Fast non-technical losses identification through Optimum-Path Forest

Fraud detection in energy systems by illegal consumers is the most actively pursued study in non-technical losses by electric power companies. Commonly used supervised pattern recognition techniques, such as Artificial Neural Networks and Support Vector Machines have been applied for automatic commercial frauds identification, however they suffer from slow convergence and high computational burden. We introduced here the Optimum-Path Forest classifier for a fast non-technical losses recognition, which has been demonstrated to be superior than neural networks and similar to Support Vector Machines, but much faster. Comparisons among these classifiers are also presented. © 2009 IEEE.

Parkinson's disease identification through Optimum-Path Forest

Artificial intelligence techniques have been extensively used for the identification of several disorders related with the voice signal analysis, such as Parkinson's disease (PD). However, some of these techniques flaw by assuming some separability in the original feature space or even so in the one induced by a kernel mapping. In this paper we propose the PD automatic recognition by means of Optimum-Path Forest (OPF), which is a new recently developed pattern recognition technique that does not assume any shape/separability of the classes/feature space. The experiments showed that OPF outperformed Support Vector Machines, Artificial Neural Networks and other commonly used supervised classification techniques for PD identification. © 2010 IEEE.

Improving Parkinson's disease identification through evolutionary-based feature selection

Parkinson's disease (PD) automatic identification has been actively pursued over several works in the literature. In this paper, we deal with this problem by applying evolutionary-based techniques in order to find the subset of features that maximize the accuracy of the Optimum-Path Forest (OPF) classifier. The reason for the choice of this classifier relies on its fast training phase, given that each possible solution to be optimized is guided by the OPF accuracy. We also show results that improved other ones recently obtained in the context of PD automatic identification. © 2011 IEEE.

Genetic identification of lamniform and carcharhiniform sharks using multiplex-PCR

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Histochemical technique for the detection of chloride cells in fish

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Análise de polimorfismos da região controle do dna mitocondrial em indivíduos nascidos e residentes no estado do espírito santo para utilização na identificação humana

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Biomobile: sistema de identificação de usuários em dispositivos móveis na plataforma Android utilizando reconhecimento de faces a partir de vídeo

Pós-graduação em Ciência da Computação - IBILCE

A temática ambiental e o ensino de biologia: o professor enquanto sujeito ecológico

Pós-graduação em Educação - IBRC

Caracterização estrutural e das interações entre a Proteína G do hRSV e potenciais inibidores

Pós-graduação em Microbiologia - IBILCE

Determinação do território de forrageamento e avaliação do uso de micro porta-iscas para as saúvas Atta sexdens rubropilosa Forel, 1908 e Atta laevigata Fr. Smith, 1858 (Hymenoptera, Formicidae)

Pós-graduação em Agronomia (Proteção de Plantas) - FCA

Reconhecimento semiautomático de dentes para a identificação humana forense

Pós-graduação em Ciência da Computação - IBILCE

Análise de SNPs do DNA mitocondrial em indivíduos residentes no estado do Espírito Santo para aplicação na Identificação Humana

Pós-graduação em Biotecnologia - IQ

Caracterização da distribuição física dos dolomitos do membro Búzios no Campo de Badejo - Bacia de Campos

In the region of Badejo oil Ffeld (Campos Basin) lies an Lower Albian dolomitic layer that shows reservoir rock and seal conditions, among others and, it is occasionally karstified. This work applies geostatistical techniques of ordinary and indicatior kriging, in an attempt to determine a method that assists the analysis of different scenarios offered for petroleum drilling from a quantitative point of view this fact is justified, because there are different visions and strategies that would be adopted under different dolomite conditions (stable - low porosity and high density; reservoir - high porosity and medium density; instable - high porosity and low dentisty). The main objective is a methodological introduction that has not been tested in dolomites before aiming to characterize the distribution of the three conditions described above by ordinary and indicatior kriging, which was based on the obtained data from the dolomite layer identification through well logs interpretation and correlation, followed by seismic interpretation. In addition, it was generated structural contour maps, based on 2D and 3D seismic data interpretation, and then, seismic attributes maps were calculated, in order to transform them into pseudo-density maps, i.e., maps that correlate the density values with the attribute values. As primary results, structural contour maps and seismic attributes were obtained and ordinary and indicatior kriging maps were done, on which it is possible to interpret the distribution of the main reservoir and risk probability for drilling of exploration wells obtaining trends N35E and N10W direction for areas of stability or reservoir levels, while the central part of the map presents a higher risk for loss of drilling fluid. The cut-off values levels were based on the values of first and third quartiles of cumulative histogram (instable and stable zones, respectively), as well as the reservoir level was set as the interval...

Identification of Mechanical Systems through Kautz Filter

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Identification of sexually dimorphic gene expression in brain tissue of the fish Leporinus macrocephalus through mRNA differential display and real time PCR analyses

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)