Detecção e diagnóstico de falhas não-supervisionados baseados em estimativa de densidade recursiva e classificador fuzzy auto-evolutivo

In this work, we propose a two-stage algorithm for real-time fault detection and identification of industrial plants. Our proposal is based on the analysis of selected features using recursive density estimation and a new evolving classifier algorithm. More specifically, the proposed approach for the detection stage is based on the concept of density in the data space, which is not the same as probability density function, but is a very useful measure for abnormality/outliers detection. This density can be expressed by a Cauchy function and can be calculated recursively, which makes it memory and computational power efficient and, therefore, suitable for on-line applications. The identification/diagnosis stage is based on a self-developing (evolving) fuzzy rule-based classifier system proposed in this work, called AutoClass. An important property of AutoClass is that it can start learning from scratch". Not only do the fuzzy rules not need to be prespecified, but neither do the number of classes for AutoClass (the number may grow, with new class labels being added by the on-line learning process), in a fully unsupervised manner. In the event that an initial rule base exists, AutoClass can evolve/develop it further based on the newly arrived faulty state data. In order to validate our proposal, we present experimental results from a level control didactic process, where control and error signals are used as features for the fault detection and identification systems, but the approach is generic and the number of features can be significant due to the computationally lean methodology, since covariance or more complex calculations, as well as storage of old data, are not required. The obtained results are significantly better than the traditional approaches used for comparison

Avaliação da aprendizagem no curso a distância de licenciatura em ciências biológicas da Universidade Estadual de Pernambuco

In contemporary society, distance education is expanding, especially in the offering of courses of initiatory professor training. By the side of possibilities, there is the need to critically reflect on the government decision to finance, and even to incite distance education, as a more economic way to achieve, within different time and space, the greatest quantity of the population, trying to fill the gaps of the Brazilian school education. The research was made in the Biology Bachelor Course offered by the Pernambuco University (UPE), in the context of the Presential Support Pole of the Paraiba State University, located in the city of Campina Grande. Along this study, we intend to analyze the evaluation practice and the instruments of valuation available in the virtual environment of learning (AVA), used by the former professors in the learning evaluation of the contents offered by the reference course. The relevance of the discussion is to reflect about the results of distance education in the initial of the professor training. To perceive the possibilities and limitations concerning the technological resources available at the educational process, especially to the evaluation practice, is primordial in order to comprehend the contents of learning that can be explored by the professors and which is the dialogical relation that is firmed between professor, preceptor and student, in favor of the learning development and an effective and meaningful education. The qualitative research had the symbolic interacionism as a methodological-theoretical approach. We gathered informations through institutional documents, documental records, questionnaires and semi-structured interviews. Treating and analyzing the data we used the content analysis method (Bardin, 1977). As a theoretical basis, we relied on authors such as Zabala (1998, 1999), Aretio (2002), Hoffmann (2003, 2005), Silva, M. (2003, 2006), Belloni (2006), Luckesi (2008), Silva, J. (2008), Vasconcelos (2008) and Domingos (2009). It was evident the need to reflect about the educational practice of the professors and preceptors responsible for the academic distance learning, concerning the evaluation of the learning contents in a autonomous and innovatory way, identifying its influence in the development of values which are considered vital to a complete professor upbringing. The evaluation in a mediator approach is necessary to the reality of an online classroom, because of its character to promote the improvement of the action of the one who is teaching and the one Who is learning in an interactive, collaborative and cooperative perspective, seeking a transformative praxis. Involved in this formation, the bachelors will be able to promote the development of capacities and skills necessary to the complete learning of theirs future students, certifying the education for life, which is a perspective that includes the knowing, the knowing how to do and how to be, a living being with sustainable relations with the others and with nature