The materialist dialectical method is a philosophical investigative method to analyze aspects of reality as complex processes composed by integrating units named poles. Dialectics has experienced considerable progress in the 19th century, with Hegel's dialectics and, in the 20th century, with the works of Marx, Engels, and Gramsci, in Philosophy and Economics. The movement of poles through their contradictions is viewed as a dynamic process with intertwined phases of evolution and revolutionary crisis. Santos et al. introduced the Objective Dialectical Classifier (ODC), a non-supervised self-organized map for classification. As a case study, we used ODC to classify 181 magnetic resonance synthetic multispectral images composed by proton density, T1-and T2-weighted synthetic brain images. Comparing ODC to k-means, fuzzy c-means, and Kohonen's self-organized maps, concerning with image fidelity indexes as estimatives of quantization distortion, we proved that ODC can reach the same quantization performance as optimal non-supervised classifiers like Kohonen's self-organized maps.

No abstract

No abstract

The materialist dialectical method is a philosophical investigative method to analyze aspects of reality. These aspects are viewed as complex processes composed by basic units named poles, which interact with each other. Dialectics has experienced considerable progress in the 19th century, with Hegel's dialectics and, in the 20th century, with the works of Marx, Engels, and Gramsci, in Philosophy and Economics. The movement of poles through their contradictions is viewed as a dynamic process with intertwined phases of evolution and revolutionary crisis. In order to build a computational process based on dialectics, the interaction between poles can be modeled using fuzzy membership functions.Based on this assumption, we introduce the Objective Dialectical Classifier (ODC), a non-supervised map for classification based on materialist dialectics and designed as an extension of fuzzy c-means classifier. As a case study, we used ODC to classify 181 magnetic resonance synthetic multispectral images composed by proton density, T 1 -and T 2 -weighted synthetic brain images. Comparing ODC to k-means, fuzzy c-means, and Kohonen's self-organized maps, concerning with image fidelity indexes as estimatives of quantization distortion, we proved that ODC can reach almost the same quantization performance as optimal non-supervised classifiers like Kohonen's self-organized maps.

The increased incidence of injuries in Brazilian athletes is of concern to then and their coaches and technical staff. The injuries are a result of various factors, and know the influence of each in favor of lesions can help prevent and treat these injuries. In health, traditional statistical methods are commonly used in the study of several cases, but it is noteworthy that such methods only detect the linear features of the data. As the real world is full of non-linear phenomena, it becomes necessary to use techniques that realize this nonlinearity. For these cases, the Artificial Neural Networks (ANN) have shown satisfactory results. This article aims to test algorithms for variable selection that extract knowledge of the weights of an ANN, to obtain the contribution of each factor in the occurrence of injuries to athletes. It is hoped that finding a new alternative needs to understand the mechanisms that favor injuries, and therefore help in prevention. Palavras-chave-Redes Neurais,Seleção de Variáveis, Lesões, Fatores de risco, Atletas. 1 Introdução O atletismo brasileiro vem crescendo de forma significativa nos últimos anos, conquistando, assim, posições no ranking mundial. O aumento na intensidade do treinamento dos atletas foi fator relevante para esse feito. Como conseqüência do aumento da demanda de exercícios cada vez maus modernos e competitivos, houve um crescimento no risco do aparecimento de lesões, o que é motivo de apreensão para atletas e treinadores, pois interrompem o processo evolutivo do treinamento. Muitos são os fatores que podem contribuir para o surgimento de tais lesões, e saber qual a relevância de cada um deles é de grande importância para os profissionais ligados ao esporte, pois sabendo os mecanismos principais dos lesionamento é possível tomar medidas preventivas. Na área de saúde, métodos estatísticos tradicionais são comumente usados no estudo dos mais diversos casos, porém vale ressaltar que tais métodos detectam apenas as características lineares dos dados. Como o mundo real é repleto de fenômenos não-lineares, torna-se necessária a utilização de técnicas que percebam esta não-linearidade. Para estes casos, as Redes Neurais Artificiais (RNA) têm mostrado resultados bastante satisfatórios. Este artigo tem como objetivo testar algoritmos de seleção de variáveis que extraem conhecimento dos pesos de uma RNA, para obter a contribuição de cada fator no surgimento de lesões em atletas. Espera-se com isso encontrar uma nova alternativa mais precisa para se entender os mecanismos favorecedores de lesões, e conseqüentemente ajudar nas medidas preventivas.