The interdepartmental classification procedure survey.

Mode of access: Internet.

Data mining framework for fatty liver disease classification in ultrasound: a hybrid feature extraction paradigm

PURPOSE: Fatty liver disease (FLD) is an increasing prevalent disease that can be reversed if detected early. Ultrasound is the safest and ubiquitous method for identifying FLD. Since expert sonographers are required to accurately interpret the liver ultrasound images, lack of the same will result in interobserver variability. For more objective interpretation, high accuracy, and quick second opinions, computer aided diagnostic (CAD) techniques may be exploited. The purpose of this work is to develop one such CAD technique for accurate classification of normal livers and abnormal livers affected by FLD. METHODS: In this paper, the authors present a CAD technique (called Symtosis) that uses a novel combination of significant features based on the texture, wavelet transform, and higher order spectra of the liver ultrasound images in various supervised learning-based classifiers in order to determine parameters that classify normal and FLD-affected abnormal livers. RESULTS: On evaluating the proposed technique on a database of 58 abnormal and 42 normal liver ultrasound images, the authors were able to achieve a high classification accuracy of 93.3% using the decision tree classifier. CONCLUSIONS: This high accuracy added to the completely automated classification procedure makes the authors' proposed technique highly suitable for clinical deployment and usage.

Prediction of crude protein and classification of the growth stage of wheat plant samples from NIR spectra

Near-infrared spectroscopy (NIRS) was used to analyse the crude protein content of dried and milled samples of wheat and to discriminate samples according to their stage of growth. A calibration set of 72 samples from three growth stages of wheat (tillering, heading and harvest) and a validation set of 28 samples was collected for this purpose. Principal components analysis (PCA) of the calibration set discriminated groups of samples according to the growth stage of the wheat. Based on these differences, a classification procedure (SIMCA) showed a very accurate classification of the validation set samples : all of them were successfully classified in each group using this procedure when both the residual and the leverage were used in the classification criteria. Looking only at the residuals all the samples were also correctly classified except one of tillering stage that was assigned to both tillering and heading stages. Finally, the determination of the crude protein content of these samples was considered in two ways: building up a global model for all the growth stages, and building up local models for each stage, separately. The best prediction results for crude protein were obtained using a global model for samples in the two first growth stages (tillering and heading), and using a local model for the harvest stage samples.

Identification of Races of Selected Isolates of Uromyces appendiculatus from Minas Gerais (Brazil) Based on the new international classification system

Twelve single-pustule isolates of Uromyces appendiculatus, the etiological agent of common bean rust, were collected in the state of Minas Gerais, Brazil, and classified according to the new international differential series and the binary nomenclature system proposed during the 3rd Bean Rust Workshop. These isolates have been used to select rust-resistant genotypes in a bean breeding program conducted by our group. The twelve isolates were classified into seven different physiological races: 21-3, 29-3, 53-3, 53-19, 61-3, 63-3 and 63-19. Races 61-3 and 63-3 were the most frequent in the area. They were represented by five and two isolates, respectively. The other races were represented by just one isolate. This is the first time the new international classification procedure has been used for U. appendiculatus physiological races in Brazil. The general adoption of this system will facilitate information exchange, allowing the cooperative use of the results obtained by different research groups throughout the world. The differential cultivars Mexico 309, Mexico 235 and PI 181996 showed resistance to all of the isolates that were characterized. It is suggested that these cultivars should be preferentially used as sources for resistance to rust in breeding programs targeting development lines adapted to the state of Minas Gerais.

Is it possible to make pixel-based radar image classification user-friendly?

In this paper we would like to shed light the problem of efficiency and effectiveness of image classification in large datasets. As the amount of data to be processed and further classified has increased in the last years, there is a need for faster and more precise pattern recognition algorithms in order to perform online and offline training and classification procedures. We deal here with the problem of moist area classification in radar image in a fast manner. Experimental results using Optimum-Path Forest and its training set pruning algorithm also provided and discussed. © 2011 IEEE.

Exploring different approaches for music genre classification

In this letter, we present different approaches for music genre classification. The proposed techniques, which are composed of a feature extraction stage followed by a classification procedure, explore both the variations of parameters used as input and the classifier architecture. Tests were carried out with three styles of music, namely blues, classical, and lounge, which are considered informally by some musicians as being “big dividers” among music genres, showing the efficacy of the proposed algorithms and establishing a relationship between the relevance of each set of parameters for each music style and each classifier. In contrast to other works, entropies and fractal dimensions are the features adopted for the classifications.

The use of context in the classification of urban aerial imagery

Urban regions present some of the most challenging areas for the remote sensing community. Many different types of land cover have similar spectral responses, making them difficult to distinguish from one another. Traditional per-pixel classification techniques suffer particularly badly because they only use these spectral properties to determine a class, and no other properties of the image, such as context. This project presents the results of the classification of a deeply urban area of Dudley, West Midlands, using 4 methods: Supervised Maximum Likelihood, SMAP, ECHO and Unsupervised Maximum Likelihood. An accuracy assessment method is then developed to allow a fair representation of each procedure and a direct comparison between them. Subsequently, a classification procedure is developed that makes use of the context in the image, though a per-polygon classification. The imagery is broken up into a series of polygons extracted from the Marr-Hildreth zero-crossing edge detector. These polygons are then refined using a region-growing algorithm, and then classified according to the mean class of the fine polygons. The imagery produced by this technique is shown to be of better quality and of a higher accuracy than that of other conventional methods. Further refinements are suggested and examined to improve the aesthetic appearance of the imagery. Finally a comparison with the results produced from a previous study of the James Bridge catchment, in Darleston, West Midlands, is made, showing that the Polygon classified ATM imagery performs significantly better than the Maximum Likelihood classified videography used in the initial study, despite the presence of geometric correction errors.

Agroclimatic classification: numerical- taxonomic procedures - a review.

The paper catalogues the procedures and steps involved in agroclimatic classification. These vary from conventional descriptive methods to modern computer-based numerical techniques. There are three mutually independent numerical classification techniques, namely Ordination, Cluster analysis, and Minimum spanning tree; and under each technique there are several forms of grouping techniques existing. The vhoice of numerical classification procedure differs with the type of data set. In the case of numerical continuous data sets with booth positive and negative values, the simple and least controversial procedures are unweighted pair group method (UPGMA) and weighted pair group method (WPGMA) under clustering techniques with similarity measure obtained either from Gower metric or standardized Euclidean metric. Where the number of attributes are large, these could be reduced to fewer new attributes defined by the principal components or coordinates by ordination technique. The first few components or coodinates explain the maximum variance in the data matrix. These revided attributes are less affected by noise in the data set. It is possible to check misclassifications using minimum spanning tree.

Domain Adaptation in remote sensing: increasing the portability of land-cover classifiers

Among the types of remote sensing acquisitions, optical images are certainly one of the most widely relied upon data sources for Earth observation. They provide detailed measurements of the electromagnetic radiation reflected or emitted by each pixel in the scene. Through a process termed supervised land-cover classification, this allows to automatically yet accurately distinguish objects at the surface of our planet. In this respect, when producing a land-cover map of the surveyed area, the availability of training examples representative of each thematic class is crucial for the success of the classification procedure. However, in real applications, due to several constraints on the sample collection process, labeled pixels are usually scarce. When analyzing an image for which those key samples are unavailable, a viable solution consists in resorting to the ground truth data of other previously acquired images. This option is attractive but several factors such as atmospheric, ground and acquisition conditions can cause radiometric differences between the images, hindering therefore the transfer of knowledge from one image to another. The goal of this Thesis is to supply remote sensing image analysts with suitable processing techniques to ensure a robust portability of the classification models across different images. The ultimate purpose is to map the land-cover classes over large spatial and temporal extents with minimal ground information. To overcome, or simply quantify, the observed shifts in the statistical distribution of the spectra of the materials, we study four approaches issued from the field of machine learning. First, we propose a strategy to intelligently sample the image of interest to collect the labels only in correspondence of the most useful pixels. This iterative routine is based on a constant evaluation of the pertinence to the new image of the initial training data actually belonging to a different image. Second, an approach to reduce the radiometric differences among the images by projecting the respective pixels in a common new data space is presented. We analyze a kernel-based feature extraction framework suited for such problems, showing that, after this relative normalization, the cross-image generalization abilities of a classifier are highly increased. Third, we test a new data-driven measure of distance between probability distributions to assess the distortions caused by differences in the acquisition geometry affecting series of multi-angle images. Also, we gauge the portability of classification models through the sequences. In both exercises, the efficacy of classic physically- and statistically-based normalization methods is discussed. Finally, we explore a new family of approaches based on sparse representations of the samples to reciprocally convert the data space of two images. The projection function bridging the images allows a synthesis of new pixels with more similar characteristics ultimately facilitating the land-cover mapping across images.

EXPLORING THE DEVELOPMENT AND PSYCHOSOCIAL CORRELATES OF SPIRITUALITY /RELIGIOSITY ACROSS ADOLESCENCE

The goal of the four studies that comprised this dissertation was to examine how spirituality/religiosity (SIR), as both an institutional and personal phenomenon, developed over time, and how its institutional (i.e., religious activity involvement) and personal (i.e., sense of connection with the sacred) components were uniquely linked with psychosocial adjustment. In Study 1, the differential longitudinal correlates of religious service attendance, as compared to involvement in other clubs, were evaluated with a sample of adolescents (n=1050) who completed a survey in grades 9, 11 and 12. Religious attendance and involvement in non-religious clubs were uniquely associated with positive adjustment in terms of lower substance use and better academic marks, particularly when involvement was sustained over time. In Study 2, the direction of effects was tested for the association between religious versus non-religious activities and both substance use and academic marks. Participants (n= 3993) were surveyed in grades 9 through 12. Higher religious attendance (but not non-religious club involvement) in one grade predicted lower levels of substance use in the next grade. Higher levels of nonreligious club involvement (but not religious service attendance) in one grade predicted higher academic achievement in the next grade, and higher academic achievement in one grade predicted more frequent non-religious club involvement in the next grade. The results suggest that different assets may be fostered in religious as compared to nonreligious activities, and, specifically, religious activity involvement may be important for the avoidance of substance use. The goal of Study 3 was to assess the unique associations between the institutional versus personal dimensions of SIR and a wide range of domains of psychosocial adjustment (namely, intrapersonal well-being, substance use, risk attitudes, parental relationship quality, academic orientation, and club involvement), and to examine the direction of effects in these associations. Participants (n=756) completed a survey in grades 11 and 12. Personal and institutional dimensions of SIR were differentially associated with adjustment, but it may only be in the domain of risk-taking (Le., risk attitudes, substance use) that SIR may predict positive adjustment over time. Finally, in Study 4, the goal was to examine how institutional and personal aspects of SIR developed within individual adolescents. Configurations of mUltiple dimensions of spirituality/religiosity were identified across 2 time points with an empirical classification procedure (cluster analysis), and sample- and individual-level development in these configurations were assessed. A five cluster-solution was optimal at both grades. Clusters were identified as aspirituallirreligious, disconnected wonderers, high institutional and personal, primarily personal, and meditators. With the exception of the high institutional and personal cluster, the cluster structures were stable over time. There also was significant intraindividual stability in all clusters over time; however, a significant proportion of individuals classified as high institutional and personal in Grade 11 moved into the primarily personal cluster in Grade 12. This program of research represented an important step towards addressing some of the limitations within the body of literature; namely, the uniqueness of religious activity involvement as a structured club, the differential link between institutional versus personal SIR and psychosocial adjustment, the direction of effects in the associations between institutional versus personal SIR and adjustment, and the way in which different dimensions of SIR may be configured and develop within individual adolescents over time.

Uso da análise discriminante regularizada (RDA) no reconhecimento de padrões em imagens digitais hiperespectral de sensoriamento remoto

Em cenas naturais, ocorrem com certa freqüência classes espectralmente muito similares, isto é, os vetores média são muito próximos. Em situações como esta, dados de baixa dimensionalidade (LandSat-TM, Spot) não permitem uma classificação acurada da cena. Por outro lado, sabe-se que dados em alta dimensionalidade [FUK 90] tornam possível a separação destas classes, desde que as matrizes covariância sejam suficientemente distintas. Neste caso, o problema de natureza prática que surge é o da estimação dos parâmetros que caracterizam a distribuição de cada classe. Na medida em que a dimensionalidade dos dados cresce, aumenta o número de parâmetros a serem estimados, especialmente na matriz covariância. Contudo, é sabido que, no mundo real, a quantidade de amostras de treinamento disponíveis, é freqüentemente muito limitada, ocasionando problemas na estimação dos parâmetros necessários ao classificador, degradando portanto a acurácia do processo de classificação, na medida em que a dimensionalidade dos dados aumenta. O Efeito de Hughes, como é chamado este fenômeno, já é bem conhecido no meio científico, e estudos vêm sendo realizados com o objetivo de mitigar este efeito. Entre as alternativas propostas com a finalidade de mitigar o Efeito de Hughes, encontram-se as técnicas de regularização da matriz covariância. Deste modo, técnicas de regularização para a estimação da matriz covariância das classes, tornam-se um tópico interessante de estudo, bem como o comportamento destas técnicas em ambientes de dados de imagens digitais de alta dimensionalidade em sensoriamento remoto, como por exemplo, os dados fornecidos pelo sensor AVIRIS. Neste estudo, é feita uma contextualização em sensoriamento remoto, descrito o sistema sensor AVIRIS, os princípios da análise discriminante linear (LDA), quadrática (QDA) e regularizada (RDA) são apresentados, bem como os experimentos práticos dos métodos, usando dados reais do sensor. Os resultados mostram que, com um número limitado de amostras de treinamento, as técnicas de regularização da matriz covariância foram eficientes em reduzir o Efeito de Hughes. Quanto à acurácia, em alguns casos o modelo quadrático continua sendo o melhor, apesar do Efeito de Hughes, e em outros casos o método de regularização é superior, além de suavizar este efeito. Esta dissertação está organizada da seguinte maneira: No primeiro capítulo é feita uma introdução aos temas: sensoriamento remoto (radiação eletromagnética, espectro eletromagnético, bandas espectrais, assinatura espectral), são também descritos os conceitos, funcionamento do sensor hiperespectral AVIRIS, e os conceitos básicos de reconhecimento de padrões e da abordagem estatística. No segundo capítulo, é feita uma revisão bibliográfica sobre os problemas associados à dimensionalidade dos dados, à descrição das técnicas paramétricas citadas anteriormente, aos métodos de QDA, LDA e RDA, e testes realizados com outros tipos de dados e seus resultados.O terceiro capítulo versa sobre a metodologia que será utilizada nos dados hiperespectrais disponíveis. O quarto capítulo apresenta os testes e experimentos da Análise Discriminante Regularizada (RDA) em imagens hiperespectrais obtidos pelo sensor AVIRIS. No quinto capítulo são apresentados as conclusões e análise final. A contribuição científica deste estudo, relaciona-se à utilização de métodos de regularização da matriz covariância, originalmente propostos por Friedman [FRI 89] para classificação de dados em alta dimensionalidade (dados sintéticos, dados de enologia), para o caso especifico de dados de sensoriamento remoto em alta dimensionalidade (imagens hiperespectrais). A conclusão principal desta dissertação é que o método RDA é útil no processo de classificação de imagens com dados em alta dimensionalidade e classes com características espectrais muito próximas.

Texturas de imagens utilizando conceitos de morfologia matemática

A textura é um atributo ainda pouco utilizado no reconhecimento automático de cenas naturais em sensoriamento remoto, já que ela advém da sensação visual causada pelas variações tonais existentes em uma determinada região da imagem, tornando difícil a sua quantificação. A morfologia matemática, através de operações como erosão, dilatação e abertura, permite decompor uma imagem em elementos fundamentais, as primitivas texturais. As primitivas texturais apresentam diversas dimensões, sendo possível associar um conjunto de primitivas com dimensões semelhantes, em uma determinada classe textural. O processo de classificação textural quantifica as primitivas texturais, extrai as distribuições das dimensões das mesmas e separa as diferentes distribuições por meio de um classificador de máxima-verossimilhança gaussiana. O resultado final é uma imagem temática na qual cada tema representa uma das texturas existentes na imagem original.

Representação social sobre educação inclusiva por professores de Cruzeiro do Sul - Acre

Nowadays the discussion about providing a quality education for all students is more and more recurrent, including for those who have special educational necessities. The discussion increases regarding that it is not enough to include these students in the regular school, but also to provide conditions of learning and development. This requirement implies changes in the educational system, as well as in the teachers‟ everyday; and these changes manifest themselves through the complexity of the functions which are assigned to the teachers and the school. The news that are generated from the perspective of the inclusive education asks for new formative models for teacher‟s performance, once he tries to (re)build knowledge, knowings and doings among troubles and conflicts as a way to decrease the impact caused by the necessary transformations. This research approached this context in order to understand the social representation about the inclusive education from teachers who work in the regular public school system in the Municipality of Cruzeiro do Sul, State of Acre. To approach the symbolic content, we elected the Multiple Classification Procedure (MCP) as the methodological approach. For that, it was necessary to apply the Technique of Free-Association of Words (TFAW) to 60 participants what provided data to the first step of the chosen methodological procedure. The criterion of choice of the participants took into account if they dealt with student who has special educational necessities and with public schools. Later, we applied MCP to 50 teachers from specialized course in inclusive education subgroup 01 and 30 teachers who has no specialized formation subgroup 02. The collected data from this step was examined through multidimensional and content analysis for a better understanding of their symbolic dimensions. The results from the multidimensional analysis showed that the subject inclusive education‟ for subgroup 01 involved the following facets: circulating discourses that meant the naming of the characteristics that teachers think indispensable to inclusive education; teachers in relation to the inclusive practice that was focused on the relation between teaching and included student, and repercussion to the student that showed the advantages that the inclusive education provided to the student who has special educational necessities. Subgroup 02 dealt with the following facets: characteristics of the included student that approached teachers‟ view on this student; negative aspects that regarded the naming of the obstacles in the achievement of inclusive education; and teacher‟s relations to the inclusive education that approach professional, affective, and formative elements. The content analysis revealed four categories: disagreeing concepts; conception of inclusive education; dimension of the teacher‟s inclusive doing, and difficulties and resistance to carry out the inclusion of a student who has special educational necessities in the regularschool. Both analyses multidimensional and content one showed that the constitution of elements in a social representation of inclusive education was a mixture formed by the characteristics of this sort of education and the school integration, materialized on the figure of the different‟ student. The representational field of the subject inclusive education‟ was associated to the social representation of the student who has special educational necessities, making clear the deficiency/ difference, and causing the difficulty of the teachers in achieving what they say about the phenomenon

Como vão se formando os professores em física e química: embates entre o ser, o ter e o fazer na formação de licenciandos da UFRN sob a perspectiva da teoria das representações sociais

The purpose of this work is to approach and understand the Social Representations (SR) (MOSCOVICI, 2003) about Physics and Chemistry from people who are major in these courses, as well as their Social Representations about teaching . We took as principle that approaching these representations it would be possible to relate their symbolic contents, in order to show how people who are following the first segments of bachelor degree courses in Physics and Chemistry become teachers, taking into account a psychosocial view. Two source of data was used during this research: Free-association Technique FA (ABRIC, 1994); and Multiple Classification Procedure (MCP) (ROAZZI, 1995). The analytical treatment of the collected data from FA was done according to the proposition of Grize, Vergés and Silem (1987 apud ABRIC, 1994, p. 66). MCP data were analyzed through MSA (Multidimensional Scalogram Analysis) and SSA (Singular Spectrum Analysis) methods associated with the Facet Theory (BILSKY, 2003). The discourses of MCP discussing groups at the moment of explanations were studied by Content Analysis as it was proposed by Bardin (1977) and Franco (2005). Indicative of an approach to the relations with knowledge (CHARLOT, 2000), the connections which aroused from the analyses showed that the group of future majors in Physics thought that this scientific field was based on a rationalist conception, influencing the idealization sense of the phenomena to be explained by Physics. Thus, Physics as school content started to require the student of the fundamental and high school to think abstractly as a cognitive skill of learning. The identifying elements observed in the relations between SR about Physics and Teaching aroused from the antagonism between future majors and their teacher, as well as from the speculation between their fundamental and high school students and themselves, mainly when they had to face the act of teaching due to the obstacles imposed by the own educational system, and by the weakness of the initial preparation. The group of future majors in Chemistry, through its discourses, showed these relations when they conceived empiricist Chemistry and said that teaching was the way of transmission of this knowledge, and didactics of Chemistry teaching was the direction to learning through pedagogic methods in order to lead the students to discoveries. The psychosocial contents which were built and showed from the symbolic relations in the studied SR achieved the relation of identity. This relation revealed identifying elements for these people, resulting from the traffic between their condition as students of Chemistry, and as teachers regarding their work, what placed the current relational contents in the teaching space, named as Knowledge changing and Adaptability . In order to study emerging questions in the discussing environment about formation and teaching professionalization, we focused the psychosocial view on this traffic and managed to observe epistemological practical and pedagogic obstacles that limited a configuration of the teaching work as a professional activity, especially from the particular conditions which led the relations of senses to Physics , Chemistry and Teaching ; and Chemistry and Physics as it was seen in this research. Generally speaking, we noted that these obstacles can denounce such obstacles concerning to the pedagogic doings which mainly impair the learning process of fundamental and high school students

Dimensões didática, afetiva e formativa de docência que tecem as representações sociais entre licenciandos da UFPI

This study intends to analyze the social representation of teaching for students of first years of undergraduate courses in Education, Letters and Biology. The field of this research was the Federal University of Piaui - Campus of Picos in 2009. To reach the objective proposed above, was used the theory of social representations to the seizure of the elements which constitute such representations according to Moscovici and colleagues, considering the contribution of Abric with his Theory of Central Nucleus and Wagner with the Theory of Sociogenesis. Data were collected in two phases: first, through the Technique of Free Association of Words (TFAW) of which 100 subjects evoked representations of their teaching through the inductor terms 'to teach', 'student' and 'teacher'. For those data we used the EVOC software that promoted to detect the elements of the core and to conclude that the social representation of teaching is one of the work performed by a master / teacher who transmits, directed to an apprentice who learns, confined to the school involving the student with all his virtues to be smart, interested and dedicated, and teacher to be friend, wise bearer of knowledge and also intelligent. Then, using the Multiple Classification Procedure (MCP) only 10 subjects made ratings of 25 more evoked words in the first phase, for the analysis of data from the MPC with the use of the SPSS software we used Multidimensional Statistical Analysis (MSA) for the Free Classification we found three dimensions of Social Representation of Teaching: The Didactic, that focuses on teacher and student being superimposed, meaning the inseparability of these elements, the Affective, which presents the elements inherent in teachers with love as the strong point of this dimension, and the Formative, that is as ambiguous as ambivalent because it sees the teacher as a professional directed to help students get an education; for Directed Classification with Similarity Structure Analysis (SSA), we learn that teaching is a profession that materializes in the classroom, which is extremely true because the action happens in this teaching space, supposing a caring, loving, cheerful, capable, apt, patient, partner, responsible, dedicated, committed educator, who has wisdom and knows how to teach and help students through dialogue to there study and learning. All of it s necessary to occur the result of teaching, which is education in a disciplinary manner. The results point to a very traditional social representation of what is the role of teachers, the role of students and the role of the relationship itself between teaching and learning through the act of teaching. With this statement, we can confirm that the structure of Social Representation of Teaching for the investigated subjects reflects the sociogenetic conditions that engendered them, and that these conditions permeate their structural organization, in particular time-context in which social representation was captured