Primary aluminum production is an uninterrupted and complex process that must operate in a closed loop, hindering possibilities for experiments to improve production. In this sense, it is important to have ways to simulate this process computationally without acting directly on the plant, since such direct intervention could be dangerous, expensive, and time-consuming. This problem is addressed in this paper by combining real data, the artificial neural network technique, and clustering methods to create soft sensors to estimate the temperature, the aluminum fluoride percentage in the electrolytic bath, and the level of metal of aluminum reduction cells (pots). An innovative strategy is used to split the entire dataset by section and lifespan of pots with automatic clustering for soft sensors. The soft sensors created by this methodology have small estimation mean squared error with high generalization power. Results demonstrate the effectiveness and feasibility of the proposed approach to soft sensors in the aluminum industry that may improve process control and save resources.

The quality of the water in the Amazon's reservoirs is of fundamental importance for natural ecosystems, biota, and for the region's population. Maintaining the water quality involves long-term monitoring programs established by the requirements of Brazilian legislation. A web interface may facilitate the use of monitoring results routinely, which allows periodic insertion of previously selected water quality parameters results, to finally provide a simple and direct way to evaluate the water quality. The general objective of this study was to develop a software based on a water quality indicator (WQI) system considering chemical, physical-chemical, and biological parameters evaluated in four seasonal periods in Samuel dam. Multivariate analysis was used to select 10 significant variables (oxidation-reduction potential, dissolved oxygen, total dissolved solids, chlorophyll a, phosphate, Ba, Ca, Fe, Na, and Sn). The web software added innovation to the project, enabling to storage of data from analysis of field-collected samples in an organized and safe way in a database, in addition to speeding up the calculation of the WQI, making it possible to classify the water quality more quickly and accurately.

No abstract

In Barcarena, several industries are in operation, some of these industries generate highly toxic by-products, which end up influencing the social, economic, and health conditions of the residents. This study aimed to evaluate the exposure of an amazonian population to the elements Cr, Mn, Ni, Pb, and Zn using hair as a bioindicator. The results showed the average hair contents of Cr (2.5±1.5 μg g-1), Mn (15.5±12.3 μg g-1), Ni (5.4±9.0 μg g-1), Pb (18.7±15.4 μg g-1), and Zn (274±227 μg g-1) in the studied residents were higher than the averages of the elements in other countries population. The highest concentrations of Ni, Pb, and Zn were detected in children under 11 years old. Cr stood out for presenting the highest levels in the 21 to 30 years old group and Mn presented a higher concentration range for the 11 to 20 years old group. Cr showed a significant correlation with age (0.901; p=0.014) in the group of children (age <11 years).

Resumen. Las universidades privadas enfrentan el desafío de reducir la tasa de evasión de estudiantes de los cursos de grados. Si esta tasa es muy alta, el beneficio de estas universidades puede reducir drásticamente, alejando a los accionistas e inversores. Este trabajo tiene como objetivo aplicar técnicas de minería de datos clasificar entre estudiantes que abandonan y los que terminan los cursos de grados, para facilitar la identificación de los posibles factores de riesgos que influyen en la evasión universitaria. Para el análisis fueron utilizados datos abiertos extraídos del portal del gobierno y diversos algoritmos de minería de datos. En los experimentos realizados, fue posible seleccionar la técnica más eficiente de clasificación para este problema, mediante el análisis de métricas de confianza, consistencia y calidad. Además, fue realizado un levantamiento de los factores que tiene mayor incidencia en la evasión y abandono de los estudiantes de las universidades privadas de la ciudad de Belem do Pará (Brasil).Abstract. The private universities face the challenge to reduce the evasion rate of the undergraduate students. If this rate is too high, the profit of these universities can drastically reduce, driving away shareholders and investors. This paper aims to apply data mining techniques to classify students who completed the course and those who dropped out, in order to facilitate the identification of possible risk factors that influence university dropout. The analysis used open data extracted from the government portal and various data mining algorithms.