An environment for knowledge discovery in biology

This paper describes a data mining environment for knowledge discovery in bioinformatics applications. The system has a generic kernel that implements the mining functions to be applied to input primary databases, with a warehouse architecture, of biomedical information. Both supervised and unsupervised classification can be implemented within the kernel and applied to data extracted from the primary database, with the results being suitably stored in a complex object database for knowledge discovery. The kernel also includes a specific high-performance library that allows designing and applying the mining functions in parallel machines. The experimental results obtained by the application of the kernel functions are reported. © 2003 Elsevier Ltd. All rights reserved.

Toward Satellite-Based Land Cover Classification Through Optimum-Path Forest

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

Estimation of croplands using indicator kriging and fuzzy classification

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Mapping soil pollution by spatial analysis and fuzzy classification

Spatial analysis and fuzzy classification techniques were used to estimate the spatial distributions of heavy metals in soil. The work was applied to soils in a coastal region that is characterized by intense urban occupation and large numbers of different industries. Concentrations of heavy metals were determined using geostatistical techniques and classes of risk were defined using fuzzy classification. The resulting prediction mappings identify the locations of high concentrations of Pb, Zn, Ni, and Cu in topsoils of the study area. The maps show that areas of high pollution of Ni and Cu are located at the northeast, where there is a predominance of industrial and agricultural activities; Pb and Zn also occur in high concentrations in the northeast, but the maps also show significant concentrations of Pb and Zn in other areas, mainly in the central and southeastern parts, where there are urban leisure activities and trade centers. Maps were also prepared showing levels of pollution risk. These maps show that (1) Cu presents a large pollution risk in the north-northwest, midwest, and southeast sectors, (2) Pb represents a moderate risk in most areas, (3) Zn generally exhibits low risk, and (4) Ni represents either low risk or no risk in the studied area. This study shows that combining geostatistics with fuzzy theory can provide results that offer insight into risk assessment for environmental pollution.

A REAPPRAISAL OF GENERIC AND SUBGENERIC CLASSIFICATION IN THE BATRACHOSPERMACEAE (RHODOPHYTA)

The generic and subgeneric classification of the family Batrachospermaceae (Rhodophyta) has long been recognized as ambiguous and often inconsistent. One of the prime features used to delineate sections of Batrachospermum, trichogyne shape, is variable even within given species. However, characters associated with the carposporophyte and the carpogonial branch, as well as carpogonial symmetry, are practical and consistent taxonomic criteria. These features have been used to redefine sectional delineation in Batrachospermum. Based on phylogenetic reasoning and practicality, it is proposed that the three genera Nothocladus, Sirodotia and Tuomeya be reduced to sectional level within Batrachospermum. The genus Batrachospermum would thus become the sole member of the Batrachospermaceae and would include two subgenera, Batrachospermum and Acarposporophytum, the former with nine clearly defined sections (Aristata, Batrachospermum, Contorta, Hybrida, Nothocladus (Skuja) stat. nov., Sirodotia (Kylin) stat. nov., Tuomeya (Harvey) stat. nov., Turficola and Viridia). As a result, the following nomenclatural changes are proposed: Batrachospermum lindaueri (Skuja) comb. nov., B. nodosum (Skuja) comb. nov., B. delicatulum (Skuja) comb. nov., B. fennicum (Skuja) comb. nov., B. suecicum (Kylin) comb. nov. and B. americanum (Kutzing) comb. nov.

Proliferating cell nuclear antigen (PCNA) in non-Hodgkin's lymphomas: Correlation with working formulation and Kiel classification in formalin-fixed paraffin-embedded material

PCNA is a 36-KD proliferating cell nuclear antigen associated with the cell cycle. The immunocytochemical detection of PCNA represents a useful tool for the study of tumor proliferation activity. This study documents the detection of PCNA, using antibody PC 10 in formalin-fixed, paraffin-embedded tissue, and correlates the proliferative activity of the non-Hodgkin's lymphomas (NHL) with histological grading assessed by the International Working Formulation (WF) and Kiel classification. In 92 cases of NHLs we found a strong correlation between the PCNA index and lymphoma grading. Statistically significant differences were also found between the proliferative index (PI) in low and high grade lymphomas according to the Kiel classification (t = 9.519; p < 0.001) and between low, intermediate and high grade lymphomas according to the WF classification (F = 79.01; p < 0.001). In the Kiel classification the mean of low grade lymphomas was 39.5% and of high grade 75.7%. In the WF the average of low grade lymphomas was 29.7%, intermediate 53.1% and high 75.1%. Although the differences among the groups had been significant, we found variations inside each histological subgroup in both classifications. The intermediate lymphomas were the most heterogeneous group, with PI inside the same histologic subtypes coincident with low and high grade lymphomas. Since PCNA may be used as a marker of cell proliferation in clinical studies to estimate the biological aggressiveness of lymphomas, its determination in intermediate grade NHL could be very useful to evaluate individual cases in this group and determine prognosis and probably the appropriate therapy.

Malware distributed collection and pre-classification system using honeypot technology

Malware has become a major threat in the last years due to the ease of spread through the Internet. Malware detection has become difficult with the use of compression, polymorphic methods and techniques to detect and disable security software. Those and other obfuscation techniques pose a problem for detection and classification schemes that analyze malware behavior. In this paper we propose a distributed architecture to improve malware collection using different honeypot technologies to increase the variety of malware collected. We also present a daemon tool developed to grab malware distributed through spam and a pre-classification technique that uses antivirus technology to separate malware in generic classes. © 2009 SPIE.

Delineation of specific management areas for coffee cultivation based on the soil-relief relationship and numerical classification

Predicting and mapping productivity areas allows crop producers to improve their planning of agricultural activities. The primary aims of this work were the identification and mapping of specific management areas allowing coffee bean quality to be predicted from soil attributes and their relationships to relief. The study area was located in the Southeast of the Minas Gerais state, Brazil. A grid containing a total of 145 uniformly spaced nodes 50 m apart was established over an area of 31. 7 ha from which samples were collected at depths of 0. 00-0. 20 m in order to determine physical and chemical attributes of the soil. These data were analysed in conjunction with plant attributes including production, proportion of beans retained by different sieves and drink quality. The results of principal component analysis (PCA) in combination with geostatistical data showed the attributes clay content and available iron to be the best choices for identifying four crop production environments. Environment A, which exhibited high clay and available iron contents, and low pH and base saturation, was that providing the highest yield (30. 4l ha-1) and best coffee beverage quality (61 sacks ha-1). Based on the results, we believe that multivariate analysis, geostatistics and the soil-relief relationships contained in the digital elevation model (DEM) can be effectively used in combination for the hybrid mapping of areas of varying suitability for coffee production. © 2012 Springer Science+Business Media New York.

Identification of Candida Spp. In Patients with Denture Stomatitis: Relationship with Gender, Age, Time of Denture use and Newton’s Classification

Epidemiological researches are important to understand the distribution and etiology of oral diseases. The actual researches that show the relationship between patient ages, denture status and denture stomatitis are scarce. So, the aim of this study was to identify of Candida spp. in patients with Denture Stomatitis (DS) and to correlate with gender, age, time of denture use and Newton’s classification. 204 complete denture patients (46 males and 158 females) were selected. DS was classified according to Newton’s classification and it was related to gender, age and time of denture use. Samples from the palatal mucosa and the surface of the upper denture of patients with DS were evaluated using PCR test for identification of Candida species. T-test, chisquare and Fisher’s exact tests were used for statistical analysis. DS was evidenced in 54.4% of the sample. According to gender 41.3% of the males and 58.3% females had the disease and the differences were statistically significant (p = 0.032). The type of DS was directly influenced by the time of denture use (p<0.001), but it was not significantly related to the age of the participants (p>0.05). C. albicans, C. tropicalis, C. glabrata, C. krusei and C. dubliniensis were identified by PCR test. DS is more prevalent in women and the prevalence of DS was influenced by the time of denture use (years). C. albicans was identified as the most frequent specie in patients with DS.

Semi-supervised learning for relevance feedback on image retrieval tasks

Relevance feedback approaches have been established as an important tool for interactive search, enabling users to express their needs. However, in view of the growth of multimedia collections available, the user efforts required by these methods tend to increase as well, demanding approaches for reducing the need of user interactions. In this context, this paper proposes a semi-supervised learning algorithm for relevance feedback to be used in image retrieval tasks. The proposed semi-supervised algorithm aims at using both supervised and unsupervised approaches simultaneously. While a supervised step is performed using the information collected from the user feedback, an unsupervised step exploits the intrinsic dataset structure, which is represented in terms of ranked lists of images. Several experiments were conducted for different image retrieval tasks involving shape, color, and texture descriptors and different datasets. The proposed approach was also evaluated on multimodal retrieval tasks, considering visual and textual descriptors. Experimental results demonstrate the effectiveness of the proposed approach.

Calcários albianos de campo petrolífero na Bacia de Campos: fácies, diagênese e modelo deposicional

Pós-graduação em Geologia Regional - IGCE

Algoritmos de aprendizado semi-supervisionado baseados em grafos aplicados na bioinformática

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

Signal classification of submerged aquatic vegetation based on the hemispherical-conical reflectance factor spectrum shape in the yellow and red regions

The water column overlying the submerged aquatic vegetation (SAV) canopy presents difficulties when using remote sensing images for mapping such vegetation. Inherent and apparent water optical properties and its optically active components, which are commonly present in natural waters, in addition to the water column height over the canopy, and plant characteristics are some of the factors that affect the signal from SAV mainly due to its strong energy absorption in the near-infrared. By considering these interferences, a hypothesis was developed that the vegetation signal is better conserved and less absorbed by the water column in certain intervals of the visible region of the spectrum; as a consequence, it is possible to distinguish the SAV signal. To distinguish the signal from SAV, two types of classification approaches were selected. Both of these methods consider the hemispherical-conical reflectance factor (HCRF) spectrum shape, although one type was supervised and the other one was not. The first method adopts cluster analysis and uses the parameters of the band (absorption, asymmetry, height and width) obtained by continuum removal as the input of the classification. The spectral angle mapper (SAM) was adopted as the supervised classification approach. Both approaches tested different wavelength intervals in the visible and near-infrared spectra. It was demonstrated that the 585 to 685-nm interval, corresponding to the green, yellow and red wavelength bands, offered the best results in both classification approaches. However, SAM classification showed better results relative to cluster analysis and correctly separated all spectral curves with or without SAV. Based on this research, it can be concluded that it is possible to discriminate areas with and without SAV using remote sensing. © 2013 by the authors; licensee MDPI, Basel, Switzerland.

Land use image classification through optimum-path forest clustering

Land use classification has been paramount in the last years, since we can identify illegal land use and also to monitor deforesting areas. Although one can find several research works in the literature that address this problem, we propose here the land use recognition by means of Optimum-Path Forest Clustering (OPF), which has never been applied to this context up to date. Experiments among Optimum-Path Forest, Mean Shift and K-Means demonstrated the robustness of OPF for automatic land use classification of images obtained by CBERS-2B and Ikonos-2 satellites. © 2011 IEEE.

Geoestística e sensoriamento remoto na classificação de imagens em áreas cultivadas com citros

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)