Search results for "Bust"

Robustas statistiskās metodes laikrindu analīzē

2019

Bakalaura darbā apskatītas robustas statistiskās metodes, ko piemēro laikrindām, ja datos ir izlēcēji. Aprakstīta robustā statistika, kāpēc tā ir nepieciešama, lūzuma punkts, novērtējumu definēšana. Apskatīti izlēcēju veidi, to ietekmes piemēri un varbūtību modeļi. Salīdzināti robustie un klasiskie novērtējumi dažādiem ARMA modeļiem. Robusta metode piemērota reālu datu piemēram.

NEW FRONTIERS OF ROBUST DESIGN WITH APPLICATION TO MOTORCYCLES.

2012

Data Augmentation for Pipeline-Based Speech Translation

2020

International audience; Pipeline-based speech translation methods may suffer from errors found in speech recognition system output. Therefore, it is crucial that machine translation systems are trained to be robust against such noise. In this paper, we propose two methods for parallel data augmentation for pipeline-based speech translation system development. The first method utilises a speech processing workflow to introduce errors and the second method generates commonly found suffix errors using a rule-based method. We show that the methods in combination allow significantly improving speech translation quality by 1.87 BLEU points over a baseline system.

Robust Neural Machine Translation: Modeling Orthographic and Interpunctual Variation

2020

Neural machine translation systems typically are trained on curated corpora and break when faced with non-standard orthography or punctuation. Resilience to spelling mistakes and typos, however, is crucial as machine translation systems are used to translate texts of informal origins, such as chat conversations, social media posts and web pages. We propose a simple generative noise model to generate adversarial examples of ten different types. We use these to augment machine translation systems’ training data and show that, when tested on noisy data, systems trained using adversarial examples perform almost as well as when translating clean data, while baseline systems’ performance drops by…

ECONOMIC ACTIVITY, CREDIT MARKET CONDITIONS, AND THE HOUSING MARKET

2017

In this paper, we assess the characteristics of the housing market and its main determinants. Using data for 20 industrial countries over the period 1970Q1–2012Q2 and a discrete-time Weibull duration model, we find that the likelihood of the end of a housing boom or a housing bust increases over time. Additionally, we show that the different phases of the housing market cycle are strongly dependent on the economic activity, but credit market conditions are particularly important in the case of housing booms. The empirical findings also indicate that although housing booms have similar lengths in European and non-European countries, housing busts are typically shorter in European countries. …

Macroeconomic performance and convergence in OECD countries

1996

Abstract This paper investigates the robustness of the correlation between growth and a set of variables which comprises accumulation rates in human and physical capital and medium term macroeconomic indicators in OECD countries. We include these variables as additional regressors in the standard growth equation that comes from the human capital-augmented Solow model. Our results show that variables related to medium term macroeconomic performance affect both growth and convergence. In some periods these variables even outperform the explanatory power of the conventional growth variables such as the accumulation rates. Our results also suggest that it is difficult to analyse the contributio…

On distributing quarterly national growth among regions

2008

In many countries a very important fraction of public expenditure is managed by regional authorities. However, in a world where economic life has quickened and become more turbulent, subnational institutions rarely have a timely regional macroeconomic picture at their disposal. The authors propose a guide to a method for estimating quarterly accounts of regions from the national quarterly and annual regional accounts, by the use of a temporal structure which eliminates possible spurious jumps. The robustness of the process and suggested practicalities are tested, and the proposal is also shown to produce better estimates than other uniregional methods often used in this framework.

Magnetic characteristics of industrial dust from different sources of emission: A case study of Poland

2015

Abstract Dust emission and deposition in topsoil have negative effect on individual components of the ecosystem. In addition to routine geochemical analyses, magnetic measurements may provide useful complementary information related to the type, concentration and grain-size distribution of the technogenic magnetic particles (TMPs) and thus the degree of contamination of the environment. The aim of this contribution is to use magnetic parameters in distinguishing dust from a wide range of sources of air pollution (power industry, cement, coke, ceramic industries and biomass combustion). We measured magnetic susceptibility, hysteresis parameters and thermomagnetic curves. Our results suggest …

Maximin Model Robust Discrete Choice Experiments

2013

Discrete choice experiments have their genesis in conjoint analysis, which was based on first-order models. For this and other reasons, discrete choice experiments in practice are usually designed for estimation of main effects. In this paper, we explore the construction of maximin model robust designs when the experimenter is concerned about the presence of interactions. We consider three classes of models—main effects models, main effects models plus first-order interactions, and secondorder models, and we construct designs that maximize the minimum efficiency of the design for the three competing models. We do so first with standard linear models and then extend our analysis to nonlinear…

An adapted optical flow algorithm for robust quantification of cardiac wall motion from standard cine-MR examinations

2012

International audience; This paper presents a method for local myocardial motion estimation from a conventional steady-state free precession cine-MRI sequence using a modified phase-based optical flow (OF) technique. Initially, the technique was tested on synthetic images to evaluate its robustness with regards to Rician noise and to brightness variations. The method was then applied to cardiac images acquired on 11 healthy subjects. Myocardial velocity is measured in centimeter per second in each studied pixel and visualized as colored vectors superimposed on MRI images. The estimated phase-based OF results were compared with a reference OF method and gave similar results on synthetic imag…