Algoritmos para mineria de datos con redes de neuronas

Este trabajo propone una serie de algoritmos con el objetivo de extraer información de conjuntos de datos con redes de neuronas. Se estudian dichos algoritmos con redes de neuronas Enhenced Neural Networks (ENN), debido a que esta arquitectura tiene algunas ventajas cuando se aproximan funciones mediante redes neuronales. En la red ENN los pesos de la matriz principal varián con cada patrón, por lo que se comete un error menor en la aproximación. Las redes de neuronas ENN reúnen la información en los pesos de su red auxiliar, se propone un método para obtener información de la red a través de dichos pesos en formas de reglas y asignando un factor de certeza de dichas reglas. La red ENN obtiene un error cuadrático medio menor que el error teórico de una aproximación matemática por ejemplo mediante polinomios de Taylor. Se muestra como una red ENN, entrenada a partir un conjunto de patrones obtenido de una función de variables reales, sus pesos asociados tienen unas relaciones similares a las que se veri_can con las variables independientes con dicha función de variables reales. Las redes de neuronas ENN aproximan polinomios, se extrae conocimiento de un conjunto de datos de forma similar a la regresión estadística, resolviendo de forma más adecuada el problema de multicolionalidad en caso de existir. Las relaciones a partir de los pesos asociados de la matriz de la red auxiliar se obtienen similares a los coeficientes de una regresión para el mismo conjunto numérico. Una red ENN entrenada a partir de un conjunto de datos de una función boolena extrae el conocimiento a partir de los pesos asociados, y la influencia de las variables de la regla lógica de la función booleana, queda reejada en esos pesos asociados a la red auxiliar de la red ENN. Se plantea una red de base radial (RBF) para la clasificación y predicción en problemas forestales y agrícolas, obteniendo mejores resultados que con el modelo de regresión y otros métodos. Los resultados con una red RBF mejoran al método de regresión si existe colinealidad entre los datos que se dispone y no son muy numerosos. También se detecta que variables tienen más importancia en virtud de la variable pronóstico. Obteniendo el error cuadrático medio con redes RBF menor que con otros métodos, en particular que con el modelo de regresión. Abstract A series of algorithms is proposed in this study aiming at the goal of producing information about data groups with a neural network. These algorithms are studied with Enheced Neural Networks (ENN), owing to the fact that this structure shows sever advantages when the functions are approximated by neural networks. Main matrix weights in th ENN vary on each pattern; so, a smaller error is produced when approximating. The neural network ENN joins the weight information contained in their auxiliary network. Thus, a method to obtain information on the network through those weights is proposed by means of rules adding a certainty factor. The net ENN obtains a mean squared error smaller than the theorical one emerging from a mathematical aproximation such as, for example, by means of Taylor's polynomials. This study also shows how in a neural network ENN trained from a set of patterns obtained through a function of real variables, its associated weights have relationships similar to those ones tested by means of the independent variables connected with such functions of real variables. The neural network ENN approximates polynomials through it information about a set of data may be obtained in a similar way than through statistical regression, solving in this way possible problems of multicollinearity in a more suitable way. Relationships emerging from the associated weights in the auxiliary network matrix obtained are similar to the coeficients corresponding to a regression for the same numerical set. A net ENN trained from a boolean function data set obtains its information from its associated weights. The inuence of the variables of the boolean function logical rule are reected on those weights associated to the net auxiliar of the ENN. A radial basis neural networks (RBF) for the classification and prediction of forest and agricultural problems is proposed. This scheme obtains better results than the ones obtained by means of regression and other methods. The outputs with a net RBF better the regression method if the collineality with the available data and their amount is not very large. Detection of which variables are more important basing on the forecast variable can also be achieved, obtaining a mean squared error smaller that the ones obtained through other methods, in special the one produced by the regression pattern.

Dysfunctional 3D model based on structural and neuropsychological information

Acquired brain injury (ABI) 1-2 refers to any brain damage occurring after birth. It usually causes certain damage to portions of the brain. ABI may result in a significant impairment of an individuals physical, cognitive and/or psychosocial functioning. The main causes are traumatic brain injury (TBI), cerebrovascular accident (CVA) and brain tumors. The main consequence of ABI is a dramatic change in the individuals daily life. This change involves a disruption of the family, a loss of future income capacity and an increase of lifetime cost. One of the main challenges in neurorehabilitation is to obtain a dysfunctional profile of each patient in order to personalize the treatment. This paper proposes a system to generate a patient s dysfunctional profile by integrating theoretical, structural and neuropsychological information on a 3D brain imaging-based model. The main goal of this dysfunctional profile is to help therapists design the most suitable treatment for each patient. At the same time, the results obtained are a source of clinical evidence to improve the accuracy and quality of our rehabilitation system. Figure 1 shows the diagram of the system. This system is composed of four main modules: image-based extraction of parameters, theoretical modeling, classification and co-registration and visualization module.

Variable Speed Limits. Review and development of an aggregate indicator based on floating car data.

Changing factors (mainly traffic intensity and weather conditions) affecting road conditions require a suitable optimal speed at any time. To solve this problem, variable speed limit systems (VSL) ? as opposed to fixed limits ? have been developed in recent decades. This term has included a number of speed management systems, most notably dynamic speed limits (DSL). In order to avoid the indiscriminate use of both terms in the literature, this paper proposes a simple classification and offers a review of some experiences, how their effects are evaluated and their results This study also presents a key indicator, which measures the speed homogeneity and a methodology to obtain the data based on floating cars and GPS technology applying it to a case study on a section of the M30 urban motorway in Madrid (Spain).

A machine learning approach to identify clinical trials involving nanodrugs and nanodevices from ClinicalTrials.gov

BACKGROUND: Clinical Trials (CTs) are essential for bridging the gap between experimental research on new drugs and their clinical application. Just like CTs for traditional drugs and biologics have helped accelerate the translation of biomedical findings into medical practice, CTs for nanodrugs and nanodevices could advance novel nanomaterials as agents for diagnosis and therapy. Although there is publicly available information about nanomedicine-related CTs, the online archiving of this information is carried out without adhering to criteria that discriminate between studies involving nanomaterials or nanotechnology-based processes (nano), and CTs that do not involve nanotechnology (non-nano). Finding out whether nanodrugs and nanodevices were involved in a study from CT summaries alone is a challenging task. At the time of writing, CTs archived in the well-known online registry ClinicalTrials.gov are not easily told apart as to whether they are nano or non-nano CTs-even when performed by domain experts, due to the lack of both a common definition for nanotechnology and of standards for reporting nanomedical experiments and results. METHODS: We propose a supervised learning approach for classifying CT summaries from ClinicalTrials.gov according to whether they fall into the nano or the non-nano categories. Our method involves several stages: i) extraction and manual annotation of CTs as nano vs. non-nano, ii) pre-processing and automatic classification, and iii) performance evaluation using several state-of-the-art classifiers under different transformations of the original dataset. RESULTS AND CONCLUSIONS: The performance of the best automated classifier closely matches that of experts (AUC over 0.95), suggesting that it is feasible to automatically detect the presence of nanotechnology products in CT summaries with a high degree of accuracy. This can significantly speed up the process of finding whether reports on ClinicalTrials.gov might be relevant to a particular nanoparticle or nanodevice, which is essential to discover any precedents for nanotoxicity events or advantages for targeted drug therapy.

Mapping Genetic Diversity of Cherimoya (Annona cherimola Mill.): Application of Spatial Analysis for Conservation and Use of Plant Genetic Resources.

There is a growing call for inventories that evaluate geographic patterns in diversity of plant genetic resources maintained on farm and in species' natural populations in order to enhance their use and conservation. Such evaluations are relevant for useful tropical and subtropical tree species, as many of these species are still undomesticated, or in incipient stages of domestication and local populations can offer yet-unknown traits of high value to further domestication. For many outcrossing species, such as most trees, inbreeding depression can be an issue, and genetic diversity is important to sustain local production. Diversity is also crucial for species to adapt to environmental changes. This paper explores the possibilities of incorporating molecular marker data into Geographic Information Systems (GIS) to allow visualization and better understanding of spatial patterns of genetic diversity as a key input to optimize conservation and use of plant genetic resources, based on a case study of cherimoya (Annona cherimola Mill.), a Neotropical fruit tree species. We present spatial analyses to (1) improve the understanding of spatial distribution of genetic diversity of cherimoya natural stands and cultivated trees in Ecuador, Bolivia and Peru based on microsatellite molecular markers (SSRs); and (2) formulate optimal conservation strategies by revealing priority areas for in situ conservation, and identifying existing diversity gaps in ex situ collections. We found high levels of allelic richness, locally common alleles and expected heterozygosity in cherimoya's putative centre of origin, southern Ecuador and northern Peru, whereas levels of diversity in southern Peru and especially in Bolivia were significantly lower. The application of GIS on a large microsatellite dataset allows a more detailed prioritization of areas for in situ conservation and targeted collection across the Andean distribution range of cherimoya than previous studies could do, i.e. at province and department level in Ecuador and Peru, respectively.

Multi-dimensional classification with super-classes

The multi-dimensional classification problem is a generalisation of the recently-popularised task of multi-label classification, where each data instance is associated with multiple class variables. There has been relatively little research carried out specific to multi-dimensional classification and, although one of the core goals is similar (modelling dependencies among classes), there are important differences; namely a higher number of possible classifications. In this paper we present method for multi-dimensional classification, drawing from the most relevant multi-label research, and combining it with important novel developments. Using a fast method to model the conditional dependence between class variables, we form super-class partitions and use them to build multi-dimensional learners, learning each super-class as an ordinary class, and thus explicitly modelling class dependencies. Additionally, we present a mechanism to deal with the many class values inherent to super-classes, and thus make learning efficient. To investigate the effectiveness of this approach we carry out an empirical evaluation on a range of multi-dimensional datasets, under different evaluation metrics, and in comparison with high-performing existing multi-dimensional approaches from the literature. Analysis of results shows that our approach offers important performance gains over competing methods, while also exhibiting tractable running time.

Detecting and characterising ramp events in wind power time series

In order to implement accurate models for wind power ramp forecasting, ramps need to be previously characterised. This issue has been typically addressed by performing binary ramp/non-ramp classifications based on ad-hoc assessed thresholds. However, recent works question this approach. This paper presents the ramp function, an innovative wavelet- based tool which detects and characterises ramp events in wind power time series. The underlying idea is to assess a continuous index related to the ramp intensity at each time step, which is obtained by considering large power output gradients evaluated under different time scales (up to typical ramp durations). The ramp function overcomes some of the drawbacks shown by the aforementioned binary classification and permits forecasters to easily reveal specific features of the ramp behaviour observed at a wind farm. As an example, the daily profile of the ramp-up and ramp-down intensities are obtained for the case of a wind farm located in Spain

Study of PM10 and PM2.5 levels in three European cities: Analysis of intra and inter urban variations

In the present paper, 1-year PM10 and PM 2.5 data from roadside and urban background monitoring stations in Athens (Greece), Madrid (Spain) and London (UK) are analysed in relation to other air pollutants (NO,NO2,NOx,CO,O3 and SO2)and several meteorological parameters (wind velocity, temperature, relative humidity, precipitation, solar radiation and atmospheric pressure), in order to investigate the sources and factors affecting particulate pollution in large European cities. Principal component and regression analyses are therefore used to quantify the contribution of both combustion and non-combustion sources to the PM10 and PM 2.5 levels observed. The analysis reveals that the EU legislated PM 10 and PM2.5 limit values are frequently breached, forming a potential public health hazard in the areas studied. The seasonal variability patterns of particulates varies among cities and sites, with Athens and Madrid presenting higher PM10 concentrations during the warm period and suggesting the larger relative contribution of secondary and natural particles during hot and dry days. It is estimated that the contribution of non-combustion sources varies substantially among cities, sites and seasons and ranges between 38-67% and 40-62% in London, 26-50% and 20-62% in Athens, and 31-58% and 33-68% in Madrid, for both PM10 and PM 2.5. Higher contributions from non-combustion sources are found at urban background sites in all three cities, whereas in the traffic sites the seasonal differences are smaller. In addition, the non-combustion fraction of both particle metrics is higher during the warm season at all sites. On the whole, the analysis provides evidence of the substantial impact of non-combustion sources on local air quality in all three cities. While vehicular exhaust emissions carry a large part of the risk posed on human health by particle exposure, it is most likely that mitigation measures designed for their reduction will have a major effect only at traffic sites and additional measures will be necessary for the control of background levels. However, efforts in mitigation strategies should always focus on optimal health effects.

Origin and evolution of the slime molds (Mycetozoa)

The Mycetozoa include the cellular (dictyostelid), acellular (myxogastrid), and protostelid slime molds. However, available molecular data are in disagreement on both the monophyly and phylogenetic position of the group. Ribosomal RNA trees show the myxogastrid and dictyostelid slime molds as unrelated early branching lineages, but actin and β-tubulin trees place them together as a single coherent (monophyletic) group, closely related to the animal–fungal clade. We have sequenced the elongation factor-1α genes from one member of each division of the Mycetozoa, including Dictyostelium discoideum, for which cDNA sequences were previously available. Phylogenetic analyses of these sequences strongly support a monophyletic Mycetozoa, with the myxogastrid and dictyostelid slime molds most closely related to each other. All phylogenetic methods used also place this coherent Mycetozoan assemblage as emerging among the multicellular eukaryotes, tentatively supported as more closely related to animals + fungi than are green plants. With our data there are now three proteins that consistently support a monophyletic Mycetozoa and at least four that place these taxa within the “crown” of the eukaryote tree. We suggest that ribosomal RNA data should be more closely examined with regard to these questions, and we emphasize the importance of developing multiple sequence data sets.

Ocular cicatricial pemphigoid antigen: Partial sequence and biochemical characterization

Ocular cicatricial pemphigoid (OCP) is an autoimmune disease that affects mainly conjunctiva and other squamous epithelia. OCP is histologically characterized by a separation of the epithelium from underlying tissues within the basement membrane zone. Immunopathological studies demonstrate the deposition of anti-basement membrane zone autoantibodies in vivo. Purified IgG from sera of patients with active OCP identified a cDNA clone from a human keratinocyte cDNA library that had complete homology with the cytoplasmic domain of β4-integrin. The sera recognized a 205-kDa protein in human epidermal, human conjunctiva, and tumor cell lysates that was identified as β4-integrin by its reaction with polyclonal and monoclonal antibodies to human β4-integrin. Sera from patients with bullous pemphigoid, pemphigus vulgaris, and cicatricial pemphigoid-like diseases did not recognize the 205-kDa protein, indicating the specificity of the binding. These data strongly implicate a role for human β4-integrin in the pathogenesis of OCP. It should be emphasized that multiple antigens in the basement membrane zone of squamous epithelia may serve as targets for a wide spectrum of autoantibodies observed in vesiculobullous diseases. Molecular definition of these autoantigens will facilitate the classification and characterization of subsets of cicatricial pemphigoid and help distinguishing them from bullous pemphigoid. This study highlights the function and importance of β4-integrin in maintaining the attachment of epithelial cells to the basement membrane.

Point mutations and sequence variability in proteins: Redistributions of preexisting populations

Here we study the effect of point mutations in proteins on the redistributions of the conformational substates. We show that regardless of the location of a mutation in the protein structure and of its type, the observed movements of the backbone recur largely at the same positions in the structures. Despite the different interactions that are disrupted and formed by the residue substitution, not only are the conformations very similar, but the regions that move are also the same, regardless of their sequential or spatial distance from the mutation. This observation leads us to conclude that, apart from some extreme cases, the details of the interactions are not critically important in determining the protein conformation or in specifying which parts of the protein would be more prone to take on different local conformations in response to changes in the sequence. This finding further illustrates why proteins manifest a robustness toward many mutational events. This nonuniform distribution of the conformer population is consistently observed in a variety of protein structural types. Topology is critically important in determining folding pathways, kinetics, building block cutting, and anatomy trees. Here we show that topology is also very important in determining which regions of the protein structure will respond to sequence changes, regardless of the sequential or spatial location of the mutation.

Chloroplast DNA evidence of colonization, adaptive radiation, and hybridization in the evolution of the Macaronesian flora.

Most evolutionary studies of oceanic islands have focused on the Pacific Ocean. There are very few examples from the Atlantic archipelagos, especially Macaronesia, despite their unusual combination of features, including a close proximity to the continent, a broad range of geological ages, and a biota linked to a source area that existed in the Mediterranean basin before the late Tertiary. A chloroplast DNA (cpDNA) restriction site analysis of Argyranthemum (Asteraceae: Anthemideae), the largest endemic genus of plants of any volcanic archipelago in the Atlantic Ocean, was performed to examine patterns of plant evolution in Macaronesia. cpDNA data indicated that Argyranthemum is a monophyletic group that has speciated recently. The cpDNA tree showed a weak correlation with the current sectional classification and insular distribution. Two major cpDNA lineages were identified. One was restricted to northern archipelagos--e.g., Madeira, Desertas, and Selvagens--and the second comprised taxa endemic to the southern archipelago--e.g., the Canary Islands. The two major radiations identified in the Canaries are correlated with distinct ecological habitats; one is restricted to ecological zones under the influence of the northeastern trade winds and the other to regions that are not affected by these winds. The patterns of phylogenetic relationships in Argyranthemum indicate that interisland colonization between similar ecological zones is the main mechanism for establishing founder populations. This phenomenon, combined with rapid radiation into distinct ecological zones and interspecific hybridization, is the primary explanation for species diversification.

Molecular cloning and sequence analysis of expansins--a highly conserved, multigene family of proteins that mediate cell wall extension in plants.

Expansins are unusual proteins discovered by virtue of their ability to mediate cell wall extension in plants. We identified cDNA clones for two cucumber expansins on the basis of peptide sequences of proteins purified from cucumber hypocotyls. The expansin cDNAs encode related proteins with signal peptides predicted to direct protein secretion to the cell wall. Northern blot analysis showed moderate transcript abundance in the growing region of the hypocotyl and no detectable transcripts in the nongrowing region. Rice and Arabidopsis expansin cDNAs were identified from collections of anonymous cDNAs (expressed sequence tags). Sequence comparisons indicate at least four distinct expansin cDNAs in rice and at least six in Arabidopsis. Expansins are highly conserved in size and sequence (60-87% amino acid sequence identity and 75-95% similarity between any pairwise comparison), and phylogenetic trees indicate that this multigene family formed before the evolutionary divergence of monocotyledons and dicotyledons. Sequence and motif analyses show no similarities to known functional domains that might account for expansin action on wall extension. A series of highly conserved tryptophans may function in expansin binding to cellulose or other glycans. The high conservation of this multigene family indicates that the mechanism by which expansins promote wall extensin tolerates little variation in protein structure.

The Impact of Shyness on Loneliness, Social Anxiety, and School Liking in Late Childhood

Author: Charity M. Walker Title: THE IMPACT OF SHYNESS ON LONELINESS, SOCIAL ANXIETY, AND SCHOOL LIKING IN LATE CHILDHOOD Advisor: Maria T. Riva, Ph.D. Degree Date: August 2011 ABSTRACT Shyness is associated with several emotional, social, and academic problems. While there are multiple difficulties that often accompany shyness, there appear to be some factors that can moderate negative effects of shyness. Research has demonstrated that certain parenting factors affect the adjustment of shy children in early childhood, but there is minimal research illuminating the effect of parenting factors in older age groups. The first purpose of this study was to examine relationships between shyness and loneliness, social anxiety, and school liking. The second purpose was to investigate whether the quality of the relationship between a parent and a 10- to 15-year-olds child influences the amount of loneliness or social anxiety a shy child experiences or how the child feels about school. Parent-child dyads served as participants and were recruited from public and private middle schools and church youth groups in Colorado and Indiana. Child participants completed several self-report surveys regarding their relationship with a parent, shyness, loneliness, social anxiety, and their attitude toward school. Parents completed a survey about their relationship with their child and responded to questions related to their perceptions of their child's shyness. Data was analyzed with a series of correlation and regression analyses. Greater degrees of self-reported shyness were found to be associated with higher levels of loneliness and social anxiety and less positive feelings about school. Due to a problem with multicollinearity during data analysis, this study was not able to explore the effect of the parent-child relationship quality on the associations between shyness and adjustment factors. Overall, these findings imply that shyness remains an important issue as children approach adolescence. Further research is needed to continue learning about the potential importance of parent-child interactions in reducing maladjustment for shy children during late childhood.

Fatores abióticos condicionantes da distribuição de espécies arbóreas em quatro formações florestais do Estado de São Paulo

No estudo das comunidades florestais, estabelecer a importância relativa dos fatores que definem a composição e a distribuição das espécies é um desafio. Em termos de gradientes ambientais o estudo das respostas das espécies arbóreas são essenciais para a compreensão dos processos ecológicos e decisões de conservação. Neste sentido, para contribuir com a elucidação dos processos ecológicos nas principais formações florestais do Estado de São Paulo (Floresta Ombrófila Densa de Terras Baixas, Floresta Ombrófila Densa Submontana, Floresta Estacional Semidecidual e Savana Florestada) este trabalho objetivou responder as seguintes questões: (I) a composição florística e a abundância das espécies arbóreas, em cada unidade fitogeográfica, variam conforme o gradiente edáfico e topográfico?; (II) características do solo e topografia podem influenciar na previsibilidade de ocorrência de espécies arbóreas de ampla distribuição em diferentes tipos vegetacionais? (III) existe relação entre o padrão de distribuição espacial de espécies arbóreas e os parâmetros do solo e topografia? O trabalho foi realizado em parcelas alocadas em unidades de conservação (UC) que apresentaram trechos representativos, em termos de conservação e tamanho, das quatro principais formações florestais presentes no Estado de São Paulo. Em cada UC foram contabilizados os indivíduos arbóreos (CAP ≥ 15 cm), topografia, dados de textura e atributos químicos dos solos em uma parcela de 10,24 ha, subdividida em 256 subparcelas. Análises de correspodência canônica foram aplicadas para estabelecer a correspondência entre a abundância das espécies e o gradiente ambiental (solo e topografia). O método TWINSPAN modificado foi aplicado ao diagrama de ordenação da CCA para avaliar a influência das variáveis ambientais (solo e topografia) na composição de espécies. Árvores de regressão \"ampliadas\" (BRT) foram ajustadas para a predição da ocorrência das espécies segundo as variáveis de solo e topografia. O índice de Getis-Ord (G) foi utilizado para determinar a autocorrelação espacial das variáveis ambientais utilizadas nos modelos de predição da ocorrência das espécies. Nas unidades fitogeográficas analisadas, a correspondência entre o gradiente ambiental (solo e topografia) e a abundância das espécies foi significativa, especialmente na Savana Florestada onde observou-se a maior relação. O solo e a topografia também se relacionaram com a semelhança na composição florística das subparcelas, com exceção da Floresta Estacional Semicidual (EEC). As principais variáveis de solo e topografia relacionadas a flora em cada UC foram: (1) Na Floresta Ombrófila Densa de Terras Baixas (PEIC) - teor de alumínio na camada profunda (Al (80-100 cm)) que pode refletir os teor de Al na superfície, acidez do solo (pH(H2O) (5-25 cm)) e altitude, que delimitou as áreas alagadas; (2) Na Floresta Ombrófila Densa Submontana (PECB) - altitude, fator que, devido ao relevo acidentado, influencia a temperatura e incidência de sol no sub-bosque; (3) Na Savana Florestada (EEA) - fertilidade, tolerância ao alumínio e acidez do solo. Nos modelos de predição BRT, as variáveis químicas dos solos foram mais importantes do que a textura, devido à pequena variação deste atributo no solo nas áreas amostradas. Dentre as variáveis químicas dos solos, a capacidade de troca catiônica foi utilizada para prever a ocorrência das espécies nas quatro formações florestais, sendo particularmente importante na camada mais profunda do solo da Floresta Ombrófila Densa de Terras Baixas (PEIC). Quanto à topografia, a altitude foi inserida na maioria dos modelos e apresentou diferentes influências sobre as áreas de estudo. De modo geral, para presença das espécies de ampla distribuição observou-se uma mesma tendência quando à associação com os atributos dos solos, porém com amplitudes dos descritores edáficos que variaram de acordo com a área de estudo. A ocorrência de Guapira opposita e Syagrus romanzoffiana, cujo padrão variou conforme a escala, foi explicada por variáveis com padrões espaciais agregados que somaram entre 30% e 50% de importância relativa no modelo BRT. A presença de A. anthelmia, cujo padrão também apresentou certo nível de agregação, foi associada apenas a uma variável com padrão agregado, a altitude (21%), que pode ter exercido grande influência na distribuição da espécie ao delimitar áreas alagadas. T. guianensis se associou a variáveis ambientais preditoras com padrão espacial agregado que somaram cerca de 70% de importância relativa, o que deve ter sido suficiente para estabelecer o padrão agregado em todas as escalas. No entanto, a influência dos fatores ambientais no padrão de distribuição da espécie não depende apenas do ótimo ambiental da espécie, mas um resultado da interação espécie-ambiente. Concluiu-se que: (I) características edáficas e topográficas explicaram uma pequena parcela da composição florística, em cada unidade fitogeográfica, embora a ocorrência de algumas espécies tenha se associado ao gradiente edáfico e topográfico; (II) a partir de características dos solos e da topografia foi possível prever a presença de espécies arbóreas, que apresentaram particularidades em relação a sua associação com o solo de cada fitofisionomia; (III) a partir de associações descritivas o solo e a topografia influenciam o padrão de distribuição espacial das espécies, na proporção em que contribuem para a presença das mesmas.