Análise de formas planas em imagens digitais

Given the widespread use of computers, the visual pattern recognition task has been automated in order to address the huge amount of available digital images. Many applications use image processing techniques as well as feature extraction and visual pattern recognition algorithms in order to identify people, to make the disease diagnosis process easier, to classify objects, etc. based on digital images. Among the features that can be extracted and analyzed from images is the shape of objects or regions. In some cases, shape is the unique feature that can be extracted with a relatively high accuracy from the image. In this work we present some of most important shape analysis methods and compare their performance when applied on three well-known shape image databases. Finally, we propose the development of a new shape descriptor based on the Hough Transform.

Avanços da informática em enfermagem no Brasil: revisão integrativa

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Análise do descritor de padrões mapeados localmente em multiescala para classificação de textura em imagens digitais

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Integrated biomarker responses as environmental status descriptors of a coastal zone (Sao Paulo, Brazil)

Sao Paulo state (Brazil) has one of the most overpopulated coastal zones in South America, where previous studies have already detected sediment and water contamination. However, biological-based monitoring considering signals of xenobiotic exposure and effects are scarce. The present study employed a battery of biomarkers under field conditions to assess the environmental quality of this coastal zone. For this purpose, the activity of CYP 450, antioxidant enzymes, DNA damage, lipid peroxidation and lysosomal membrane were analysed in caged mussels and integrated using Factorial Analysis. A representation of estimated factor scores was performed in order to confirm the factor descriptions characterizing the studied areas. Biomarker responses indicated signals of mussels` impaired health during the monitoring, which pointed to the impact of different sources of contaminants in the water quality and identified critical areas. This integrated approach produced a rapid, sensitive and cost-effective assessment, which could be incorporated as a descriptor of environmental status in future coastal zones biomonitoring. (C) 2011 Elsevier Inc. All rights reserved.

Self-Organizing Maps of Molecular Descriptors for Sesquiterpene Lactones and Their Application to the Chemotaxonomy of the Asteraceae Family

The Asteraceae, one of the largest families among angiosperms, is chemically characterised by the production of sesquiterpene lactones (SLs). A total of 1,111 SLs, which were extracted from 658 species, 161 genera, 63 subtribes and 15 tribes of Asteraceae, were represented and registered in two dimensions in the SISTEMATX, an in-house software system, and were associated with their botanical sources. The respective 11 block of descriptors: Constitutional, Functional groups, BCUT, Atom-centred, 2D autocorrelations, Topological, Geometrical, RDF, 3D-MoRSE, GETAWAY and WHIM were used as input data to separate the botanical occurrences through self-organising maps. Maps that were generated with each descriptor divided the Asteraceae tribes, with total index values between 66.7% and 83.6%. The analysis of the results shows evident similarities among the Heliantheae, Helenieae and Eupatorieae tribes as well as between the Anthemideae and Inuleae tribes. Those observations are in agreement with systematic classifications that were proposed by Bremer, which use mainly morphological and molecular data, therefore chemical markers partially corroborate with these classifications. The results demonstrate that the atom-centred and RDF descriptors can be used as a tool for taxonomic classification in low hierarchical levels, such as tribes. Descriptors obtained through fragments or by the two-dimensional representation of the SL structures were sufficient to obtain significant results, and better results were not achieved by using descriptors derived from three-dimensional representations of SLs. Such models based on physico-chemical properties can project new design SLs, similar structures from literature or even unreported structures in two-dimensional chemical space. Therefore, the generated SOMs can predict the most probable tribe where a biologically active molecule can be found according Bremer classification.

Diet of Astyanax paranae (Characidae) in streams with different riparian land covers in the Passa-Cinco River basin, southeastern Brazil

An analysis of the diet of Astyanax paranae Eigenmann, 1914 in nine streams located in the Passa-Cinco River basin (upper Parana River system) was performed to investigate the feeding habits of this species, check for possible spatial variations in diet and to investigate the influence of riparian vegetation in the composition of the diet. Stomach contents of 243 specimens were analyzed by the methods of relative frequency of occurrence and volume, and the diet was characterized by the alimentary index (AI(i)). The species showed insectivorous feeding habits, with a predominance of terrestrial and aquatic insects in the diet, varying by location. In most streams, resources of allochthonous origin were the most consumed. The participation of aquatic insects and terrestrial plants were high in most streams, while terrestrial insects and invertebrates were highest in streams with a greater presence of riparian forest. The two streams located draining pasture fields were the only places were A. paranae consumed algae and macrophyte fragments. These results were corroborated by the analysis of similarity (ANOSIM): the descriptor "percentage of riparian forest" was the highest environmental influence on the diet of A. paranae. The study shows that riparian forest percentage on the stream reach determines the species diet composition, but A. paranae is also able to gather enough food resources in a variety of severely degraded environments.

Evolution of Body Elongation in Gymnophthalmid Lizards: Relationships with Climate

The evolution of elongated body shapes in vertebrates has intrigued biologists for decades and is particularly recurrent among squamates. Several aspects might explain how the environment influences the evolution of body elongation, but climate needs to be incorporated in this scenario to evaluate how it contributes to morphological evolution. Climatic parameters include temperature and precipitation, two variables that likely influence environmental characteristics, including soil texture and substrate coverage, which may define the selective pressures acting during the evolution of morphology. Due to development of geographic information system (GIS) techniques, these variables can now be included in evolutionary biology studies and were used in the present study to test for associations between variation in body shape and climate in the tropical lizard family Gymnophthalmidae. We first investigated how the morphological traits that define body shape are correlated in these lizards and then tested for associations between a descriptor of body elongation and climate. Our analyses revealed that the evolution of body elongation in Gymnophthalmidae involved concomitant changes in different morphological traits: trunk elongation was coupled with limb shortening and a reduction in body diameter, and the gradual variation along this axis was illustrated by less-elongated morphologies exhibiting shorter trunks and longer limbs. The variation identified in Gymnophthalmidae body shape was associated with climate, with the species from more arid environments usually being more elongated. Aridity is associated with high temperatures and low precipitation, which affect additional environmental features, including the habitat structure. This feature may influence the evolution of body shape because contrasting environments likely impose distinct demands for organismal performance in several activities, such as locomotion and thermoregulation. The present study establishes a connection between morphology and a broader natural component, climate, and introduces new questions about the spatial distribution of morphological variation among squamates.

Ligand- and Structure-Based Drug Design Strategies and PPAR delta/alpha Selectivity

Peroxisome-proliferator-activated receptors are a class of nuclear receptors with three subtypes: a, ? and d. Their main function is regulating gene transcription related to lipid and carbohydrate metabolism. Currently, there are no peroxisome-proliferator-activated receptors d drugs being marketed. In this work, we studied a data set of 70 compounds with a and d activity. Three partial least square models were created, and molecular docking studies were performed to understand the main reasons for peroxisome-proliferator-activated receptors d selectivity. The obtained results showed that some molecular descriptors (log P, hydration energy, steric and polar properties) are related to the main interactions that can direct ligands to a particular peroxisome-proliferator-activated receptors subtype.

Central poststroke pain: somatosensory abnormalities and the presence of associated myofascial pain syndrome

Background: Central post-stroke pain (CPSP) is a neuropathic pain syndrome associated with somatosensory abnormalities due to central nervous system lesion following a cerebrovascular insult. Post-stroke pain (PSP) refers to a broader range of clinical conditions leading to pain after stroke, but not restricted to CPSP, including other types of pain such as myofascial pain syndrome (MPS), painful shoulder, lumbar and dorsal pain, complex regional pain syndrome, and spasticity-related pain. Despite its recognition as part of the general PSP diagnostic possibilities, the prevalence of MPS has never been characterized in patients with CPSP patients. We performed a cross-sectional standardized clinical and radiological evaluation of patients with definite CPSP in order to assess the presence of other non-neuropathic pain syndromes, and in particular, the role of myofascial pain syndrome in these patients. Methods: CPSP patients underwent a standardized sensory and motor neurological evaluation, and were classified according to stroke mechanism, neurological deficits, presence and profile of MPS. The Visual Analogic Scale (VAS), McGill Pain Questionnaire (MPQ), and Beck Depression Scale (BDS) were filled out by all participants. Results: Forty CPSP patients were included. Thirty-six (90.0%) had one single ischemic stroke. Pain presented during the first three months after stroke in 75.0%. Median pain intensity was 10 (5 to 10). There was no difference in pain intensity among the different lesion site groups. Neuropathic pain was continuous-ongoing in 34 (85.0%) patients and intermittent in the remainder. Burning was the most common descriptor (70%). Main aggravating factors were contact to cold (62.5%). Thermo-sensory abnormalities were universal. MPS was diagnosed in 27 (67.5%) patients and was more common in the supratentorial extra-thalamic group (P <0.001). No significant differences were observed among the different stroke location groups and pain questionnaires and scales scores. Importantly, CPSP patients with and without MPS did not differ in pain intensity (VAS), MPQ or BDS scores. Conclusions: The presence of MPS is not an exception after stroke and may present in association with CPSP as a common comorbid condition. Further studies are necessary to clarify the role of MPS in CPSP.

A comparative study on multiscale fractal dimension descriptors

Fractal theory presents a large number of applications to image and signal analysis. Although the fractal dimension can be used as an image object descriptor, a multiscale approach, such as multiscale fractal dimension (MFD), increases the amount of information extracted from an object. MFD provides a curve which describes object complexity along the scale. However, this curve presents much redundant information, which could be discarded without loss in performance. Thus, it is necessary the use of a descriptor technique to analyze this curve and also to reduce the dimensionality of these data by selecting its meaningful descriptors. This paper shows a comparative study among different techniques for MFD descriptors generation. It compares the use of well-known and state-of-the-art descriptors, such as Fourier, Wavelet, Polynomial Approximation (PA), Functional Data Analysis (FDA), Principal Component Analysis (PCA), Symbolic Aggregate Approximation (SAX), kernel PCA, Independent Component Analysis (ICA), geometrical and statistical features. The descriptors are evaluated in a classification experiment using Linear Discriminant Analysis over the descriptors computed from MFD curves from two data sets: generic shapes and rotated fish contours. Results indicate that PCA, FDA, PA and Wavelet Approximation provide the best MFD descriptors for recognition and classification tasks. (C) 2012 Elsevier B.V. All rights reserved.

Changes in phytoplankton composition in response to tides, wind-induced mixing conditions, and freshwater outflows in an urbanised estuarine complex

Recent reports have shown an increase in potentially harmful phytoplankton in Santos bay (Southeastern Brazilian Coast), located in a highly urbanised estuarine complex. Prediction of blooms is, thus, essential but the phytoplankton community structure in very dynamic regions is difficult to determine. In the present work, we discriminate bloom forming microphytoplankton dominance and their relationship to physical and meteorological variables to look for patterns observed in different tides and seasons. Comparing 8 distinct situations, we found five scenarios of dominance that could be related to winds, tides and rainfall: i) Surfers, diatoms occurring during high surf zone energies; ii) Sinkers, represented by larger celled diatoms during spring tide, after periods of high precipitation rates; iii) Opportunistic mixers, composed of chain forming diatoms with small or elongate cells occurring during neap tides; iv) Local mixers, microplanktonic diatoms and dinoflagellates which occurred throughout the 298 sampling stations; and v) Mixotrophic dinoflagellates, after intense estuarine discharges. Results suggest alterations in the temporal patterns for some bloom-forming species, while others appeared in abundances above safe limits for public health. This approach can also illustrate possible impacts of changes in freshwater discharge in highly urbanised estuaries.

Texture analysis by multi-resolution fractal descriptors

This work proposes a novel texture descriptor based on fractal theory. The method is based on the Bouligand- Minkowski descriptors. We decompose the original image recursively into four equal parts. In each recursion step, we estimate the average and the deviation of the Bouligand-Minkowski descriptors computed over each part. Thus, we extract entropy features from both average and deviation. The proposed descriptors are provided by concatenating such measures. The method is tested in a classification experiment under well known datasets, that is, Brodatz and Vistex. The results demonstrate that the novel technique achieves better results than classical and state-of-the-art texture descriptors, such as Local Binary Patterns, Gabor-wavelets and co-occurrence matrix.

Autenticación de personas a partir de la biometría de la región dígito palmar

[ES] En este artículo se presenta un sistema novedoso para la autenticación automática de personas basado en un indicador biométrico de la mano: la huella de la región dígito palmar. La imagen de los pliegues de la base del dedo índice se ha tomado con una cámara digital comercial. Dichas imágenes han sido digitalmente procesadas con el fin de realzar las colinas y valles de los pliegues de la piel. Estas líneas son seguidas para establecer los puntos de bifurcación y término denominados minucias, los cuales forman el descriptor de la huella dígito palmar. Un clasificador basado en un umbral y el coeficiente de correlación de Pearson verifica si una nueva huella pertenece a la identidad reclamada. Los resultados obtenidos muestran una confianza superior al 98% trabajando con 38 personas entre las cuales se incluyen huellas de baja calidad.

Clustering of variables around latent components: an application in consumer science

The present work proposes a method based on CLV (Clustering around Latent Variables) for identifying groups of consumers in L-shape data. This kind of datastructure is very common in consumer studies where a panel of consumers is asked to assess the global liking of a certain number of products and then, preference scores are arranged in a two-way table Y. External information on both products (physicalchemical description or sensory attributes) and consumers (socio-demographic background, purchase behaviours or consumption habits) may be available in a row descriptor matrix X and in a column descriptor matrix Z respectively. The aim of this method is to automatically provide a consumer segmentation where all the three matrices play an active role in the classification, getting homogeneous groups from all points of view: preference, products and consumer characteristics. The proposed clustering method is illustrated on data from preference studies on food products: juices based on berry fruits and traditional cheeses from Trentino. The hedonic ratings given by the consumer panel on the products under study were explained with respect to the product chemical compounds, sensory evaluation and consumer socio-demographic information, purchase behaviour and consumption habits.

Evaluation of LBP and HOG descriptors for clothing attribute description

[EN]In this work an experimental study about the capability of the LBP, HOG descriptors and color for clothing attribute classification is presented. Two different variants of the LBP descriptor are considered, the original LBP and the uniform LBP. Two classifiers, Linear SVM and Random Forest, have been included in the comparison because they have been frequently used in clothing attributes classification. The experiments are carried out with a public available dataset, the clothing attribute dataset, that has 26 attributes in total. The obtained accuracies are over 75% in most cases, reaching 80% for the necktie or sleeve length attributes.