Short-term relation between air pollutants and hospitalizations for respiratory diseases: analysis by temporal association rules.

This study investigates the relation between exposure to critical air pollution events with multipollutant (CO, PM10, PM2.5, NO2, O3, and SO2) and hospitalizations for respiratory diseases in the metropolitan area of São Paulo (RMSP) and in the countryside and coastline, from 2017 to 2021. Data mining analysis by temporal association rules searched for frequent patterns of respiratory diseases and multipollutants associated with time intervals. In the results, pollutants PM10, PM2.5, and O3 showed high concentration values in the three regions, SO2 on the coast, and NO2 in the RMSP. Seasonality was similar between pollutants and between cities and concentrations significantly higher in winter, except for O3, which was present in warm seasons. Hospitalizations were recurrent during the transition from summer to colder periods. In approximately 35% of the total days with hospitalization greater than the annual average, one or more pollutants had a high concentration. The rules showed that PM2.5, PM10, and O3 pollutants are strongly associated with increased hospitalizations in the RMSP (PM2.5 and PM10 with 38.5% support and 77% confidence) and in Campinas (PM2.5 with 66.1% support and 94% confidence) and the pollutant O3 with maximum support of 17.5%. On the coast, SO2 was related to high hospitalizations (43.85% support and 80% confidence). The pollutants CO and NO2 were not associated with the increase in hospitalizations. The ratio delay indicates the pollutants that were associated with hospitalizations, having concentration remained above the limit for three days, oscillating in smaller hospitalizations on the 1st day and again higher on the 2nd and 3rd days of delay, in a decreasing way. In conclusion, high pollutant exposure is significantly associated with daily hospitalization for respiratory problems. The cumulative effect of air pollutants increased hospitalization in the following days, in addition to identifying the pollutants and which pollutant combinations are most harmful to health in each region.

Spatial patterns and temporal variations of pollutants at 56 air quality monitoring stations in the state of São Paulo, Brazil.

This study applied two data mining tasks: clustering and association rules to a dataset of pollutants in the state of São Paulo. The clustering task was applied to temporal patterns and geospatial distributions of pollutants, and the association rules were used to identify prevailing meteorological conditions when there were high concentrations of pollutants from 2017 to 2019. The results indicated good adequacy of the cluster, indicating different pollution levels per group, with a silhouette coefficient from 0.26 to 0.72. In the spatial evaluation, the groups severely polluted were located in the metropolitan region, on the coast and, some inland cities, by industrial, vehicular, burning, agriculture, and other emissions. The cluster identified a strong presence of O3 and PM2.5 in 65% and 72% of the monitored stations in several areas of the state. As for the distance between the sources of pollution, the groups of PM10 and NO2 were geographically distant, while PM2.5, CO, SO2, and O3 were closer, suggesting a spatial relationship of exposure. Seasonality was similar between groups, with significantly higher concentrations in winter, except for O3, for which higher concentrations occurred in summer. Meteorological conditions contributed to critical episodes of pollution (support and confidence greater than 80%), with low temperature and humidity, low rainfall, and milder wind associated with increased pollutants. In conclusion, investigating spatial representativeness allows revealing spatial and temporal patterns of pollutants and unfavorable meteorological conditions to diffusion. Thus, ideal and effective measures can be taken to avoid critical periods of exposure based on the behavior of pollutants in different regions and related climate changes.

Discussion concerning the application of data mining technology in sports performance management / Discussão sobre a aplicação da tecnologia de mineração de dados na gestão do desempenho esportivo / Debate sobre la aplicación de la tecnología de minería de datos en la gestión del rendimiento deportivo

ABSTRACT Introduction: Finding the factors that contribute to success in student performance or failure is necessary for every teacher. Data mining, which is already used in companies for management processes, can be essential in this research. Objective: Discuss the data mining algorithms application in sports performance management. Method: A database was developed considering seasonal factors, health benefit index, and sports behavior characteristics. The data were entered under fuzzy logic, processed, and analyzed in IBM SPSS Modeler Software. Decision-making efficiency was improved with the target base interpolation analysis and the C spatial noise reduction methods. The fidelity of sports behavior was consolidated under Gauss time series analysis. Results: The relationship between the mining algorithm to find the existing problems and the association results in the mining rules provided valuable information for improving health guidelines to the physical activity students. Conclusion: The original data from the educational system can be transformed into useful information through the association rules algorithm, and the relationship between the performance can be obtained, providing the improvement in the decision making for the benefit of the physical level of the students. Evidence Level II; Therapeutic Studies - Investigating the results.

RESUMO Introdução: Encontrar os fatores que contribuam para o sucesso no desempenho do aluno ou o seu fracasso é uma necessidade de todo professor. A mineração de dados, que já é utilizada em empresas para processos de gestão, pode ser uma importante aliada dessa pesquisa. Objetivo: Discutir a aplicação de algoritmos da mineração de dados na gestão do desempenho esportivo. Método: Um banco de dados foi desenvolvido considerando fatores sazonais, índice de benefício de saúde e características do comportamento esportivo. Os dados foram inseridos sob lógica Fuzzy, processados e analisados no Software IBM SPSS Modeler. A eficiência da tomada de decisão foi aprimorada com o método de análise de interpolação da base de alvo e o método de redução de ruído espacial C. A fidelidade do comportamento esportivo foi consolidada sob a análise de séries atemporais de Gauss. Resultados: A relação entre o algoritmo de mineração para encontrar os problemas existentes e os resultados da associação nas regras de mineração forneceram informações valiosas para o aprimoramento da orientação à saúde dos alunos praticantes de atividades físicas. Conclusão: Os dados originais do sistema educacional podem ser transformados em informações úteis por meio do algoritmo de regras de associação e a relação entre o desempenho pode ser obtida proporcionando o aperfeiçoamento na tomada de decisão para o benefício do nível físico dos alunos. Nível de evidência II; Estudos Terapêuticos - Investigação de Resultados.

RESUMEN Introducción: Encontrar los factores que contribuyen al éxito en el rendimiento de los alumnos o a su fracaso es una necesidad de todo profesor. La minería de datos, que ya se utiliza en las empresas para los procesos de gestión, puede ser un importante aliado en esta investigación. Objetivo: Discutir la aplicación de los algoritmos de minería de datos en la gestión del rendimiento deportivo. Método: Se elaboró una base de datos teniendo en cuenta los factores estacionales, el índice de beneficios para la salud y las características del comportamiento deportivo. Los datos se introdujeron bajo lógica difusa, se procesaron y analizaron en el software IBM SPSS Modeler. La eficacia de la toma de decisiones se mejoró con el método de análisis de interpolación de la base del objetivo y el método de reducción del ruido espacial C. La fidelidad del comportamiento deportivo se consolidó bajo el análisis de series temporales de Gauss. Resultados: La relación entre el algoritmo de minería para encontrar los problemas existentes y los resultados de la asociación en las reglas de minería proporcionaron información valiosa para la mejora de la orientación sanitaria de los estudiantes que practican actividades físicas. Conclusión: Los datos originales del sistema educativo se pueden transformar en información útil mediante el algoritmo de reglas de asociación y se puede obtener la relación entre el rendimiento proporcionando la mejora en la toma de decisiones en beneficio del nivel físico de los alumnos. Nivel de evidencia II; Estudios terapéuticos - Investigación de resultados.

Optimization of water quality monitoring programs by data mining.

Water quality monitoring programs are essential planning and management tools, but they face many challenges in the developing world. The scarcity of financial and human resources and the unavailability of infrastructure often make it impossible to meet the legal requirements of water monitoring. Many approaches to optimizing water quality monitoring programs have already been proposed. However, few investigations have developed and tested data mining for this purpose. This article has developed data-based models to reduce the number of water quality parameters of monitoring programs using data mining. The objective was to extract patterns from the database, expressed by association rules, which together with field parameters, measured with automatic probes, can estimate laboratory variables. This approach was applied in 35 monitoring stations along 27 river basins throughout Brazil. The data are from fifty years of monitoring (1971-2021), constituting 6328 observations of 60 water quality parameters investigated in different environmental contexts, water quality, and the structuring of monitoring programs. With the applied approach it was possible to estimate 56% of the laboratory parameters in the monitoring stations investigated. The influence of environmental characteristics on the optimization capacity of monitoring programs was evident. The methodology used was not influenced by different water quality levels and anthropogenic impacts. However, the number of parameters was the most influential element in optimization. Monitoring programs with 20 or more water quality variables have the highest potential (≥44%) of optimization by this methodology. Results demonstrate that this approach is a promising alternative that can reduce the frequency of analyses measured in the laboratory and increase the spatial and temporal coverage of water quality monitoring networks.

An analysis of malaria in the Brazilian Legal Amazon using divergent association rules.

In data analysis, the mining of frequent patterns plays an important role in the discovery of associations and correlations between data. During this process, it is common to produce thousands of association rules (ARs), making the study of each one arduous. This problem weakens the process of finding useful information. There is a scientific effort to develop approaches capable of filtering interesting patterns, balancing the number of ARs produced with the goal of not being trivial and known by specialists. However, even when such approaches are adopted, the number of produced ARs can still be high. This work contributes by presenting Divergent Association Rules Approach (DARA), a novel approach for obtaining ARs that presents themselves in divergence with the data distribution. DARA is applied right after traditional approaches to filtering interesting patterns. To validate our approach, we studied the dataset related to the occurrence of malaria in the Brazilian Legal Amazon. The discovered patterns highlight that ARs brought relevant insights from the data. This article contributes both in the medical and computer science fields since this novel computational approach enabled new findings regarding malaria in Brazil.

Knowledge Extraction and Improved Data Fusion for Sales Prediction in Local Agricultural Markets.

In this paper, a monitoring system of agricultural production is modeled as a Data Fusion System (data from local fairs and meteorological data). The proposal considers the particular information of sales in agricultural markets for knowledge extraction about the associations among them. This association knowledge is employed to improve predictions of sales using a spatial prediction technique, as shown with data collected from local markets of the Andean region of Ecuador. The commercial activity in these markets uses Alternative Marketing Circuits (CIALCO). This market platform establishes a direct relationship between producer and consumer prices and promotes direct commercial interaction among family groups. The problem is presented first as a general fusion problem with a network of spatially distributed heterogeneous data sources, and is then applied to the prediction of products sales based on association rules mined in available sales data. First, transactional data is used as the base to extract the best association rules between products sold in different local markets, knowledge that allows the system to gain a significant improvement in prediction accuracy in the spatial region considered.

Worldwide co-occurrence analysis of 17 species of the genus Brachypodium using data mining.

The co-occurrence of plant species is a fundamental aspect of plant ecology that contributes to understanding ecological processes, including the establishment of ecological communities and its applications in biological conservation. A priori algorithms can be used to measure the co-occurrence of species in a spatial distribution given by coordinates. We used 17 species of the genus Brachypodium, downloaded from the Global Biodiversity Information Facility data repository or obtained from bibliographical sources, to test an algorithm with the spatial points process technique used by Silva et al. (2016), generating association rules for co-occurrence analysis. Brachypodium spp. has emerged as an effective model for monocot species, growing in different environments, latitudes, and elevations; thereby, representing a wide range of biotic and abiotic conditions that may be associated with adaptive natural genetic variation. We created seven datasets of two, three, four, six, seven, 15, and 17 species in order to test the algorithm with four different distances (1, 5, 10, and 20 km). Several measurements (support, confidence, lift, Chi-square, and p-value) were used to evaluate the quality of the results generated by the algorithm. No negative association rules were created in the datasets, while 95 positive co-occurrences rules were found for datasets with six, seven, 15, and 17 species. Using 20 km in the dataset with 17 species, we found 16 positive co-occurrences involving five species, suggesting that these species are coexisting. These findings are corroborated by the results obtained in the dataset with 15 species, where two species with broad range distributions present in the previous dataset are eliminated, obtaining seven positive co-occurrences. We found that B. sylvaticum has co-occurrence relations with several species, such as B. pinnatum, B. rupestre, B. retusum, and B. phoenicoides, due to its wide distribution in Europe, Asia, and north of Africa. We demonstrate the utility of the algorithm implemented for the analysis of co-occurrence of 17 species of the genus Brachypodium, agreeing with distributions existing in nature. Data mining has been applied in the field of biological sciences, where a great amount of complex and noisy data of unseen proportion has been generated in recent years. Particularly, ecological data analysis represents an opportunity to explore and comprehend biological systems with data mining and bioinformatics tools.

Heterogeneity of Multimedia Exposures to Neurotoxic Elements (Al, As, Cd, Pb, Mn, and Hg) in Breastfed Infants from Porto Velho, Brazil.

Infant exposure to neurotoxic elements is a public health issue that needs monitoring with regard to breast milk composition. We studied six neurotoxic elements in breast milk samples at different stages of lactation in mothers from Porto Velho, Brazil. We used a flow-injection mercury system (FIMS) to determine total Hg concentrations and an inductively coupled plasma optical emission spectrometer (ICP-OES) to determine the concentrations of Al, As, Cd, Pb, and Mn in 106 donors of a human milk bank. Association rules analyses were applied to determine the pattern of binary and ternary mixtures of the measured exposants. The metal concentration was mostly below the limit of detection (LOD) for Cd (99%), Pb (84%), and Hg (72%), and it was above the LOD for As (53%), Mn (60%), and Al (82%), respectively. Median concentrations (dry weight) of Al, As, Hg, Mn, and Pb were 1.81 µg/g, 13.8 ng/g, 7.1 ng/g, 51.1 ng/g, and 0.43 µg/g, respectively. Al is singly the most frequent element to which infants are exposed. Occurring binary combination (> LOD) was 56% for Al-Mn, 41% for Al-As, 22% for Al-Hg, and 13% for Al-Pb. In 100% of neonates, exposure to Al-ethylmercury (EtHg) occurred through immunization with thimerosal-containing vaccines (TCV). Association rules analysis revealed that Al was present in all of the multilevel combinations and hierarchical levels and that it showed a strong link with other neurotoxic elements (especially with Mn, As, and Hg). (a) Nursing infants are exposed to combinations of neurotoxicants by different routes, dosages, and at different stages of development; (b) In breastfed infants, the binary exposures to Al and total Hg can occur through breast milk and additionally through TCV (EtHg and Al);

Knowledge-based model to support decision-making when choosing between two association data mining techniques / Modelo basado en conocimiento para apoyar la toma de decisiones entre dos técnicas de asociación de la minería de datos / Modelo baseado no conhecimento para apoiar a tomada de decisões entre duas técnicas de associação de mineração de dados

Abstract Introduction. This paper presents the functionality and characterization of two Data Mining (DM) techniques, logistic regression and association rules (Apriori Algorithm). This is done through a conceptual model that enables to choose the appropriate data mining project technique for obtaining knowledge from criteria that describe the specific project to be developed. Objective. Support decision making when choosing the most appropriate technique for the development of a data mining project. Materials and methods. Association and logistic regression techniques are characterized in this study, showing the functionality of their algorithms. Results. The proposed model is the input for the implementation of a knowledge-based system that emulates a human expert's knowledge at the time of deciding which data mining technique to choose against a specific problem that relates to a data mining project. It facilitates verification of the business processes of each one of the techniques, and measures the correspondence between a project's objectives versus the components provided by both the logistic regression and the association rules techniques. Conclusion. Current and historical information is available for decision-making through the generated data mining models. Data for the models are taken from Data Warehouses, which are informational environments that provide an integrated and total view of the organization.

Resumen Introducción. El artículo muestra en un modelo conceptual basado en conocimiento la caracterización y funcionalidad de dos técnicas de Minería de Datos (MD) regresión logística y reglas de asociación, para elegir la técnica de MD apropiada en proyectos de obtención de conocimiento a partir criterios que describen el proyecto específico a ser desarrollado. Objetivo. Apoyar la toma de decisiones en el momento de elegir cual técnica es la más apropiada para el desarrollo de un proyecto de minería de datos. Materiales y métodos. Las técnicas de asociación y regresión logística son caracterizadas, mostrando la funcionalidad de sus algoritmos. Resultados. El modelo propuesto es el insumo para la implementación de un Sistema basado en conocimiento que imita el conocimiento de un experto humano en el momento de tomar la decisión de que técnica de minería de datos escoger frente a un problema específico que relaciona un proyecto de minería de datos. Facilita la verificación de los procesos de negocio de cada una de las técnicas, y mide la correspondencia entre los objetivos trazados de un proyecto versus los componentes que ofrecen la técnica de regresión logística y la técnica de reglas de asociación. Conclusión. La información actual e histórica se encuentra disponible para la toma de decisiones a través de los modelos generados por la minería de datos. Los datos para los modelos son provenientes de bodegas de datos, las cuales son entornos informativos, que proporcionan una visión integrada y total de la organización.

Resumo Introdução. O artigo mostra em um modelo conceituai baseado no conhecimento a caracterização e funcionalidade de duas técnicas de regressão logística de Data Mining (MD) e regras de associação, para escolher a técnica de MD apropriada em projetos de aquisição de conhecimento com base em critérios que descrevem a Projeto específico a ser desenvolvido. Objetivo. Apoie a tomada de decisão no momento da escolha da técnica mais apropriada para o desenvolvimento de um projeto de mineração de dados. Materiais e métodos. As técnicas de associação e regressão logística são caracterizadas, mostrando a funcionalidade de seus algoritmos. Resultados. O modelo proposto é a entrada para a implementação de um sistema baseado no conhecimento que imita o conhecimento de um perito humano ao decidir qual técnica de mineração de dados escolher contra um problema específico que relaciona um projeto de mineração para informações. Facilita a verificação dos processos de negócios de cada uma das técnicas e mede a correspondência entre os objetivos de um projeto versus os componentes que oferecem a técnica de regressão logística e a técnica das regras de associação. Conclusão. Informações atuais e históricas estão disponíveis para a tomada de decisões através de modelos gerados pela mineração de dados. Os dados para os modelos provêm de data warehouses, que são ambientes informativos, que fornecem uma visão integrada e total da organização.