Oropharyngeal dysphagia identification using wavelets and optimum path forest

The swallowing disturbers are defined as oropharyngeal dysphagia when present specifies signals and symptoms that are characterized for alterations in any phases of swallowing. Early diagnosis is crucial for the prognosis of patients with dysphagia and the potential to diagnose dysphagia in a noninvasive manner by assessing the sounds of swallowing is a highly attractive option for the dysphagia clinician. This study proposes a new framework for oropharyngeal dysphagia identification, having two main contributions: a new set of features extract from swallowing signal by discrete wavelet transform and the dysphagia classification by a novel pattern classifier called OPF. We also employed the well known SVM algorithm in the dysphagia identification task, for comparison purposes. We performed the experiments in two sub-signals: the first was the moment of the maximal peak (MP) of the signal and the second is the swallowing apnea period (SAP). The OPF final accuracy obtained were 85.2% and 80.2% for the analyzed signals MP and SAP, respectively, outperforming the SVM results. ©2008 IEEE.

Performance evaluation of the fuzzy ARTMAP for network intrusion detection

Recently, considerable research work have been conducted towards finding fast and accurate pattern classifiers for training Intrusion Detection Systems (IDSs). This paper proposes using the so called Fuzzy ARTMAT classifier to detect intrusions in computer network. Our investigation shows, through simulations, how efficient such a classifier can be when used as the learning mechanism of a typical IDS. The promising evaluation results in terms of both detection accuracy and training duration indicate that the Fuzzy ARTMAP is indeed viable for this sort of application.

Análise de técnicas de reconhecimento de padrões para a identificação biométrica de usuários em aplicações WEB Utilizando faces a partir de vídeos

Pós-graduação em Ciência da Computação - IBILCE

Pattern recognition theory in nonlinear signal processing

A body of research has developed within the context of nonlinear signal and image processing that deals with the automatic, statistical design of digital window-based filters. Based on pairs of ideal and observed signals, a filter is designed in an effort to minimize the error between the ideal and filtered signals. The goodness of an optimal filter depends on the relation between the ideal and observed signals, but the goodness of a designed filter also depends on the amount of sample data from which it is designed. In order to lessen the design cost, a filter is often chosen from a given class of filters, thereby constraining the optimization and increasing the error of the optimal filter. To a great extent, the problem of filter design concerns striking the correct balance between the degree of constraint and the design cost. From a different perspective and in a different context, the problem of constraint versus sample size has been a major focus of study within the theory of pattern recognition. This paper discusses the design problem for nonlinear signal processing, shows how the issue naturally transitions into pattern recognition, and then provides a review of salient related pattern-recognition theory. In particular, it discusses classification rules, constrained classification, the Vapnik-Chervonenkis theory, and implications of that theory for morphological classifiers and neural networks. The paper closes by discussing some design approaches developed for nonlinear signal processing, and how the nature of these naturally lead to a decomposition of the error of a designed filter into a sum of the following components: the Bayes error of the unconstrained optimal filter, the cost of constraint, the cost of reducing complexity by compressing the original signal distribution, the design cost, and the contribution of prior knowledge to a decrease in the error. The main purpose of the paper is to present fundamental principles of pattern recognition theory within the framework of active research in nonlinear signal processing.

Optimization of neural classifiers based on bayesian decision boundaries and idle neurons pruning

In this article we describe a feature extraction algorithm for pattern classification based on Bayesian Decision Boundaries and Pruning techniques. The proposed method is capable of optimizing MLP neural classifiers by retaining those neurons in the hidden layer that realy contribute to correct classification. Also in this article we proposed a method which defines a plausible number of neurons in the hidden layer based on the stem-and-leaf graphics of training samples. Experimental investigation reveals the efficiency of the proposed method. © 2002 IEEE.

A Markov random field model for combining optimum-path forest classifiers using decision graphs and game strategy approach

The research on multiple classifiers systems includes the creation of an ensemble of classifiers and the proper combination of the decisions. In order to combine the decisions given by classifiers, methods related to fixed rules and decision templates are often used. Therefore, the influence and relationship between classifier decisions are often not considered in the combination schemes. In this paper we propose a framework to combine classifiers using a decision graph under a random field model and a game strategy approach to obtain the final decision. The results of combining Optimum-Path Forest (OPF) classifiers using the proposed model are reported, obtaining good performance in experiments using simulated and real data sets. The results encourage the combination of OPF ensembles and the framework to design multiple classifier systems. © 2011 Springer-Verlag.

Applying machine learning based on multiscale classifiers to detect remote phenology patterns in Cerrado savanna trees

Plant phenology is one of the most reliable indicators of species responses to global climate change, motivating the development of new technologies for phenological monitoring. Digital cameras or near remote systems have been efficiently applied as multi-channel imaging sensors, where leaf color information is extracted from the RGB (Red, Green, and Blue) color channels, and the changes in green levels are used to infer leafing patterns of plant species. In this scenario, texture information is a great ally for image analysis that has been little used in phenology studies. We monitored leaf-changing patterns of Cerrado savanna vegetation by taking daily digital images. We extract RGB channels from the digital images and correlate them with phenological changes. Additionally, we benefit from the inclusion of textural metrics for quantifying spatial heterogeneity. Our first goals are: (1) to test if color change information is able to characterize the phenological pattern of a group of species; (2) to test if the temporal variation in image texture is useful to distinguish plant species; and (3) to test if individuals from the same species may be automatically identified using digital images. In this paper, we present a machine learning approach based on multiscale classifiers to detect phenological patterns in the digital images. Our results indicate that: (1) extreme hours (morning and afternoon) are the best for identifying plant species; (2) different plant species present a different behavior with respect to the color change information; and (3) texture variation along temporal images is promising information for capturing phenological patterns. Based on those results, we suggest that individuals from the same species and functional group might be identified using digital images, and introduce a new tool to help phenology experts in the identification of new individuals from the same species in the image and their location on the ground. © 2013 Elsevier B.V. All rights reserved.

Rank Aggregation for Pattern Classifier Selection in Remote Sensing Images

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Longitudinal distribution and lateral pattern of megalopal settlement and juvenile recruitment of Carcinus maenas (L.) (Brachyura, Portunidae) in the Mira River Estuary, Portugal

Settlement is a critical process in the life history of crabs, and thus affecting the abundance, distribution and structure of estuarine communities. The spatial pattern of settlement of megalopae of the shore crab Carcinus maenas along a longitudinal estuarine gradient (Mira River Estuary, Portugal) was examined, as well as its effects on the juvenile population. To measure megalopal settlement, four replicate collectors were deployed in six equally spaced stations along the estuarine axis. Juveniles were collected on the same locations with a quadrat randomly deployed on the substrate. To assess fine-scale megalopal settlement within a curved region of the estuary, replicate collectors were deployed on both margins along Moinho da Asneira curve. Megalopae settled differently along the six longitudinal points, with a tendency to attenuate their settlement upstream. Within the curved region, megalopae preferentially settled on the left margin collectors, probably due to the weaker velocity speeds felt on this margin. Concerning the overall juvenile density, there were significant differences among the stations distributed along the estuary, but they did no reflect a longitudinal dispersion attenuation pattern. Size-frequency distribution of the juvenile population showed that the average size is higher on the left margin. Recruits (carapace length between 1.0 mm and 3.4 mm) were more abundant on the upstream stations. Density of early juveniles (3.4 mm-6.5 mm) and juveniles (6.5 mm-10 mm) was more stable throughout the estuary axis than that of recruits. This distribution pattern may result from tidal excursion processes or mechanisms to avoid biotic interactions, such as predation and competition. (c) 2006 Elsevier Ltd. All rights reserved.

Determination of the highest no-effect dose (HNED) and of the elimination pattern for cocaine in horses

Cocaine is one of the most widespread illegal stimulants utilized by the human population throughout the world. The aim of this study was to establish the highest no-effect dose (HNED) of cocaine on the spontaneous locomotor activity (SLA) of horses in a behavior chamber, and thereby to determine the maximal acceptable threshold of the urinary drug concentration in horses. Twelve English thoroughbred mares received 0.02, 0.03, 0.04, 0.08 or 0.12 mg kg(-1) cocaine i.v. or saline solution (control). It was noted that doses above 0.04 mg kg(-1) induced a significant increase in SLA (P < 0.05, Tukey's test). No significant increase in SLA was seen in the mares that received 0.03 mg kg(-1), but the animals showed important behavioral changes that did not occur after the 0.02 mg kg(-1) dose. It was concluded that the HNED of cocaine for horses in a behavior chamber is 0.02 mg kg(-1). After injection of this dose in five horses, urine samples were collected at predetermined intervals through vesical catheterization. The concentrations of cocaine, norcocaine, benzoylecgonine and ecgonine methyl ester were quantified by liquid chromatography/electrospray ionization tandem mass spectrometry. Cocaine and norcocaine concentrations remained consistently below the level of detection. Benzoylecgonine reached a mean (+/- SEM) maximum concentration of 531.9 +/- 168.7 ng ml(-1) after 4 h, whereas ecgonine methyl ester peaked 2 h after injection at a concentration of 97.2 +/- 26.5 ng ml(-1). The maximum admissible concentration for cocaine and/or metabolites in the urine of horses is difficult to establish unequivocally because of the substantial individual variation in the drug elimination pattern observed in horses, which can be inferred by the large standard error of the means obtained. Copyright (C) 2002 John Wiley Sons, Ltd.

Annual pattern of plasma melatonin and progesterone concentrations in hair and wool ewe lambs kept under natural photoperiod at lower latitudes in the southern hemisphere

To study the annual pattern of plasma melatonin and progesterone concentrations in hair [Santa Ines (SI)] and wool [Romney Marsh (RM) and Suffolk (SU)] ewe lambs kept under natural photoperiods at 21 degrees 59'S, 12 ewe lambs (four/breed) were used. For melatonin, blood samples were collected monthly throughout the year at the onset (17:00, 19:00 and 21:00 hr) and end (04:00, 06:00 and 08:00 hr) of the night, and for progesterone the samples were collected in the morning, two to three times a week throughout the year. Plasma melatonin concentrations at different times of the day changed according to the season. In diurnal periods (17:00 and 8:00 hr) no seasonal differences were observed but they became evident in the nocturnal intervals (21:00 and 4:00 hr) and transitional night-day (6:00 hr) times. The patterns of melatonin secretion were higher in winter and autumn than in spring and summer. The patterns of plasma progesterone secretion were affected by interaction between breed and season. There was no seasonal variation in plasma progesterone concentrations for SI females. The progesterone pattern for RM and SU females varied with season. The plasma levels were higher in autumn and winter than in spring and summer. At 21 degrees 59'S hair and wool ewe lambs showed the same annual pattern of plasma melatonin concentration while the annual progesterone profiles were quite different. For SI females this pattern was constant along all seasons and for RM and SU females this pattern was higher during autumn and winter than spring and summer.

The breathing pattern and the ventilatory response to aquatic and aerial hypoxia and hypercarbia in the frog Pipa carvalhoi

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

Immune response pattern of the popliteal lymph nodes of dogs with visceral leishmaniasis

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

Soil sampling intensity and spatial distribution pattern of soils attributes and corn yield in no-tillage system

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

Postharvest changes and respiratory pattern of bacuri fruit (Platonia insignis Mart.) at different maturity stages during ambient storage

O bacuri (Platonia insignis, Mart.) é um dos mais importantes entre os frutos da Amazônia. Todavia, pouco se sabe sobre sua fisiologia pós-colheita, bem como, estádio de maturação, mudanças durante o armazenamento sob condições ambientais e padrão respiratório. Os frutos foram colhidos em três estádios de maturação baseados na coloração do epicarpo: verde-escuro, verde-claro e de vez (50% amarelo), com o objetivo de se determinar as modificações de coloração e padrão respiratório durante armazenamento sob condições de ambiente (25,2 ºC, 75,1 % UR). Os frutos de todos os estádios de maturação apresentaram, a partir do terceiro dia de colheita, comportamento respiratório não climatérico, com os frutos de vez apresentando maior taxa de produção de CO2 até o quarto dia de armazenamento (177,63 mg CO2.kg-1.h-1). O amarelecimento aumentou durante o armazenamento e foi relacionado com a diminuição da luminosidade (L), cromaticidade e ângulo hue. Os frutos de vez podem ser armazenados sob condições de ambiente por até 10 dias sem nenhuma perda da qualidade comercial.