Network-based high level data classification

Traditional supervised data classification considers only physical features (e. g., distance or similarity) of the input data. Here, this type of learning is called low level classification. On the other hand, the human (animal) brain performs both low and high orders of learning and it has facility in identifying patterns according to the semantic meaning of the input data. Data classification that considers not only physical attributes but also the pattern formation is, here, referred to as high level classification. In this paper, we propose a hybrid classification technique that combines both types of learning. The low level term can be implemented by any classification technique, while the high level term is realized by the extraction of features of the underlying network constructed from the input data. Thus, the former classifies the test instances by their physical features or class topologies, while the latter measures the compliance of the test instances to the pattern formation of the data. Our study shows that the proposed technique not only can realize classification according to the pattern formation, but also is able to improve the performance of traditional classification techniques. Furthermore, as the class configuration's complexity increases, such as the mixture among different classes, a larger portion of the high level term is required to get correct classification. This feature confirms that the high level classification has a special importance in complex situations of classification. Finally, we show how the proposed technique can be employed in a real-world application, where it is capable of identifying variations and distortions of handwritten digit images. As a result, it supplies an improvement in the overall pattern recognition rate.

Atributos físicos de um Latossolo Vermelho correlacionados linear e espacialmente com a consorciação de guandu com milheto

O sistema cultivo mínimo, por possibilitar pouca movimentação de solo, menor número de operações agrícolas sem incorporação dos resíduos vegetais, apresenta vantagens em razão do menor custo de preparo e da redução das perdas de solo e água. No ano agrícola de 2006/2007, na Fazenda de Ensino e Pesquisa da Faculdade de Engenharia de Ilha Solteira, SP, Brasil - FEIS/UNESP, situada nas condições do Cerrado Brasileiro, objetivou-se analisar a produtividade de massa de matéria seca da consorciação de forragem (guandu+milheto) (MSF), em função de atributos físicos do solo, tais como resistência à penetração (RP), umidade gravimétrica (UG), umidade volumétrica (UV) e densidade do solo (DS) nas profundidades de 0,0-0,10 m; 0,10-0,20 m e 0,20-0,30 m. Para tanto, foi instalado um ensaio, contendo 117 pontos amostrais, em um Latossolo Vermelho distroférrico, sob pivô central, numa área experimental de 1600 m² sob cultivo mínimo. A análise estatística constou de análise descritiva inicial dos atributos e análise das correlações lineares simples entre eles, e, finalmente, de análise geoestatística. Do ponto de vista da correlação espacial, o atributo que mais bem explica a produtividade de massa de matéria seca da consorciação é a densidade do solo na camada de 0,20-0,30 m, com uma correlação inversa, indicando que as espécies se desenvolvem bem em solos adensados.

Perceived neighborhood problems: multilevel analysis to evaluate psychometric properties in a Southern adult Brazilian population

Abstract Background Physical attributes of the places in which people live, as well as their perceptions of them, may be important health determinants. The perception of place in which people dwell may impact on individual health and may be a more telling indicator for individual health than objective neighborhood characteristics. This paper aims to evaluate psychometric and ecometric properties of a scale on the perceptions of neighborhood problems in adults from Florianopolis, Southern Brazil. Methods Individual, census tract level (per capita monthly familiar income) and neighborhood problems perception (physical and social disorders) variables were investigated. Multilevel models (items nested within persons, persons nested within neighborhoods) were run to assess ecometric properties of variables assessing neighborhood problems. Results The response rate was 85.3%, (1,720 adults). Participants were distributed in 63 census tracts. Two scales were identified using 16 items: Physical Problems and Social Disorder. The ecometric properties of the scales satisfactory: 0.24 to 0.28 for the intra-class correlation and 0.94 to 0.96 for reliability. Higher values on the scales of problems in the physical and social domains were associated with younger age, more length of time residing in the same neighborhood and lower census tract income level. Conclusions The findings support the usefulness of these scales to measure physical and social disorder problems in neighborhoods.

Hydro-physical characterization of soils under tropical semi-deciduous forest

The study of the hydro-physical behavior in soils using toposequences is of great importance for better understanding the soil, water and vegetation relationships. This study aims to assess the hydro-physical and morphological characterization of soil from a toposequence in Galia, state of São Paulo, Brazil). The plot covers an area of 10.24 ha (320 × 320 m), located in a semi-deciduous seasonal forest. Based on ultra-detailed soil and topographic maps of the area, a representative transect from the soil in the plot was chosen. Five profiles were opened for the morphological description of the soil horizons, and hydro-physical and micromorphological analyses were performed to characterize the soil. Arenic Haplustult, Arenic Haplustalf and Aquertic Haplustalf were the soil types observed in the plot. The superficial horizons had lower density and greater hydraulic conductivity, porosity and water retention in lower tensions than the deeper horizons. In the sub-superficial horizons, greater water retention at higher tensions and lower hydraulic conductivity were observed, due to structure type and greater clay content. The differences observed in the water retention curves between the sandy E and the clay B horizons were mainly due to the size distribution, shape and type of soil pores.

Gradients in N-cycling attributes along forestry and agricultural land-use systems are indicative of soil capacity for N supply

Indicators of soil quality associated with N-cycling were assessed under different land-use systems (native forest NAT, reforestation with Araucaria angustifolia or Pinus taeda and agricultural use AGR) to appraise the effects on the soil potential for N supply. The soil total N ranged from 2 to 4 g/kg (AGR and NAT, respectively), and the microbial biomass N ranged from 80 to 250 mg/kg, being higher in NAT and A. angustifolia, and lower in P. taeda and AGR sites. Activities of asparaginase (ca. 50200 mg NH4+-N/kg per h), glutaminase (ca. 200800 mg NH4+-N/kg per h) and urease (ca. 80200 mg NH4+-N/kg/h) were also more intense in the NAT and A. angustifolia-reforested soils, indicating greater capacity for N mineralization. The NAT and AGR soils showed the highest and the lowest ammonification rate, respectively (ca. 1 and 0.4 mg NH4+-N/kg per day), but the inverse for nitrification rate (ca. 12 and 26%), indicating a low capacity for N supply, in addition to higher risks of N losses in the AGR soil. A multivariate analysis indicated more similarity between NAT and A. angustifolia-reforested sites, whilst the AGR soil was different and associated with a higher nitrification rate. In general, reforestation with the native species A. angustifolia had less impact than reforestation with the exogenous species P. taeda, considering the soil capacity for N supply. However, AGR use caused more changes, generally decrease in indicators of N-cycling, showing a negative soil management effect on the sustainability of this agroecosystem.

Mapeamento de solos e da produtividade de plantações de Eucalyptus grandis, com uso de sistema de informação geográfica

Detailed environmental land characterization is essential for technical and financial planning, for both the scientific point of view and technological application. This work aimed at the physiographic and pedological characterization and eucalyptus productivity mapping at Itatinga Forest Sciences Experimental Station (southeastern Brazil), using geographic information systems in order to identify possible cause-effect relationships between forest productivity and soil attributes. The digital cartographic dataset was structured as follows: as primary source of data, aerial photograph and field survey were used and, as a secondary source, topographical, geological and land use occupation maps were used. For mapping wood productivity at age six (MAI6, Mean Annual Increment), inventory data of permanent plots (same species, provenance and age) were used, which were obtained from Eucalyptus grandis plantations. Using simple linear correlation and backward stepwise multiple regression analysis, the dependent variable (MAI) was related with physical and chemical characteristics of the soils. Two standards of contour curves were identified, one with close curves, narrow and surrounding the drainage network, in the steeper and lower altitude areas; the other, with spaced contour lines, in the areas of higher altitude and with plane relief. Six types of soils were characterized as being highly related to the physiographic patterns of the area: loamy sandy to sandy clayey Typic Hapludox (LVAd, 47.5%), clayey Rhodic Hapludox (LVd1, 33.4%), sandy clay Rhodic Hapludox (LVd2, 6%), clayey Rhodic Hapludox (LVdf, 9.1%), Entisols (G, 3.4%) and Fluvents soil (RY, 0.6%). There were large variations in wood productivity in the Eucalyptus grandis plantations, characterized in six classes, ranging from 26 to 52 m(3) ha(-1) yr(-1). These productivity changes were strictly related to soil mapping units. Through multiple regression analysis, we found that clay and organic matter contents were the attributes which most strongly explained the productivity differences.

Spectral behavior of some modal soil profiles from São Paulo State, Brazil

Remote sensing has a high potential for environmental evaluation. However, a necessity exists for a better understanding of the relations between the soil attributes and spectral data. The objective of this work was to analyze the spectral behavior of some soil profiles from the region of Piracicaba, São Paulo State, using a laboratory spectroradiometer (400 to 2500 nm). The relations between the reflected electromagnetic energy and the soil physical, chemical and mineralogical attributes were analyzed, verifying the spectral variations of soil samples in depth along the profiles with their classification and discrimination. Sandy soil reflected more, presenting a spectral curve with an ascendant form, opposite to clayey soils. The 1900 nm band discriminated soil with 2:1 mineralogy from the 1:1 and oxidic soils. It was possible to detect the presence of kaolinite, gibbsite, hematite and goethite in the soils through the descriptive aspects of curves, absorption features and reflectance intensity. A relation exists between the weathering stage and spectral data. The evaluation of the superficial and subsuperficial horizon samples allowed characterizing and discriminating the analytical variability of the profile, helping to soil distinguishing and classification.