Search results for "Machine learning."
showing 10 items of 1455 documents
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.
Estimating the gravity equation with the actual number of exporting firms
2013
Para estimar correctamente el efecto de los costes de comerciar sobre las exportaciones de las empresas, la ecuación de gravedad debe controlar por el número de empresas que opera en el mercado internacional. Debido a la ausencia de datos, estudios anteriores han controlado esta variable mediante técnicas econométricas que también pueden generar estimaciones sesgadas. Para superar estos problemas este trabajo estima una ecuación de gravedad utilizando una nueva base de datos de la OCDE y EUROSTAT , que incluye el número de empresas exportadoras en cada relación bilateral. Nuestros resultados muestran que no controlar el margen extensivo genera sesgos muy importantes en la estimación de los …
Decision Committee Learning with Dynamic Integration of Classifiers
2000
Decision committee learning has demonstrated spectacular success in reducing classification error from learned classifiers. These techniques develop a classifier in the form of a committee of subsidiary classifiers. The combination of outputs is usually performed by majority vote. Voting, however, has a shortcoming. It is unable to take into account local expertise. When a new instance is difficult to classify, then the average classifier will give a wrong prediction, and the majority vote will more probably result in a wrong prediction. Instead of voting, dynamic integration of classifiers can be used, which is based on the assumption that each committee member is best inside certain subar…
Dynamic Integration of Decision Committees
2000
Decision committee learning has demonstrated outstanding success in reducing classification error with an ensemble of classifiers. In a way a decision committee is a classifier formed upon an ensemble of subsidiary classifiers. Voting, which is commonly used to produce the final decision of committees has, however, a shortcoming. It is unable to take into account local expertise. When a new instance is difficult to classify, then it easily happens that only the minority of the classifiers will succeed, and the majority voting will quite probably result in a wrong classification. We suggest that dynamic integration of classifiers is used instead of majority voting in decision committees. Our…
Dynamic integration with random forests
2006
Random Forests (RF) are a successful ensemble prediction technique that uses majority voting or averaging as a combination function. However, it is clear that each tree in a random forest may have a different contribution in processing a certain instance. In this paper, we demonstrate that the prediction performance of RF may still be improved in some domains by replacing the combination function with dynamic integration, which is based on local performance estimates. Our experiments also demonstrate that the RF Intrinsic Similarity is better than the commonly used Heterogeneous Euclidean/Overlap Metric in finding a neighbourhood for local estimates in the context of dynamic integration of …
Comparison of Different Hypotheses Regarding the Spread of Alzheimer’s Disease Using Markov Random Fields and Multimodal Imaging
2018
Alzheimer’s disease (AD) is characterized by a cascade of pathological processes that can be assessed in vivo using different neuroimaging methods. Recent research suggests a systematic sequence of pathogenic events on a global biomarker level, but little is known about the associations and dependencies of distinct lesion patterns on a regional level. Markov random fields are a probabilistic graphical modeling approach that represent the interaction between individual random variables by an undirected graph. We propose the novel application of this approach to study the interregional associations and dependencies between multimodal imaging markers of AD pathology and to compare different hy…
Comprehensive platelet phenotyping supports the role of platelets in the pathogenesis of acute venous thromboembolism - results from clinical observa…
2020
Background: The pathogenesis of arterial and venous thrombosis is in large part interlaced. How much platelet phenotype relates to acute venous thromboembolism (VTE) independent of the underlying cardiovascular profile is presently poorly investigated.Methods: Platelet count and mean platelet volume (MPV), platelet aggregation in whole blood and platelet rich plasma (PRP), platelet-dependent thrombin generation (TG) and platelet surface activation markers were measured under standardized conditions. Machine learning was applied to identify the most relevant characteristics associated with VTE from a large array (N = 58) of clinical and plateletrelated variables.Findings: VTE cases (N = 159)…
Application of machine learning techniques to analyse the effects of physical exercise in ventricular fibrillation
2014
This work presents the application of machine learning techniques to analyse the influence of physical exercise in the physiological properties of the heart, during ventricular fibrillation. To this end, different kinds of classifiers (linear and neural models) are used to classify between trained and sedentary rabbit hearts. The use of those classifiers in combination with a wrapper feature selection algorithm allows to extract knowledge about the most relevant features in the problem. The obtained results show that neural models outperform linear classifiers (better performance indices and a better dimensionality reduction). The most relevant features to describe the benefits of physical …
Profiling movement behaviours in pre-school children: A self-organised map approach.
2019
Application of machine learning techniques has the potential to yield unseen insights into movement and permits visualisation of complex behaviours and tangible profiles. The aim of this study was to identify profiles of relative motor competence (MC) and movement behaviours in pre-school children using novel analytics. One-hundred and twenty-five children (4.3 ± 0.5y, 1.04 ± 0.05 m, 17.8 ± 3.2 kg, BMI: 16.2 ± 1.9 kg
Distributed analysis of simultaneous EEG-fMRI time-series: modeling and interpretation issues
2009
Functional magnetic resonance imaging (fMRI) and electroencephalography (EEG) represent brain activity in terms of a reliable anatomical localization and a detailed temporal evolution of neural signals. Simultaneous EEG-fMRI recordings offer the possibility to greatly enrich the significance and the interpretation of the single modality results because the same neural processes are observed from the same brain at the same time. Nonetheless, the different physical nature of the measured signals by the two techniques renders the coupling not always straightforward, especially in cognitive experiments where spatially localized and distributed effects coexist and evolve temporally at different …