal Of Computational and Applied Mathematics, 366, 2020.J. C. Jimenez, Hugo de la Cruz, P. A. de Maio. Efficient Computation Of Phi-functions In Exponential Integrators. Journal Of Computational and Applied Mathematics, 2758, 2020.Hugo de la Cruz. Stabilized explicit methods for the approximation of stochastic systems driven by small additive noises. Chaos, Solitons & Fractals,140, 2020.Yuri Fahham Saporito. Stochastic Control and Differential Games with Path-Dependent Influence of Controls on Dynamics and Running Cost. SIAM Journal on Control and Optimization, 57, 2019.