Particle competition and cooperation to prevent error propagation from mislabeled data in semi-supervised learning

Semi-supervised learning is applied to classification problems where only a small portion of the data items is labeled. In these cases, the reliability of the labels is a crucial factor, because mislabeled items may propagate wrong labels to a large portion or even the entire data set. This paper aims to address this problem by presenting a graph-based (network-based) semi-supervised learning method, specifically designed to handle data sets with mislabeled samples. The method uses teams of walking particles, with competitive and cooperative behavior, for label propagation in the network constructed from the input data set. The proposed model is nature-inspired and it incorporates some features to make it robust to a considerable amount of mislabeled data items. Computer simulations show the performance of the method in the presence of different percentage of mislabeled data, in networks of different sizes and average node degree. Importantly, these simulations reveals the existence of the critical points of the mislabeled subset size, below which the network is free of wrong label contamination, but above which the mislabeled samples start to propagate their labels to the rest of the network. Moreover, numerical comparisons have been made among the proposed method and other representative graph-based semi-supervised learning methods using both artificial and real-world data sets. Interestingly, the proposed method has increasing better performance than the others as the percentage of mislabeled samples is getting larger. © 2012 IEEE.

BBA: A binary bat algorithm for feature selection

Feature selection aims to find the most important information from a given set of features. As this task can be seen as an optimization problem, the combinatorial growth of the possible solutions may be in-viable for a exhaustive search. In this paper we propose a new nature-inspired feature selection technique based on the bats behaviour, which has never been applied to this context so far. The wrapper approach combines the power of exploration of the bats together with the speed of the Optimum-Path Forest classifier to find the set of features that maximizes the accuracy in a validating set. Experiments conducted in five public datasets have demonstrated that the proposed approach can outperform some well-known swarm-based techniques. © 2012 IEEE.

Improving image classification through descriptor combination

The efficiency in image classification tasks can be improved using combined information provided by several sources, such as shape, color, and texture visual properties. Although many works proposed to combine different feature vectors, we model the descriptor combination as an optimization problem to be addressed by evolutionary-based techniques, which compute distances between samples that maximize their separability in the feature space. The robustness of the proposed technique is assessed by the Optimum-Path Forest classifier. Experiments showed that the proposed methodology can outperform individual information provided by single descriptors in well-known public datasets. © 2012 IEEE.

Suíte plutônica Alumiador, grupo Amonguijá, maciço rio apa - MS

The Rio Apa Massif corresponds the southern portion of the Amazon Craton and is located in the southwest of Mato Grosso do Sul State. It consists on Paleoproterozoic rocks of Rio Apa Complex, Alto Tererê Group and Amonguijá Group, is subdivided into Alumiador Plutonic Suite and Serra da Bocaina Volcanic Suite. The volcanic suite is comprises sub volcanic, volcanic and varied volcanoclastics rocks with composition ranging from alkali-rhyolitic to rhyolite types. The plutonic suite corresponds to an N-S elongated batholith and is characterized by four main segments delimited by NW-SE faults. The southern and central main segments, discussed in this paper, are characterized by the following petrographic facies: medium to fine grained hornblende-biotite monzogranites, coarse grained biotite monzogranites, graphic biotite sienogranites and muscovite sienogranites and the northern segment is contemporaneous and is composed of two different sequences of rocks, one acid and another of basic to ultrabasic composition. The southern and central segment consists of to chemically compatible rocks with the types I and A Granites. These are calc-alkaline rocks of high potassium to the shoshonitic and subalkaline. Constitute sin-collisional granites of metaluminous the peraluminous characters of the Amonguijá Magmatic Arc, but they exhibit late litotypes with chemical characteristics of post tectonic granites from intraplate environment.

Determination of disease biomarkers in Eucalyptus by comprehensive two-dimensional gas chromatography and multivariate data analysis

In this paper is reported the use of the chromatographic profiles of volatiles to determine disease markers in plants - in this case, leaves of Eucalyptus globulus contaminated by the necrotroph fungus Teratosphaeria nubilosa. The volatile fraction was isolated by headspace solid phase microextraction (HS-SPME) and analyzed by comprehensive two-dimensional gas chromatography-fast quadrupole mass spectrometry (GC. ×. GC-qMS). For the correlation between the metabolic profile described by the chromatograms and the presence of the infection, unfolded-partial least squares discriminant analysis (U-PLS-DA) with orthogonal signal correction (OSC) were employed. The proposed method was checked to be independent of factors such as the age of the harvested plants. The manipulation of the mathematical model obtained also resulted in graphic representations similar to real chromatograms, which allowed the tentative identification of more than 40 compounds potentially useful as disease biomarkers for this plant/pathogen pair. The proposed methodology can be considered as highly reliable, since the diagnosis is based on the whole chromatographic profile rather than in the detection of a single analyte. © 2013 Elsevier B.V..

Fuzzy community structure detection by particle competition and cooperation

Identification and classification of overlapping nodes in networks are important topics in data mining. In this paper, a network-based (graph-based) semi-supervised learning method is proposed. It is based on competition and cooperation among walking particles in a network to uncover overlapping nodes by generating continuous-valued outputs (soft labels), corresponding to the levels of membership from the nodes to each of the communities. Moreover, the proposed method can be applied to detect overlapping data items in a data set of general form, such as a vector-based data set, once it is transformed to a network. Usually, label propagation involves risks of error amplification. In order to avoid this problem, the proposed method offers a mechanism to identify outliers among the labeled data items, and consequently prevents error propagation from such outliers. Computer simulations carried out for synthetic and real-world data sets provide a numeric quantification of the performance of the method. © 2012 Springer-Verlag.

The use of elevation map histograms for topographic heterogeneity analysis

Surface defects are extremely important in mechanical characterization of several different materials. Therefore, the analysis of surface finishing is essential for a further simulation of surface mechanical properties in a customized project in materials science and technology. One of the methods commonly employed for such purpose is the statistical mapping of different sample surface regions using the depth from focus technique. The analysis is usually performed directly from the elevation maps which are obtained from the digital image processing. In this paper, the possibility of quantifying the surface heterogeneity of Silicon Carbide porous ceramics by elevation map histograms is presented. The advantage of this technique is that it allows the qualitative or quantitative verification of all surface image fields that cannot be done by using the Surface Plot plugin of image J™ platform commonly used in digital image processing. © 2012 Springer Science+Business Media, LLC.

Temporomandibular joint condylar changes following maxillomandibular advancement and articular disc repositioning

Purpose To evaluate condylar changes 1 year after bimaxillary surgical advancement with or without articular disc repositioning using longitudinal quantitative measurements in 3-dimensional (3D) temporomandibular joint (TMJ) models. Methods Twenty-seven patients treated with maxillomandibular advancement (MMA) underwent cone-beam computed tomography before surgery, immediately after surgery, and at 1-year follow-up. All patients underwent magnetic resonance imaging before surgery to assess disc displacements. Ten patients without disc displacement received MMA only. Seventeen patients with articular disc displacement received MMA with simultaneous TMJ disc repositioning (MMA-Drep). Pre- and postsurgical 3D models were superimposed using a voxel-based registration on the cranial base. Results The location, direction, and magnitude of condylar changes were displayed and quantified by graphic semitransparent overlays and 3D color-coded surface distance maps. Rotational condylar displacements were similar in the 2 groups. Immediately after surgery, condylar translational displacements of at least 1.5 mm occurred in a posterior, superior, or mediolateral direction in patients treated with MMA, whereas patients treated with MMA-Drep presented more marked anterior, inferior, and mediolateral condylar displacements. One year after surgery, more than half the patients in the 2 groups presented condylar resorptive changes of at least 1.5 mm. Patients treated with MMA-Drep presented condylar bone apposition of at least 1.5 mm at the superior surface in 26.4%, the anterior surface in 23.4%, the posterior surface in 29.4%, the medial surface in 5.9%, or the lateral surface in 38.2%, whereas bone apposition was not observed in patients treated with MMA. Conclusions One year after surgery, condylar resorptive changes greater than 1.5 mm were observed in the 2 groups. Articular disc repositioning facilitated bone apposition in localized condylar regions in patients treated with MMA-Drep. © 2013 American Association of Oral and Maxillofacial Surgeons.

Grafias não-convencionais da coda silábica nasal em dados de escrita de jovens e adultos em processo de alfabetização

Pós-graduação em Estudos Linguísticos - IBILCE

Trocas ortográficas na grafia da coda silábica simples por alunos da Educação de Jovens e Adultos (EJA)

Pós-graduação em Estudos Linguísticos - IBILCE

Segmentação de palavras: prosódia e convenções ortográficas na reelaboração da escrita infantil

Pós-graduação em Estudos Linguísticos - IBILCE

Generalização cartográfica para um Sistema de Navegação e Guia de Rota em Automóvel áudio-dinâmico com múltiplas escalas

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Desenvolvimento do protótipo de um atlas escolar interativo

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Visualização 3D de uma imagem digital

Pós-graduação em Ciências Cartográficas - FCT

Harry Clarke e a literatura: da pintura em vitrais à ilustração de livros

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)