A simple PI tuning rule for integrating plus dead time (IPDT) systems, with large parametric uncertainty, is developed. In order to deal with parametric uncertainty a family of plants is considered. The design specifi...
详细信息
A simple PI tuning rule for integrating plus dead time (IPDT) systems, with large parametric uncertainty, is developed. In order to deal with parametric uncertainty a family of plants is considered. The design specifications are upper bounds on the sensitivity and the complementary sensitivity functions, that must be satisfied for any element belonging to the plants set. When applied to a system without uncertainty (or with no significant uncertainty) the well-known SIMC tuning rule is recovered. To conclude, several examples are analyzed to illustrate the proposed tuning rule.
In this paper we utilize Bayesian modeling and inference to learn a softmax classification model which performs Supervised Classification and Active Learning. For p p-priors are used to impose sparsity on the adaptive...
详细信息
Many real classification tasks are oriented to sequence (neighbor) labeling, that is, assigning a label to every sample of a signal while taking into account the sequentiality (or neighborhood) of the samples. This is...
详细信息
In public vs. private solutions (i.e. Cloud vs. In-house, or leased vs. Owned) for storage, both alternatives have their pros and cons. Cloud storage can easily adapt to the company needs, but exhibits a higher unit c...
详细信息
In public vs. private solutions (i.e. Cloud vs. In-house, or leased vs. Owned) for storage, both alternatives have their pros and cons. Cloud storage can easily adapt to the company needs, but exhibits a higher unit cost than in-house solutions. On the other hand, if the company relies on its own storage equipment, it must periodically purchase it on the basis of forecasts, which may prove imprecise and lead to idle equipment. In this paper, we propose a comparative evaluation tool for the two procurement approaches, where the cloud can play the role of either exclusive storage medium or supplement to in-house equipment (in the case of underestimation of storage needs). The tool considers the impact of equipment acquisition intervals and forecast accuracy over a long time horizon, adopting a Geometric Brownian Motion model for the evolution of storage capacity needs, it can be employed as a decision support tool for procurement decisions.
An interval estimate is provided for the Herfindahl-Hirschman Index (HHI) when the knowledge about the market is incomplete, and we know just the largest market shares. Two rigorous bounds are provided for the HHI, wi...
详细信息
An interval estimate is provided for the Herfindahl-Hirschman Index (HHI) when the knowledge about the market is incomplete, and we know just the largest market shares. Two rigorous bounds are provided for the HHI, without any further assumptions. Though the interval gets wider as the sum of the known market shares gets smaller, the estimate proves to be quite tight even when the fraction of the market that we do not know in detail is as high as 30%. This robustness is shown through three examples, considering respectively a set of real data and two sets of synthetic data, with the company sizes (a proxy for market shares) following respectively a Zipf law and a Pareto distribution.
In this paper we utilize Bayesian modeling and inference to learn a softmax classification model which performs Supervised Classification and Active Learning. For p < 1, l_p-priors are used to impose sparsity on th...
详细信息
ISBN:
(纸本)9781479946037
In this paper we utilize Bayesian modeling and inference to learn a softmax classification model which performs Supervised Classification and Active Learning. For p < 1, l_p-priors are used to impose sparsity on the adaptive parameters. Using variational inference, all model parameters are estimated and the posterior probabilities of the classes given the samples are calculated. A relationship between the prior model used and the independent Gaussian prior model is provided. The posterior probabilities are used to classify new samples and to define two Active Learning methods to improve classifier performance: Minimum Probability and Maximum Entropy. In the experimental section the proposed Bayesian framework is applied to Image Segmentation problems on both synthetic and real datasets, showing higher accuracy than state-of-the-art approaches.
General Concept Inclusion (GCIs) absorption algorithms have shown to play an important role in classical Description Logics (DLs) reasoners, as they allow to transform GCIs into simpler forms to which apply specialise...
详细信息
General Concept Inclusion (GCIs) absorption algorithms have shown to play an important role in classical Description Logics (DLs) reasoners, as they allow to transform GCIs into simpler forms to which apply specialised inference rules, resulting in an important performance gain. In this work, we develop a first absorption algorithm for fuzzy DLs, and evaluate it over some ontologies.
Fuzzy Description Logics (DLs) are a formalism for the representation of structured knowledge that is imprecise or vague by nature. In fuzzy DLs, restricting to a finite set of degrees of truth has proved to be useful...
详细信息
Many real classification tasks are oriented to sequence (neighbor) labeling, that is, assigning a label to every sample of a signal while taking into account the sequentiality (or neighborhood) of the samples. This is...
详细信息
ISBN:
(纸本)9781479957521
Many real classification tasks are oriented to sequence (neighbor) labeling, that is, assigning a label to every sample of a signal while taking into account the sequentiality (or neighborhood) of the samples. This is normally approached by first filtering the data and then performing classification. In consequence, both processes are optimized separately, with no guarantee of global optimality. In this work we utilize Bayesian modeling and inference to jointly learn a classifier and estimate an optimal filterbank. Variational Bayesian inference is used to approximate the posterior distributions of all unknowns, resulting in an iterative procedure to estimate the classifier parameters and the filterbank coefficients. In the experimental section we show, using synthetic and real data, that the proposed method compares favorably with other classification/filtering approaches, without the need of parameter tuning.
The ubiquitous learning is used as a means of supporting teaching processes by means of the use of mobile and wireless communication technologies, sensors and tracking mechanisms / tracking, working together to integr...
详细信息
The ubiquitous learning is used as a means of supporting teaching processes by means of the use of mobile and wireless communication technologies, sensors and tracking mechanisms / tracking, working together to integrate students with their environment. The process of clinical learning for nursing students may be the main cause of increased stress on teachers and students, given the problematic nature of the patients. This paper presents an ubiquitous learning system based on active learning methodology that provides context awareness support for nursing courses. An experiment with control and experimental groups with nursing students demonstrates that for theoretical concepts to be successfully transferred into practice, the context of practice needs to be considered.
暂无评论