Lauro de Paula

Universidade Federal de Goiás, Institute of Informatics, Graduate Student

Pontifícia Universidade Católica de Goiás, Departamento de Computação, Alumnus

Followers

269

Following

487

Co-authors

Public Views

Lauro is BSc in Computer Science with emphasis in Computational Mathematics from Pontifical Catholic University of Goiás, Brazil (2012), and MSc in Computer Science from Federal University of Goiás - UFG, Brazil (2014). Currently, Lauro is a PhD Student in Computer Science at Federal University of Mato Grosso do Sul in association with UFG (2015-2018). He is also a Research Scientist, professor at a few universities, reviewer and editorial board member of national and international journals, and member of research groups.

Lauro is an eternal apprentice who is always seeking for new personal and professional challenges. Nowadays, he is willing to become a Data Scientist in some multinational company. Thus, he is starting the Post-Graduation course in Big Data and Machine Learning at Sul-Americana College - FASAM, Brazil (2017-2018).

In the last five years, Lauro published important scientific papers in international conferences as well as in international journals with relevant impact factor. Lauro has achieved important awards of excellence in scientific research. He has interest in problems and applications mainly involving: scientific computing, parallel computing, evolutionary algorithms, bioinspired metaheuristics for feature selection, Big Data and machine learning.

Talk to me: [email protected]
Address: Brazil

less

Anderson Soares

Mário César Ugulino de Araújo

UFPB - Universidade Federal da Paraíba

Mario Araujo

UFPB - Universidade Federal da Paraíba

PUC Goiás

University of Tennessee Knoxville

Abdul Rohman

Jamshid Piri

University of Zabol

InterestsView All (30)

Uploads

Papers by Lauro de Paula

Variable Selection as a Non-Completely Decomposable Problem: A Case Study in Multivariate Calibration

Proceedings of the Genetic and Evolutionary Computation Conference Companion, 2017

Variable selection is a procedure used to choose a subset of features in order to extract informa... more Variable selection is a procedure used to choose a subset of features in order to extract information from them. It has been widely used in multivariate calibration together with statistical techniques to build a model from which it is possible to be interpreted by users. Genetic algorithms (GAs) have been successfully utilized as a variable selection method in multivariate calibration models. However, GAs solve a problem by trying diierent decompositions, and the variable selection problem usually can not be properly decomposed when there is considerable correlation among variables. Consequently , GAs tend to lead to a poor variable selection performance if the variables interdepence is strong. is work comes from a doctoral thesis, which is still in development and aims to (not only) demonstrate that selecting variables in multivariate calibration is a non-completely decomposable problem. Based on the preliminary results, we are able to claim the viability of our initial hypothesis.

Lauro de Paula

Uploads

Papers by Lauro de Paula

Log In