Gustavo Teodoro Laureano

Multi-objective evolutionary algorithm for variable selection in calibration problems: A case study for protein concentration prediction

This paper presents a multi-objective formulation for variable selection in calibration problems. The prediction of protein concentration on wheat is obtained by a linear regression model using variables obtained by a spectrophotometer device. This device measure hundreds of correlated variables related with physicochemical properties and that can be used to estimate the protein concentration. The problem is the selection of a subset informative and uncorrelated variables that help the minimization of prediction error. In this work we propose the use of two objectives in this problem: the prediction error and the number of variables in the model, both related to linear equations system stability. We proposed a multi-objective formulation using two multi-objective algorithms: the NSGA-II and the SPEA-II. Additionally we propose a final decision maker method to choice the final subset of variables from the Pareto front. For the case study is used wheat data obtained by NIR spectrometry where the objective is the determination of a variable subgroup with information about protein concentration. The results of traditional techniques of multivariate calibration as the Successive Projections Algorithm (SPA), Partial Least Square (PLS) and mono-objective genetic algorithm are presents for comparisons. For NIR spectral analysis of protein concentration on wheat, the number of variables selected from 775 spectral variables was reduced for just 10 in the SPEA-II algorithm. The prediction error decreased from 0.2 in the classical methods to 0.09 in proposed approach, a reduction of 45%. The model using variables selected by SPEA-II had better prediction performance than classical algorithms and full-spectrum partial least-squares (PLS).

A New Approach to Detect Use of Alcohol Through Iris Videos Using Computer Vision

In all modern society the increase in alcohol consumption has caused many problems and the potential harmful effects of alcohol on human health are known. There are some ways to identify alcohol in a person, but they are invasive and embarrassing for people. This work proposes a new non-invasive and simple test to detect use of alcohol through of pupillary reflex analysis. The initial results present rates near 85% in the correct identification using algorithms for pattern recognition, demonstrating the efficacy of the test method.

A topological approach for detection of chessboard patterns for camera calibration

Abstract This work aims to automatically identify chessboard patterns for camera calibration. The method uses a fast x-shaped corner detector and a geometric mesh to represent the relative association between features. The mesh allows considering the regularity of the chessboard pattern and a topological filter is presented. The matching between real world points and their image projections is done using neighboring properties in a filtered mesh. The point location is locally updated to the subpixel precision with a specific x-corner detector. The calibration points are determined even when the pattern is partially occluded. The experiments show that the proposed algorithm provides a robust detection of the chessboard patterns and take great advantage of image frames. The method is applicable for both online and off-line detection of chessboard patterns.

Hybrid Genetic-Fuzzy Algorithm for Variable Selection in Spectroscopy

This paper presents a hybrid multi-objective genetic fuzzy algorithm for the variable-selection problem in spectroscopy. The problem formulation considers three fitness functions related to linear equations system stability. These fitness functions are models with fuzzy sets that evaluate the fitness solution for pick out the best to crossover. The population diversity is obtained applying the crowding distance method. The study shows that the selection by a fuzzy decision has better results than the selection by non-domination in problems where the fitness weighing is more proper than no-domination solutions.