Uso da análise multivariada para caracterização de comunidades infestantes em cana-soca

Pós-graduação em Agronomia (Produção Vegetal) - FCAV

Exigências de lisina e de metionina+cistina digestíveis para aves de corte da linhagem ISA Label em sistemas semi-confinado

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Utilização de técnicas de análise de agrupamento do risco de geada no Estado do Paraná para a cultura do milho safrinha

Pós-graduação em Agronomia (Energia na Agricultura) - FCA

Perfil geográfico multivariado da água consumida no município de Botucatu

Pós-graduação em Biometria - IBB

Comparing label free electrochemical impedimetric and capacitive biosensing architectures

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

Establishing erosion susceptibility: analytical hierarchical process and traditional approaches

This study evaluated alternatives for producing erosion susceptibility maps, considering different weight combinations for an environment's attributes, according to four different points of views. The attributes considered were landform, steepness, soils, rocks and land occupation. Considered alternatives were: (1) equal weights, more traditional approach, (2) different weights, according to a previous study in the area, (3) different weights, based on other works in the literature, and (4) different weights based on the analytical hierarchical process. The area studied included the Prosa Basin located in Campo Grande-Mato Grosso do Sul State, Brazil. The results showed that the assessed alternatives can be used together or in different stages of studies aiming at urban planning and decision-making on the interventions to be applied.

Multivariate analysis of the temporal variability of sugarcane ripening in south-eastern Brazil

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Label-free Capacitive Diagnostics: Exploiting Local Redox Probe State Occupancy

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

A path- and label-cost propagation approach to speedup the training of the optimum-path forest classifier

In general, pattern recognition techniques require a high computational burden for learning the discriminating functions that are responsible to separate samples from distinct classes. As such, there are several studies that make effort to employ machine learning algorithms in the context of big data classification problems. The research on this area ranges from Graphics Processing Units-based implementations to mathematical optimizations, being the main drawback of the former approaches to be dependent on the graphic video card. Here, we propose an architecture-independent optimization approach for the optimum-path forest (OPF) classifier, that is designed using a theoretical formulation that relates the minimum spanning tree with the minimum spanning forest generated by the OPF over the training dataset. The experiments have shown that the approach proposed can be faster than the traditional one in five public datasets, being also as accurate as the original OPF. (C) 2014 Elsevier B. V. All rights reserved.

Static Video Summarization through Optimum-Path Forest Clustering

This paper introduces the Optimum-Path Forest (OPF) classifier for static video summarization, being its results comparable to the ones obtained by some state-of-the-art video summarization techniques. The experimental section has been conducted using several image descriptors in two public datasets, followed by an analysis of OPF robustness regarding one ad-hoc parameter. Future works are guided to improve OPF effectiveness on each distinct video category.

Pseudechis guttatus venom proteome: Insights into evolution and toxin clustering

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Automatic visual dictionary generation through optimum-path forest clusteringautomatic visual dictionary generation through optimum-path forest clustering

Image categorization by means of bag of visual words has received increasing attention by the image processing and vision communities in the last years. In these approaches, each image is represented by invariant points of interest which are mapped to a Hilbert Space representing a visual dictionary which aims at comprising the most discriminative features in a set of images. Notwithstanding, the main problem of such approaches is to find a compact and representative dictionary. Finding such representative dictionary automatically with no user intervention is an even more difficult task. In this paper, we propose a method to automatically find such dictionary by employing a recent developed graph-based clustering algorithm called Optimum-Path Forest, which does not make any assumption about the visual dictionary's size and is more efficient and effective than the state-of-the-art techniques used for dictionary generation.

Análise de propriedades topológicas das redes biológicas integradas da Escherichia coli e da Saccharomyces cerevisiae

Biological processes are complex and possess emergent properties that can not be explained or predict by reductionism methods. To overcome the limitations of reductionism, researchers have been used a group of methods known as systems biology, a new interdisciplinary eld of study aiming to understand the non-linear interactions among components embedded in biological processes. These interactions can be represented by a mathematical object called graph or network, where the elements are represented by nodes and the interactions by edges that link pair of nodes. The networks can be classi- ed according to their topologies: if node degrees follow a Poisson distribution in a given network, i.e. most nodes have approximately the same number of links, this is a random network; if node degrees follow a power-law distribution in a given network, i.e. small number of high-degree nodes and high number of low-degree nodes, this is a scale-free network. Moreover, networks can be classi ed as hierarchical or non-hierarchical. In this study, we analised Escherichia coli and Saccharomyces cerevisiae integrated molecular networks, which have protein-protein interaction, metabolic and transcriptional regulation interactions. By using computational methods, such as MathematicaR , and data collected from public databases, we calculated four topological parameters: the degree distribution P(k), the clustering coe cient C(k), the closeness centrality CC(k) and the betweenness centrality CB(k). P(k) is a function that calculates the total number of nodes with k degree connection and is used to classify the network as random or scale-free. C(k) shows if a network is hierarchical, i.e. if the clusterization coe cient depends on node degree. CC(k) is an indicator of how much a node it is in the lesse way among others some nodes of the network and the CB(k) is a pointer of how a particular node is among several ...(Complete abstract click electronic access below)

Particle competition and cooperation for semi-supervised learning with label noise

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