The Self-Organizing Map (SOM) is a type of neural network that forms a regular grid of neurons where clusters of neurons represent different classes of targets. The aim of this thesis is to design electromagnetic target classifiers by using the Self-Organizing Map (SOM) type artificial neural networks for dielectric and conducting objects with simple or complex geometries. Design simulations will be realized for perfect dielectric spheres and also for small-scaled aircraft targets modeled by thin conducting wires. The SOM classifiers will be designed by target features extracted from the scattered signals of targets at various aspects by using the Wigner distribution. Noise performance of classifiers will be improved by using slightly noisy input data in SOM training.

The response of geological materials at the scale of meters and the response of buried targets of different shapes and sizes using controlled-source electromagnetic induction (CSEM) is investigated. This dissertation focuses on three topics; i) frac- tal properties on electric conductivity data from near-surface geology and processing techniques for enhancing man-made target responses, ii) non-linear inversion of spa- tiotemporal data using continuation method, and iii) classification of CSEM transient and spatiotemporal data. In the first topic, apparent conductivity profiles and maps were studied to de- termine self-affine properties of the geological noise and the effects of man-made con- ductive metal targets. 2-D Fourier transform and omnidirectional variograms showed that variations in apparent conductivity exhibit self-affinity, corresponding to frac- tional Brownian motion. Self-affinity no longer holds when targets are buried in the near-surface, making feasible the use of spectral methods to determine their pres- ence. The difference between the geology and target responses can be exploited using wavelet decomposition. A series of experiments showed that wavelet filtering is able to separate target responses from the geological background. In the second topic, a continuation-based inversion method approach is adopted, based on path-tracking in model space, to solve the non-linear least squares prob- lem for unexploded ordnance (UXO) data. The model corresponds to a stretched- exponential decay of eddy currents induced in a magnetic spheroid. The fast inversion of actual field multi-receiver CSEM responses of inert, buried ordnance is also shown. Software based on the continuation method could be installed within a multi-receiver CSEM sensor and used for near-real-time UXO decision. In the third topic, unsupervised self-organizing maps (SOM) were adapted for data clustering and classification. The use of self-organizing maps (SOM) for central- loop CSEM transients shows potential capability to perform classification, discrimi- nating background and non-dangerous items (clutter) data from, for instance, unex- ploded ordnance. Implementation of a merge SOM algorithm showed that clustering and classification of spatiotemporal CSEM data is possible. The ability to extract tar- get signals from a background-contaminated pattern is desired to avoid dealing with forward models containing subsurface response or to implement processing algorithm to remove, to some degree, the effects of background response and the target-host interactions.

<p>Recent literature has investigated the use of different clustering techniques for analysis of gene expression data. For example, self-organizing maps (SOMs) have been used to identify gene clusters of clear biological relevance in human hematopoietic differentiation and the yeast cell cycle (Tamayo et al., 1999). Hierarchical clustering has also been proposed for identifying clusters of genes that share common roles in cellular processes (Eisen et al., 1998; Michaels et al., 1998; Wen et al., 1998). Systematic evaluation of clustering results is as important as generating the clusters. However, this is a difficult task, which is often overlooked in gene expression studies. Several gene expression studies claim success of the clustering algorithm without showing a validation of complete clusterings, for example Ben-Dor and Yakhini (1999) and Törönen et al. (1999).</p><p>In this dissertation we propose an evaluation approach based on a relative entropy measure that uses additional knowledge about genes (gene annotations) besides the gene expression data. More specifically, we use gene annotations in the form of an enzyme classification hierarchy, to evaluate clusterings. This classification is based on the main chemical reactions that are catalysed by enzymes. Furthermore, we evaluate clusterings with pure statistical measures of cluster validity (compactness and isolation).</p><p>The experiments include applying two types of clustering methods (SOMs and hierarchical clustering) on a data set for which good annotation is available, so that the results can be partly validated from the viewpoint of biological relevance.</p><p>The evaluation of the clusters indicates that clusters obtained from hierarchical average linkage clustering have much higher relative entropy values and lower compactness and isolation compared to SOM clusters. Clusters with high relative entropy often contain enzymes that are involved in the same enzymatic activity. On the other hand, the compactness and isolation measures do not seem to be reliable for evaluation of clustering results.</p>

Este estudo propõe um modelo híbrido que reúne uma rede neural do tipo SOM (Self-Organizing Map) com uma rede neural do tipo Multicamadas com Retropropagação (BPN: Backpropagation Network). A utilização da rede SOM tem o intuito de segmentar a base de dados em diversos clusters, onde são ressaltadas suas diferenças. A rede BPN é usada para construir um modelo matemático de previsão que descreve a relação entre os indicadores e o valor de fechamento de cada cluster formado na rede SOM. A viabilidade e o percentual de efetividade do modelo proposto são demonstrados através de experimentos de predição de índices utilizados pelo NYSE (New York Stock Exchange). O modelo foi elaborado a partir de uma base de dados composta pelo índice NYSE Composite U.S. 100 no período entre 02 de abril de 2004 a 08 de novembro de 2012. Como variáveis de entrada para as redes neurais, foram utilizados 10 índices: MA_10, BIAS_20, WMS%R_9, K_9, D_9, MTM_10, ROC_10, CCI_24, AR_26, BR_26. Os resultados obtidos com o modelo híbrido proposto se mostraram superiores aos obtidos com modelos convencionais estatísticos. / This study proposes a hybrid model that combines a neural network SOM (Self-Organizing Map) with a neural network with Multilayer Backpropagation (BPN: Backpropagation Network). The SOM aims to segment the database into different clusters, where they highlight their differences. The BPN network is used to build a predictive mathematical model that describes the relationship between the indicators and the closing value of each cluster formed in the SOM. The percentage of viability and effectiveness of the proposed model are demonstrated through experiments predict index used by the NYSE (New York Stock Exchange). The model was developed from a database composed of 100 U.S. NYSE Composite Index in the period from April, 02, 2004 to November, 08, 2012. As input variables for neural networks, we used 10 indices: MA_10, BIAS_20, WMS%R_9, K_9, D_9, MTM_10, ROC_10, CCI_24, AR_26, BR_26. Results obtained with the proposed hybrid model were higher than those obtained with conventional statisticals techniques.

No description available.

No description available.

Este estudo propõe um modelo híbrido que reúne uma rede neural do tipo SOM (Self-Organizing Map) com uma rede neural do tipo Multicamadas com Retropropagação (BPN: Backpropagation Network). A utilização da rede SOM tem o intuito de segmentar a base de dados em diversos clusters, onde são ressaltadas suas diferenças. A rede BPN é usada para construir um modelo matemático de previsão que descreve a relação entre os indicadores e o valor de fechamento de cada cluster formado na rede SOM. A viabilidade e o percentual de efetividade do modelo proposto são demonstrados através de experimentos de predição de índices utilizados pelo NYSE (New York Stock Exchange). O modelo foi elaborado a partir de uma base de dados composta pelo índice NYSE Composite U.S. 100 no período entre 02 de abril de 2004 a 08 de novembro de 2012. Como variáveis de entrada para as redes neurais, foram utilizados 10 índices: MA_10, BIAS_20, WMS%R_9, K_9, D_9, MTM_10, ROC_10, CCI_24, AR_26, BR_26. Os resultados obtidos com o modelo híbrido proposto se mostraram superiores aos obtidos com modelos convencionais estatísticos. / This study proposes a hybrid model that combines a neural network SOM (Self-Organizing Map) with a neural network with Multilayer Backpropagation (BPN: Backpropagation Network). The SOM aims to segment the database into different clusters, where they highlight their differences. The BPN network is used to build a predictive mathematical model that describes the relationship between the indicators and the closing value of each cluster formed in the SOM. The percentage of viability and effectiveness of the proposed model are demonstrated through experiments predict index used by the NYSE (New York Stock Exchange). The model was developed from a database composed of 100 U.S. NYSE Composite Index in the period from April, 02, 2004 to November, 08, 2012. As input variables for neural networks, we used 10 indices: MA_10, BIAS_20, WMS%R_9, K_9, D_9, MTM_10, ROC_10, CCI_24, AR_26, BR_26. Results obtained with the proposed hybrid model were higher than those obtained with conventional statisticals techniques.

nÃo hà / In this dissertation it is reported the results of a comprehensive comparative study involving six local models applied to the task of learning the inverse kinematics of three redundant robotic arm (planar, PUMA 560 and Motoman HP6). The evaluated algorithms are the following ones: radial basis functions network (RBFN), local model network (LMN), SOMbased local linear mapping (LLM), local linear mapping over k-winners (K-SOM), local weighted regression (LWR) and counter propagation (CP). Each algorithm is evaluated with respect to its accuracy in estimating the joint angles given the cartesian coordinates which comprise end-effector trajectories within the robot workspace. A comprehensive evaluation of the performances of the aforementioned algorithms is carried out based on correlation analysis of the residuals. Finally, hypothesis testing procedures are also executed in order to verifying if there are significant differences in performance among the best algorithms. / Nesta dissertaÃÃo sÃo reportados os resultados de um amplo estudo comparativo envolvendo seis modelos locais aplicados à tarefa de aproximaÃÃo do modelo cinemÃtico inverso de 3 robÃs manipuladores (planar, PUMA 560 e Motoman HP6). Os modelos avaliados sÃo os seguintes: rede de funÃÃes de base radial (RBFN), rede de modelos locais (LMN), mapeamento linear local baseado em SOM (LLM), mapeamento linear local usando K vencedores (KSOM), regressÃo local ponderada (LWR) e rede counterpropagation (CP). Estes algoritmos sÃo avaliados quanto à acurÃcia na estimaÃÃo dos Ãngulos das juntas dos robÃs manipuladores em experimentos envolvendo a geraÃÃo de vÃrios tipos de trajetÃrias no espaÃo de trabalho dos referidos robÃs. Uma avaliaÃÃo abrangente do desempenho de cada algoritmo à feita com base na anÃlise dos resÃduos e testes de hipÃteses sÃo realizados para verificar a semelhanÃa estatistica entre os desempenhos dos melhores algoritmos.

Este estudo propõe um modelo híbrido que reúne uma rede neural do tipo SOM (Self-Organizing Map) com uma rede neural do tipo Multicamadas com Retropropagação (BPN: Backpropagation Network). A utilização da rede SOM tem o intuito de segmentar a base de dados em diversos clusters, onde são ressaltadas suas diferenças. A rede BPN é usada para construir um modelo matemático de previsão que descreve a relação entre os indicadores e o valor de fechamento de cada cluster formado na rede SOM. A viabilidade e o percentual de efetividade do modelo proposto são demonstrados através de experimentos de predição de índices utilizados pelo NYSE (New York Stock Exchange). O modelo foi elaborado a partir de uma base de dados composta pelo índice NYSE Composite U.S. 100 no período entre 02 de abril de 2004 a 08 de novembro de 2012. Como variáveis de entrada para as redes neurais, foram utilizados 10 índices: MA_10, BIAS_20, WMS%R_9, K_9, D_9, MTM_10, ROC_10, CCI_24, AR_26, BR_26. Os resultados obtidos com o modelo híbrido proposto se mostraram superiores aos obtidos com modelos convencionais estatísticos. / This study proposes a hybrid model that combines a neural network SOM (Self-Organizing Map) with a neural network with Multilayer Backpropagation (BPN: Backpropagation Network). The SOM aims to segment the database into different clusters, where they highlight their differences. The BPN network is used to build a predictive mathematical model that describes the relationship between the indicators and the closing value of each cluster formed in the SOM. The percentage of viability and effectiveness of the proposed model are demonstrated through experiments predict index used by the NYSE (New York Stock Exchange). The model was developed from a database composed of 100 U.S. NYSE Composite Index in the period from April, 02, 2004 to November, 08, 2012. As input variables for neural networks, we used 10 indices: MA_10, BIAS_20, WMS%R_9, K_9, D_9, MTM_10, ROC_10, CCI_24, AR_26, BR_26. Results obtained with the proposed hybrid model were higher than those obtained with conventional statisticals techniques.

Recent literature has investigated the use of different clustering techniques for analysis of gene expression data. For example, self-organizing maps (SOMs) have been used to identify gene clusters of clear biological relevance in human hematopoietic differentiation and the yeast cell cycle (Tamayo et al., 1999). Hierarchical clustering has also been proposed for identifying clusters of genes that share common roles in cellular processes (Eisen et al., 1998; Michaels et al., 1998; Wen et al., 1998). Systematic evaluation of clustering results is as important as generating the clusters. However, this is a difficult task, which is often overlooked in gene expression studies. Several gene expression studies claim success of the clustering algorithm without showing a validation of complete clusterings, for example Ben-Dor and Yakhini (1999) and Törönen et al. (1999). In this dissertation we propose an evaluation approach based on a relative entropy measure that uses additional knowledge about genes (gene annotations) besides the gene expression data. More specifically, we use gene annotations in the form of an enzyme classification hierarchy, to evaluate clusterings. This classification is based on the main chemical reactions that are catalysed by enzymes. Furthermore, we evaluate clusterings with pure statistical measures of cluster validity (compactness and isolation). The experiments include applying two types of clustering methods (SOMs and hierarchical clustering) on a data set for which good annotation is available, so that the results can be partly validated from the viewpoint of biological relevance. The evaluation of the clusters indicates that clusters obtained from hierarchical average linkage clustering have much higher relative entropy values and lower compactness and isolation compared to SOM clusters. Clusters with high relative entropy often contain enzymes that are involved in the same enzymatic activity. On the other hand, the compactness and isolation measures do not seem to be reliable for evaluation of clustering results.