Determining the geographical origin of lettuce with data mining applied to micronutrients and soil properties

Lettuce (Lactuca sativa) is the main leafy vegetable produced in Brazil. Since its production is widespread all over the country, lettuce traceability and quality assurance is hampered. In this study, we propose a new method to identify the geographical origin of Brazilian lettuce. The method uses a powerful data mining technique called support vector machines (SVM) applied to elemental composition and soil properties of samples analyzed. We investigated lettuce produced in São Paulo and Pernambuco, two states in the southeastern and northeastern regions in Brazil, respectively. We investigated efficiency of the SVM model by comparing its results with those achieved by traditional linear discriminant analysis (LDA). The SVM models outperformed the LDA models in the two scenarios investigated, achieving an average of 98 % prediction accuracy to discriminate lettuce from both states. A feature evaluation formula, called F–score, was used to measure the discriminative power of the variables analyzed. The soil exchangeable cation capacity, soil contents of low crystalized Al and Zn content in lettuce samples were the most relevant components for differentiation. Our results reinforce the potential of data mining and machine learning techniques to support traceability strategies and authentication of leafy vegetables.

Data mining as a hatchery process evaluation tool

The hatchery is one of the most important segments of the poultry chain, and generates an abundance of data, which, when analyzed, allow for identifying critical points of the process . The aim of this study was to evaluate the applicability of the data mining technique to databases of egg incubation of broiler breeders and laying hen breeders. The study uses a database recording egg incubation from broiler breeders housed in pens with shavings used for litters in natural mating, as well as laying hen breeders housed in cages using an artificial insemination mating system. The data mining technique (DM) was applied to analyses in a classification task, using the type of breeder and house system for delineating classes. The database was analyzed in three different ways: original database, attribute selection, and expert analysis. Models were selected on the basis of model precision and class accuracy. The data mining technique allowed for the classification of hatchery fertile eggs from different genetic groups, as well as hatching rates and the percentage of fertile eggs (the attributes with the greatest classification power). Broiler breeders showed higher fertility (> 95 %), but higher embryonic mortality between the third and seventh day post-hatching (> 0.5 %) when compared to laying hen breeders eggs. In conclusion, applying data mining to the hatchery process, selection of attributes and strategies based on the experience of experts can improve model performance.

Data mining as a hatchery process evaluation tool

The hatchery is one of the most important segments of the poultry chain, and generates an abundance of data, which, when analyzed, allow for identifying critical points of the process . The aim of this study was to evaluate the applicability of the data mining technique to databases of egg incubation of broiler breeders and laying hen breeders. The study uses a database recording egg incubation from broiler breeders housed in pens with shavings used for litters in natural mating, as well as laying hen breeders housed in cages using an artificial insemination mating system. The data mining technique (DM) was applied to analyses in a classification task, using the type of breeder and house system for delineating classes. The database was analyzed in three different ways: original database, attribute selection, and expert analysis. Models were selected on the basis of model precision and class accuracy. The data mining technique allowed for the classification of hatchery fertile eggs from different genetic groups, as well as hatching rates and the percentage of fertile eggs (the attributes with the greatest classification power). Broiler breeders showed higher fertility (> 95 %), but higher embryonic mortality between the third and seventh day post-hatching (> 0.5 %) when compared to laying hen breeders eggs. In conclusion, applying data mining to the hatchery process, selection of attributes and strategies based on the experience of experts can improve model performance.(AU)

An in silico data mining of the ammonium transporter gene family in Ananas comosus L / Uma mineração de dados in silico da família do gene transportador de amônio em Ananas comosus L

Arguably, the nitrogen (N) is an important and essential component for plant growth and development. Among the sources of N available, the ammonium is a major inorganic nitrogen source for plants is mobilized by ammonium transporter (AMT). In this study, data mining revealed that the Ananas comosus L. genome was identified eight genes of the AMT family. Based on this information, we conducted a comprehensive analysis using some bioinformatics tools in order to individually characterize the identified genes. The comprehensive analysis of AMT will provide an important foundation for further investigation of the regulatory mechanisms of AcoAMTs in A. comosus L.

Indiscutivelmente, o nitrogênio (N) é um componente importante e essencial para o crescimento e desenvolvimento das plantas. Dentre as fontes de N disponíveis, o amônio é a principal fonte de nitrogênio inorgânico para as plantas, sendo mobilizado pelo transportador de amônio (AMT). Neste estudo, a mineração de dados revelou que no genoma de Ananas comosus L. foram identificados oito genes da família AMT. Com base nessas informações, realizamos uma análise abrangente usando algumas ferramentas de bionformática com a finalidade de caracterizar individualmente os genes identificados. A análise abrangente do AMT fornecerá uma base importante para uma investigação mais aprofundada dos mecanismos regulatórios de AcoAMTs em A. comosus L.

An in silico data mining of the ammonium transporter gene family in Ananas comosus L / Uma mineração de dados in silico da família do gene transportador de amônio em Ananas comosus L

Arguably, the nitrogen (N) is an important and essential component for plant growth and development. Among the sources of N available, the ammonium is a major inorganic nitrogen source for plants is mobilized by ammonium transporter (AMT). In this study, data mining revealed that the Ananas comosus L. genome was identified eight genes of the AMT family. Based on this information, we conducted a comprehensive analysis using some bioinformatics tools in order to individually characterize the identified genes. The comprehensive analysis of AMT will provide an important foundation for further investigation of the regulatory mechanisms of AcoAMTs in A. comosus L.(AU)

Indiscutivelmente, o nitrogênio (N) é um componente importante e essencial para o crescimento e desenvolvimento das plantas. Dentre as fontes de N disponíveis, o amônio é a principal fonte de nitrogênio inorgânico para as plantas, sendo mobilizado pelo transportador de amônio (AMT). Neste estudo, a mineração de dados revelou que no genoma de Ananas comosus L. foram identificados oito genes da família AMT. Com base nessas informações, realizamos uma análise abrangente usando algumas ferramentas de bionformática com a finalidade de caracterizar individualmente os genes identificados. A análise abrangente do AMT fornecerá uma base importante para uma investigação mais aprofundada dos mecanismos regulatórios de AcoAMTs em A. comosus L.(AU)

Preprocessing procedures and supervised classification applied to a database of systematic soil survey

Data Mining techniques play an important role in the prediction of soil spatial distribution in systematic soil surveying, though existing methodologies still lack standardization and a full understanding of their capabilities. The aim of this work was to evaluate the performance of preprocessing procedures and supervised classification approaches for predicting map units from 1:100,000-scale conventional semi-detailed soil surveys. Sheets of the Brazilian National Cartographic System on the 1:50,000 scale, Dois Córregos (Brotas 1:100,000-scale sheet), São Pedro and Laras (Piracicaba 1:100,000-scale sheet) were used for developing models. Soil map information and predictive environmental covariates for the dataset were obtained from the semi-detailed soil survey of the state of São Paulo, from the Brazilian Institute of Geography and Statistics (IBGE) 1:50,000-scale topographic sheets and from the 1:750,000-scale geological map of the state of São Paulo. The target variable was a soil map unit of four types: local soil unit name and soil class at three hierarchical levels of the Brazilian System of Soil Classification (SiBCS). Different data preprocessing treatments and four algorithms all having different approaches were also tested. Results showed that composite soil map units were not adequate for the machine learning process. Class balance did not contribute to improving the performance of classifiers. Accuracy values of 78 % and a Kappa index of 0.67 were obtained after preprocessing procedures with Random Forest, the algorithm that performed best. Information from conventional map units of semi-detailed (4th order) 1:100,000 soil survey generated models with values for accuracy, precision, sensitivity, specificity and Kappa indexes that support their use in programs for systematic soil surveying.

Preprocessing procedures and supervised classification applied to a database of systematic soil survey

Data Mining techniques play an important role in the prediction of soil spatial distribution in systematic soil surveying, though existing methodologies still lack standardization and a full understanding of their capabilities. The aim of this work was to evaluate the performance of preprocessing procedures and supervised classification approaches for predicting map units from 1:100,000-scale conventional semi-detailed soil surveys. Sheets of the Brazilian National Cartographic System on the 1:50,000 scale, Dois Córregos (Brotas 1:100,000-scale sheet), São Pedro and Laras (Piracicaba 1:100,000-scale sheet) were used for developing models. Soil map information and predictive environmental covariates for the dataset were obtained from the semi-detailed soil survey of the state of São Paulo, from the Brazilian Institute of Geography and Statistics (IBGE) 1:50,000-scale topographic sheets and from the 1:750,000-scale geological map of the state of São Paulo. The target variable was a soil map unit of four types: local soil unit name and soil class at three hierarchical levels of the Brazilian System of Soil Classification (SiBCS). Different data preprocessing treatments and four algorithms all having different approaches were also tested. Results showed that composite soil map units were not adequate for the machine learning process. Class balance did not contribute to improving the performance of classifiers. Accuracy values of 78 % and a Kappa index of 0.67 were obtained after preprocessing procedures with Random Forest, the algorithm that performed best. Information from conventional map units of semi-detailed (4th order) 1:100,000 soil survey generated models with values for accuracy, precision, sensitivity, specificity and Kappa indexes that support their use in programs for systematic soil surveying.(AU)

Prediction of soil CO2 flux in sugarcane management systems using the Random Forest approach

The Random Forest algorithm is a data mining technique used for classifying attributes in order of importance to explain the variation in an attribute-target, as soil CO2 flux. This study aimed to identify prediction of soil CO2 flux variables in management systems of sugarcane through the machine-learning algorithm called Random Forest. Two different management areas of sugarcane in the state of São Paulo, Brazil, were selected: burned and green. In each area, we assembled a sampling grid with 81 georeferenced points to assess soil CO2 flux through automated portable soil gas chamber with measuring spectroscopy in the infrared during the dry season of 2011 and the rainy season of 2012. In addition, we sampled the soil to evaluate physical, chemical, and microbiological attributes. For data interpretation, we used the Random Forest algorithm, based on the combination of predicted decision trees (machine learning algorithms) in which every tree depends on the values of a random vector sampled independently with the same distribution to all the trees of the forest. The results indicated that clay content in the soil was the most important attribute to explain the CO2 flux in the areas studied during the evaluated period. The use of the Random Forest algorithm originated a model with a good fit (R2 = 0.80) for predicted and observed values.(AU)

Classification of soil respiration in areas of sugarcane renewal using decision tree

The use of data mining is a promising alternative to predict soil respiration from correlated variables. Our objective was to build a model using variable selection and decision tree induction to predict different levels of soil respiration, taking into account physical, chemical and microbiological variables of soil as well as precipitation in renewal of sugarcane areas. The original dataset was composed of 19 variables (18 independent variables and one dependent (or response) variable). The variable-target refers to soil respiration as the target classification. Due to a large number of variables, a procedure for variable selection was conducted to remove those with low correlation with the variable-target. For that purpose, four approaches of variable selection were evaluated: no variable selection, correlation-based feature selection (CFS), chisquare method (χ2) and Wrapper. To classify soil respiration, we used the decision tree induction technique available in the Weka software package. Our results showed that data mining techniques allow the development of a model for soil respiration classification with accuracy of 81 %, resulting in a knowledge base composed of 27 rules for prediction of soil respiration. In particular, the wrapper method for variable selection identified a subset of only five variables out of 18 available in the original dataset, and they had the following order of influence in determining soil respiration: soil temperature > precipitation > macroporosity > soilmoisture > potential acidity.

Classification of soil respiration in areas of sugarcane renewal using decision tree

The use of data mining is a promising alternative to predict soil respiration from correlated variables. Our objective was to build a model using variable selection and decision tree induction to predict different levels of soil respiration, taking into account physical, chemical and microbiological variables of soil as well as precipitation in renewal of sugarcane areas. The original dataset was composed of 19 variables (18 independent variables and one dependent (or response) variable). The variable-target refers to soil respiration as the target classification. Due to a large number of variables, a procedure for variable selection was conducted to remove those with low correlation with the variable-target. For that purpose, four approaches of variable selection were evaluated: no variable selection, correlation-based feature selection (CFS), chisquare method (χ2) and Wrapper. To classify soil respiration, we used the decision tree induction technique available in the Weka software package. Our results showed that data mining techniques allow the development of a model for soil respiration classification with accuracy of 81 %, resulting in a knowledge base composed of 27 rules for prediction of soil respiration. In particular, the wrapper method for variable selection identified a subset of only five variables out of 18 available in the original dataset, and they had the following order of influence in determining soil respiration: soil temperature > precipitation > macroporosity > soilmoisture > potential acidity.(AU)

Prospecting for sludge bacteria from a poultry slaughterhouse, with potential for degrading organic substances / Prospecção de bactérias de lodo de abatedouro de aves com potencial degradador de substâncias orgânicas

The sludge produced in wastewater treatment plants of slaughterhouses is a rich source of chemical, organic, and microbiological constituents that can be biotechnologically exploited. The purpose of this study was to (i) conduct a chemical analysis of the sludge, and (ii) isolate, quantify, and describe the amylolytic, cellulolytic, ligninolytic, proteolytic, and keratinolytic bacteria in the sludge. Sludge samples were collected at the wastewater treatment plant of the Francap SA poultry company. The nutrient contents, C/N ratio, and pH were determined. For the bacterial count, 10 g sludge was diluted in 90 mL saline solution, which was serially diluted to 10-12. Aliquots of 100 µL of each dilution were transferred to selective media for isolation of bacteria that degrade organic substances. The colony-forming units were determined for each culture medium. Individual colonies were purified and characterized morphologically. The sludge contained 9.5, 1.21, and 0.45 dag kg-1 of N, P, and K, respectively. Fiftytwo isolates were purified and characterized, with 2.11 × 1012 to 9.55 ×1015 colony-forming units per g sludge. In conclusion, the sludge generated in poultry slaughterhouse wastewater treatment plants is a rich source of organo-mineral constituents and bacteria with biotechnological potential for degrading organic substances.

Os lodos produzidos nas estações de tratamento de efluentes de abatedouros são uma fonte de riqueza química, orgânica e microbiológica que precisa ser explorada biotecnologicamente. Objetivou-se neste estudo: (i) realizar a caracterização química do lodo e (ii) isolar, quantificar e caracterizar bactérias amilolíticas, celulolíticas, ligninolíticas, proteolíticas e queratinolíticas do lodo. Amostras de lodo foram coletadas na estação de tratamento de efluentes da empresa avícola FRANCAP S.A. Foram determinados os teores de nutrientes, a relação C/N e o pH. Para a quantificação bacteriana, 10 g de lodo foram diluídos em 90 mL de solução salina e dela, realizaram-se diluições seriadas até 10-12. Alíquotas de 100 µL de cada diluição foram transferidas aos meios seletivos para isolamento de bactérias degradadoras de substâncias orgânicas. Determinaram-se as unidades formadoras de colônia para cada meio de cultivo. Colônias individuais foram purificadas e caracterizadas morfologicamente. O lodo apresentou teores de N, P e K, de 9,5, 1,21 e 0,45 dag kg-1, respectivamente. Foram purificados e caracterizados 52 isolados, as unidades formadoras de colônia variaram entre 2,11 x 1012 a 9,55 x 1015. Conclui-se que os lodos gerados nas estações de tratamento de efluentes de abatedouro de aves são uma fonte de riqueza organomineral, além de apresentar bactérias com potencial biotecnológico de degradar substâncias orgânicas.

Prospecting for sludge bacteria from a poultry slaughterhouse, with potential for degrading organic substances / Prospecção de bactérias de lodo de abatedouro de aves com potencial degradador de substâncias orgânicas

The sludge produced in wastewater treatment plants of slaughterhouses is a rich source of chemical, organic, and microbiological constituents that can be biotechnologically exploited. The purpose of this study was to (i) conduct a chemical analysis of the sludge, and (ii) isolate, quantify, and describe the amylolytic, cellulolytic, ligninolytic, proteolytic, and keratinolytic bacteria in the sludge. Sludge samples were collected at the wastewater treatment plant of the Francap SA poultry company. The nutrient contents, C/N ratio, and pH were determined. For the bacterial count, 10 g sludge was diluted in 90 mL saline solution, which was serially diluted to 10-12. Aliquots of 100 µL of each dilution were transferred to selective media for isolation of bacteria that degrade organic substances. The colony-forming units were determined for each culture medium. Individual colonies were purified and characterized morphologically. The sludge contained 9.5, 1.21, and 0.45 dag kg-1 of N, P, and K, respectively. Fiftytwo isolates were purified and characterized, with 2.11 × 1012 to 9.55 ×1015 colony-forming units per g sludge. In conclusion, the sludge generated in poultry slaughterhouse wastewater treatment plants is a rich source of organo-mineral constituents and bacteria with biotechnological potential for degrading organic substances.(AU)

Os lodos produzidos nas estações de tratamento de efluentes de abatedouros são uma fonte de riqueza química, orgânica e microbiológica que precisa ser explorada biotecnologicamente. Objetivou-se neste estudo: (i) realizar a caracterização química do lodo e (ii) isolar, quantificar e caracterizar bactérias amilolíticas, celulolíticas, ligninolíticas, proteolíticas e queratinolíticas do lodo. Amostras de lodo foram coletadas na estação de tratamento de efluentes da empresa avícola FRANCAP S.A. Foram determinados os teores de nutrientes, a relação C/N e o pH. Para a quantificação bacteriana, 10 g de lodo foram diluídos em 90 mL de solução salina e dela, realizaram-se diluições seriadas até 10-12. Alíquotas de 100 µL de cada diluição foram transferidas aos meios seletivos para isolamento de bactérias degradadoras de substâncias orgânicas. Determinaram-se as unidades formadoras de colônia para cada meio de cultivo. Colônias individuais foram purificadas e caracterizadas morfologicamente. O lodo apresentou teores de N, P e K, de 9,5, 1,21 e 0,45 dag kg-1, respectivamente. Foram purificados e caracterizados 52 isolados, as unidades formadoras de colônia variaram entre 2,11 x 1012 a 9,55 x 1015. Conclui-se que os lodos gerados nas estações de tratamento de efluentes de abatedouro de aves são uma fonte de riqueza organomineral, além de apresentar bactérias com potencial biotecnológico de degradar substâncias orgânicas.(AU)

Calibration of the maximum carboxylation velocity (Vcmax) using data mining techniques and ecophysiological data from the Brazilian semiarid region, for use in Dynamic Global Vegetation Models / Calibração da velocidade máxima de carboxilação (Vcmax), utilizando técnicas de mineração de dados e dados de ecofisiologia da região semiárida brasileira, para uso em Modelos de Vegetação Globais Dinâmicos

Abstract The semiarid region of northeastern Brazil, the Caatinga, is extremely important due to its biodiversity and endemism. Measurements of plant physiology are crucial to the calibration of Dynamic Global Vegetation Models (DGVMs) that are currently used to simulate the responses of vegetation in face of global changes. In a field work realized in an area of preserved Caatinga forest located in Petrolina, Pernambuco, measurements of carbon assimilation (in response to light and CO2) were performed on 11 individuals of Poincianella microphylla, a native species that is abundant in this region. These data were used to calibrate the maximum carboxylation velocity (Vcmax) used in the INLAND model. The calibration techniques used were Multiple Linear Regression (MLR), and data mining techniques as the Classification And Regression Tree (CART) and K-MEANS. The results were compared to the UNCALIBRATED model. It was found that simulated Gross Primary Productivity (GPP) reached 72% of observed GPP when using the calibrated Vcmax values, whereas the UNCALIBRATED approach accounted for 42% of observed GPP. Thus, this work shows the benefits of calibrating DGVMs using field ecophysiological measurements, especially in areas where field data is scarce or non-existent, such as in the Caatinga.(AU)

Resumo A região semiárida do nordeste do Brasil, a Caatinga, é extremamente importante devido à sua biodiversidade e endemismo. Medidas de fisiologia vegetal são cruciais para a calibração de Modelos de Vegetação Globais Dinâmicos (DGVMs) que são atualmente usados para simular as respostas da vegetação diante das mudanças globais. Em um trabalho de campo realizado em uma área de floresta preservada na Caatinga localizada em Petrolina, Pernambuco, medidas de assimilação de carbono (em resposta à luz e ao CO2) foram realizadas em 11 indivíduos de Poincianella microphylla, uma espécie nativa que é abundante nesta região. Estes dados foram utilizados para calibrar a velocidade máxima de carboxilação (Vcmax) usada no modelo INLAND. As técnicas de calibração utilizadas foram Regressão Linear Múltipla (MLR) e técnicas de mineração de dados como Classification And Regression Tree (CART) e K-MEANS. Os resultados foram comparados com o modelo INLAND não calibrado. Verificou-se que a Produtividade Primária Bruta (PPB) simulada atingiu 72% da PPB observada ao usar os valores de Vcmax calibrado, enquanto que o modelo não calibrado obteve-se 42% da PPB observada. Assim, este trabalho mostra os benefícios de calibrar DGVMs usando medidas ecofisiológicas de campo, especialmente em áreas onde os dados de campo são escassos ou inexistentes, como na Caatinga.(AU)

O uso do data mining na Promoção de Saúde: uma revisão sistemática da literatura / The use of data mining in health promotion

O data mining (mineração de dados) é uma das etapas do processo Knowledge Discovery in Database, que tornou se a ferramenta mais conhecida do mesmo, pois sua metodologia visa a preparação e exploração dos dados, interpretação dos resultados e a percepção dos conhecimentos minerados. Diante o crescente número de dados na área da saúde, o data mining pode ser uma ferramenta de grande importância na extração de conhecimento dos dados e dessa forma poderá auxiliar os gestores de saúde nas tomadas de decisões voltadas a prevenção e promoção da saúde.

Data mining is one of the steps of the process of Knowledge Discovery in Databases, which became the most well-known tool of this process, as it has the aim of preparing and exploring data; interpreting results and providing a perception of the mined data. Given the growing knowledge in healthcare, data mining can be a very important tool in knowledge discovery and may aid heath manager decision making in prevention and health promotion.

O uso do data mining na Promoção de Saúde: uma revisão sistemática da literatura / The use of data mining in health promotion

O data mining (mineração de dados) é uma das etapas do processo Knowledge Discovery in Database, que tornou se a ferramenta mais conhecida do mesmo, pois sua metodologia visa a preparação e exploração dos dados, interpretação dos resultados e a percepção dos conhecimentos minerados. Diante o crescente número de dados na área da saúde, o data mining pode ser uma ferramenta de grande importância na extração de conhecimento dos dados e dessa forma poderá auxiliar os gestores de saúde nas tomadas de decisões voltadas a prevenção e promoção da saúde.(AU)

Data mining is one of the steps of the process of Knowledge Discovery in Databases, which became the most well-known tool of this process, as it has the aim of preparing and exploring data; interpreting results and providing a perception of the mined data. Given the growing knowledge in healthcare, data mining can be a very important tool in knowledge discovery and may aid heath manager decision making in prevention and health promotion.(AU)

Árvore de decisão e a densidade mínima de amostras no mapeamento da cobertura da terra / Decision tree and minimum sample density in land cover mapping

A cobertura da terra é uma informação espacial de extrema relevância para uma série de modelos, sendo utilizada para estimar a produção de sedimentos e para mensurar a potencialidade da paisagem em sequestrar carbono. A classificação da cobertura da terra pelo método de classificação supervisionado necessita de áreas de treino, já que essas áreas devem ser representativas para cada classe de cobertura da terra. Para o algoritmo de classificação por árvore de decisão (AD), a complexidade da AD resulta em diferentes valores de acurácias para os mapas temáticos. Desse modo, o objetivo deste estudo foi determinar a densidade mínima de amostras em um modelo por AD, a fim de discriminar as classes de cobertura da terra e avaliar o tamanho da AD gerada quanto ao seu número de folhas. Além disso, preocupou-se em identificar as classes da cobertura da terra de mais difícil classificação. Nesse contexto, foram utilizadas bandas da imagem do satélite RESOURCESAT-1 e índices espectrais. A densidade mínima de amostras variou entre 0,15 e 0,30% da área total para cada classe. Esse intervalo de amostragem possibilitou resultados melhores que 80% para o índice kappa. O menor agrupamento entre observações em uma mesma folha terminal foi de 45, e as classes mais difíceis de classificar foram floresta e lavoura de arroz, devido à semelhança espectral que as florestas sombreadas possuem com as lavouras de arroz irrigadas.(AU)

Land cover is a spatial information of great relevance for a variety of models for estimating sediment yield and to measure the potential of the landscape carbon sequestration. The classification of land cover by the supervised method requires training areas, these areas must be representative of each class of land cover. For the classification decision tree (DT) algorithm, the complexity of DT, results in different values of accuracies for thematic maps. Thus, the objective of this study was to estimate the minimum sample density in a DT model which would allow to discriminate land cover classes, evaluate the size of the generated DT model, as well as, identify the more difficult land cover class to be mapped. Satellite images from RESOURCESAT-1as well as spectral indices were used in the study. The minimum sample density varied between 0.15 and 0.30% of the total area for each class, this sampling interval allowed better results than 80% for kappa index. The smallest grouping of observations in the same terminal leaf was 45 observations. In this study the most difficult land use classes to be mapped were forest and rice crops due to spectral similarity of shaded forests with irrigated rice crops.(AU)

Spatial distribution of seropositive dogs to Leptospira spp. and evaluation of leptospirosis risk factors using a decision tree

Background: Leptospirosis is an important zoonotic disease associated with poor areas of urban settings of developing countries and early diagnosis and prompt treatment may prevent disease. Although rodents are reportedly considered the main reservoirs of leptospirosis, dogs may develop the disease, may become asymptomatic carriers and may be used as sentinels for disease epidemiology. The use of Geographical Information Systems (GIS) combined with spatial analysis techniques allows the mapping of the disease and the identification and assessment of health risk factors. Besides the use of GIS and spatial analysis, the technique of data mining, decision tree, can provide a great potential to find a pattern in the behavior of the variables that determine the occurrence of leptospirosis. The objective of the present study was to apply Geographical Information Systems and data prospection (decision tree) to evaluate the risk factors for canine leptospirosis in an area of Curitiba, PR. Materials, Methods & Results: The present study was performed on the Vila Pantanal, a urban poor community in the city of Curitiba. A total of 287 dog blood samples were randomly obtained house-by-house in a two-day sampling on January 2010. In addition, a questionnaire was applied to owners at the time of sampling. Geographical coordinates related to each household of tested dog were obtained using a Global Positioning System (GPS) for mapping the spatial distribution of reagent and non-reagent dogs to leptospirosis. For the decision tree, risk factors included results of microagglutination test (MAT) from the serum of dogs, previous disease on the household, contact with rats or other dogs, dog breed, outdoors access, feeding, trash around house or backyard, open sewer proximity and flooding. A total of 189 samples (about 2/3 of overall samples) were randomly selected for the training file and consequent decision rules. The remained 98 samples were used for the testing file. The seroprevalence showed a pattern of spatial distribution that involved all the Pantanal area, without agglomeration of reagent animals. In relation to data mining, from 189 samples used in decision tree, a total of 165 (87.3%) animal samples were correctly classified, generating a Kappa index of 0.413. A total of 154 out of 159 (96.8%) samples were considered non-reagent and were correctly classified and only 5/159 (3.2%) were wrongly identified. On the other hand, only 11 (36.7%) reagent samples were correctly classified, with 19 (63.3%) samples failing diagnosis. Discussion: The spatial distribution that involved all the Pantanal area showed that all the animals in the area are at risk of contamination by Leptospira spp. Although most samples had been classified correctly by the decision tree, a degree of difficulty of separability related to seropositive animals was observed, with only 36.7% of the samples classified correctly. This can occur due to the fact of seronegative animals number is superior to the number of seropositive ones, taking the differences in the pattern of variable behavior. The data mining helped to evaluate the most important risk factors for leptospirosis in an urban poor community of Curitiba. The variables selected by decision tree reflected the important factors about the existence of the disease (default of sewer, presence of rats and rubbish and dogs with free access to street). The analyses showed the multifactorial character of the epidemiology of canine leptospirosis.