Multi-attribute recognition is one of the main topics attaining much attention in the pattern recognition field these days. The conventional approaches to multi-attribute recognition has mainly focused on developing an individual classifier for each attribute. However, due to rapid growth of deep learning techniques, multi-attribute recognition using multi-task learning enables the simultaneous recognition of more than two relevant recognition tasks through a single network. A number of studies on multi-task learning have shown that it is effective in improving recognition performance for all tasks when related tasks are learned together. However, since there are no specific criteria for determining the relationship among attributes, it is difficult and confusing to choose a good combination of tasks that have a positive impact on recognition performance. As one way to solve this problem, we propose a multi-attribute recognition method based on the novel output representations of a deep learning network which automatically learns the exclusive and joint relationship among attribute recognition tasks. We apply our proposed method to multi-attribute recognition of facial images, and confirm the effectiveness through experiments on a benchmark database.
Neyman–Scott rectangular pulse is a stochastic rainfall model with five parameters. The impacts of initial values and optimization methods on the parameter estimation of the Neyman–Scott rectangular pulse model were investigated using both the method of moments and the method of maximum likelihood. The estimates using the method of moments were influenced by the optimization method and were sensitive to the initial values and the aggregation scale of the data. Thus, by using frequentist estimation methods, we cannot guarantee the unique values as estimates. The aim of this study is to find more reliable unique values as estimates using a Bayesian approach. In this approach, parameters are estimated from the posterior distribution, and model performance is assessed by comparing observed values with fitted values. Slice sampling within the Gibbs sampler algorithm demonstrates superior convergence and model fitting, yielding unique estimates for the model parameters. The main conclusion of this study is that Bayesian estimation methods outperform other estimation methods in terms of providing reliable and stable estimates that improve rainfall generation accuracy.
31 March 2019 in Communications for Statistical Applications and Methods
Resumo Objetivos Identificar fatores preditivos de maus-tratos ao idoso relacionados a idosos e seus principais cuidadores e a relação entre formação profissional de saúde e identificação de maus-tratos. Métodos Estudo quantitativo e analítico. Os potenciais fatores de risco para maus-tratos relacionados a 40 idosos e seus cuidadores foram coletados por meio da observação de 12 profissionais de saúde e em uma associação de enfermeiras visitantes. O treinamento de profissionais de saúde na identificação de maus-tratos foi investigado. Estatística descritiva, teste [...] Resumo Objetivos Identificar fatores preditivos de maus-tratos ao idoso relacionados a idosos e seus principais cuidadores e a relação entre formação profissional de saúde e identificação de maus-tratos. Métodos Estudo quantitativo e analítico. Os potenciais fatores de risco para maus-tratos relacionados a 40 idosos e seus cuidadores foram coletados por meio da observação de 12 profissionais de saúde e em uma associação de enfermeiras visitantes. O treinamento de profissionais de saúde na identificação de maus-tratos foi investigado. Estatística descritiva, teste
1 March 2011 in Journal of the Korean Statistical Society