Search results for "extreme"
showing 10 items of 319 documents
Mislabel Detection of Finnish Publication Ranks
2019
The paper proposes to analyze a data set of Finnish ranks of academic publication channels with Extreme Learning Machine (ELM). The purpose is to introduce and test recently proposed ELM-based mislabel detection approach with a rich set of features characterizing a publication channel. We will compare the architecture, accuracy, and, especially, the set of detected mislabels of the ELM-based approach to the corresponding reference results on the reference paper.
Bayesian inference for the extremal dependence
2016
A simple approach for modeling multivariate extremes is to consider the vector of component-wise maxima and their max-stable distributions. The extremal dependence can be inferred by estimating the angular measure or, alternatively, the Pickands dependence function. We propose a nonparametric Bayesian model that allows, in the bivariate case, the simultaneous estimation of both functional representations through the use of polynomials in the Bernstein form. The constraints required to provide a valid extremal dependence are addressed in a straightforward manner, by placing a prior on the coefficients of the Bernstein polynomials which gives probability one to the set of valid functions. The…
Extreme value theory versus traditional GARCH approaches applied to financial data: a comparative evaluation
2013
Although stock prices fluctuate, the variations are relatively small and are frequently assumed to be normally distributed on a large time scale. But sometimes these fluctuations can become determinant, especially when unforeseen large drops in asset prices are observed that could result in huge losses or even in market crashes. The evidence shows that these events happen far more often than would be expected under the generalised assumption of normally distributed financial returns. Thus it is crucial to model distribution tails properly so as to be able to predict the frequency and magnitude of extreme stock price returns. In this paper we follow the approach suggested by McNeil and Frey …
Flood Frequency Analysis for Sicily, Italy
2006
In this paper a regional flood frequency analysis based on the two-component extreme value TCEV distribution is developed using flood data recorded in Sicily. The hierarchical approach, characterized by three investigation levels for estimating the parameters of the theoretical distribution, is discussed first. The highest level of homogeneity hypothesis with regard to the skewness coefficient was verified by using a Monte Carlo technique and taking account of the separation effect proposed by Matalas et al. in 1975. This analysis also showed 1 the inability of the generalized extreme value model to reproduce the empirical cumulative distribution function CDF of the skewness coefficients, a…
Core (XUV/VUV) and boundary (UV/vis/IR) plasma spectroscopy in fusion devices
2021
This contribution describes the basic applications of passive optical emission spectroscopy in the visible and far-UV region of electromagnetic radiation to diagnostics of the magnetic confinement fusion plasma. To simplify and condense the broad topic it presents the most common ways of analyzing the spectra of atoms, ions and molecules in fusion plasma and disseminating results of those analysis to the non-spectroscopists. It provides the reasons for choosing some particular regions, elements and charge states to determine the impurity content and plasma-surface interactions in MCF (Magnetic Confinement Fusion) reactor. Examples used in the contribution are predominantly from measurements…
Heat pipe controlled syntheses of ionic liquids in microstructured reactors
2009
Abstract The combination of a heat pipe and a microstructured reactor allows to perform highly exothermal reactions under safe conditions. First experiments for the synthesis of 1,3-dimethylimidazolium-triflate from 1-methylimidazol and methyl triflate showed that at high flow rates of more than 5 ml/min through a single 300 μm × 500 μm wide and 400 mm long channel quantitative conversion could be achieved. This chemical reaction, known for extreme heat release, can be retained under thermal control even at much higher flow rates.
Hardware implementation of real-time Extreme Learning Machine in FPGA: Analysis of precision, resource occupation and performance
2016
Extreme Learning Machine (ELM) on-chip learning is implemented on FPGA.Three hardware architectures are evaluated.Parametrical analysis of accuracy, resource occupation and performance is carried out. Display Omitted Extreme Learning Machine (ELM) proposes a non-iterative training method for Single Layer Feedforward Neural Networks that provides an effective solution for classification and prediction problems. Its hardware implementation is an important step towards fast, accurate and reconfigurable embedded systems based on neural networks, allowing to extend the range of applications where neural networks can be used, especially where frequent and fast training, or even real-time training…
The Logic of Gift: Inspiring behavior in organizations beyond the limits of duty and exchange
2016
[EN] Giving without the expectation of reward is difficult to understand in organizational contexts. In opposition to a logic based on self-interest or a sense of duty, a "logic of gift" has been proposed as a way to understand the phenomenon of free, unconditional giving. However, the rationale behind, and effects of, this logic have been under-explored. This paper responds by first clarifying the three logics of action¿the logic of exchange, the logic of duty, and the logic of gift¿and then explains how their balanced integration promises to enhance organizational life and outcomes. Having explicated the unique character and contributions of the logic of gift, the paper further suggests p…
Property loss potentials for European midlatitude storms in a changing climate
2007
[1] Winter storms of the midlatitudes are an important factor for property losses caused by natural hazards over Europe. The storm series in early 1990 and late 1999 led to enormous economic damages and insured claims. Although significant trends in North Atlantic/European storm activity have not been identified for the last few decades, recent studies provide evidence that under anthropogenic climate change the number of extreme storms could increase, whereas the total number of cyclones may be slightly reduced. In this study, loss potentials derived from an ensemble of climate models using a simple storm damage model under climate change conditions are shown. For the United Kingdom and Ge…
Geomorphologic Risk Modelling of the Sibiu Depression Using Geospatial Surface Analyses
2011
Extreme events in general, and the geomorphologic ones in particular, are highly topical problems. There were addresses by many researchers in the field of geology and physical geography (more specific by the climatologists and geomorphologists), but also by biologists, chemists, ecologists, etc. These are studied through the analysis of some types of processes and production mechanisms, and secondly by the effects they create on other environmental subsystems.