Search results for "data models"
showing 10 items of 18 documents
Parallel Pairwise Epistasis Detection on Heterogeneous Computing Architectures
2016
This is a post-peer-review, pre-copyedit version of an article published in IEEE Transactions on Parallel and Distributed Systems. The final authenticated version is available online at: http://dx.doi.org/10.1109/TPDS.2015.2460247. [Abstract] Development of new methods to detect pairwise epistasis, such as SNP-SNP interactions, in Genome-Wide Association Studies is an important task in bioinformatics as they can help to explain genetic influences on diseases. As these studies are time consuming operations, some tools exploit the characteristics of different hardware accelerators (such as GPUs and Xeon Phi coprocessors) to reduce the runtime. Nevertheless, all these approaches are not able t…
Modelling and development of a generic observatory to harvest and analyze big data
2021
Big Data fascinate, both because of the value they hold that can provide a significant advantage in decision-making, and because of the challenges that their exploitation represents. These challenges are present at several levels of analytics workflows. At the level of the creation of software architectures, the volume and the velocity require at least enough performance to handle the ingestion and storage of data. The data variety has also an impact, as several new storage systems have emerged, each one corresponding to a specific need. The polystores are systems that integrate this diversity, to gain flexibility compared to the data warehouses, now too rigid. However, this diversification…
Advancing Deep Learning for Earth Sciences: From Hybrid Modeling to Interpretability
2020
Machine learning and deep learning in particular have made a huge impact in many fields of science and engineering. In the last decade, advanced deep learning methods have been developed and applied to remote sensing and geoscientific data problems extensively. Applications on classification and parameter retrieval are making a difference: methods are very accurate, can handle large amounts of data, and can deal with spatial and temporal data structures efficiently. Nevertheless, several important challenges need still to be addressed. First, current standard deep architectures cannot deal with long-range dependencies so distant driving processes (in space or time) are not captured, and the…
Deep Learning-Based Real-Time Object Detection in Inland Navigation
2019
International audience; Semi-autonomous and fully-autonomous systems must have knowledge about the objects in their environment to ensure a safe navigation. Modern approaches implement deep learning techniques to train a neural network for object detection. This project will study the effectiveness of using several promising algorithms such as Faster R-CNN, SSD, and different versions of YOLO, to detect, classify, and track objects in near real-time fluvial domain. Since no dataset is available for this purpose in literature, we first started by annotating a dataset of 2488 images with almost 35 400 annotations for training the convolutional neural network architectures. We made this data s…
RENT CREATION AND RENT SHARING: NEW MEASURES AND IMPACTS ON TOTAL FACTOR PRODUCTIVITY
2019
International audience; This analysis proposes new measures of rent creation and rent sharing and assesses their impact on productivity on cross-country-industry panel data. We find first that: (1) anticompetitive product market regulations positively affect rent creation and (2) employment protection legislation boosts hourly wages, particularly for low-skill workers. However, we find no significant impact of this employment legislation on rent sharing, as the hourly wage increases are offset by a negative impact on hours worked. Second, using regulation indicators as instruments, we find that rent creation and rent sharing both have a substantial negative impact on total factor productivi…
Explicación teórica y compromisos ontológicos : un modelo estructuralista
2021
En este ensayo me propongo esbozar un modelo de «explicación teórica con compromisos ontológicos». No se pretende que tal modelo tenga aplicación al uso de 'explicación' en la vida cotidiana, y ni siquiera que sea aplicable a todos los contextos científicos, tan sólo que tiene una significación genuina en grandes porciones de las ciencias naturales, particularmente en la física, y más generalmente en aquellas disciplinas que han sido matematizadas más o menos sistemáticamente. Mi tesis general, que voy a tratar de articular en lo que sigue, es simplemente la siguiente: al menos en muchos contextos de la ciencia teórica, la explicación adopta la forma de la inserción de una estructura de dat…
Requirement analysis for an artificial intelligence model for the diagnosis of the COVID-19 from chest X-ray data
2021
There are multiple papers published about different AI models for the COVID-19 diagnosis with promising results. Unfortunately according to the reviews many of the papers do not reach the level of sophistication needed for a clinically usable model. In this paper I go through multiple review papers, guidelines, and other relevant material in order to generate more comprehensive requirements for the future papers proposing a AI based diagnosis of the COVID-19 from chest X-ray data (CXR). Main findings are that a clinically usable AI needs to have an extremely good documentation, comprehensive statistical analysis of the possible biases and performance, and an explainability module.
Measuring the Rate of Information Transfer in Point-Process Data: Application to Cardiovascular Interactions
2021
We present the implementation to cardiovascular variability of a method for the information-theoretic estimation of the directed interactions between event-based data. The method allows to compute the transfer entropy rate (TER) from a source to a target point process in continuous time, thus overcoming the severe limitations associated with time discretization of event-based processes. In this work, the method is evaluated on coupled cardiovascular point processes representing the heartbeat dynamics and the related peripheral pulsation, first using a physiologically-based simulation model and then studying real point-process data from healthy subjects monitored at rest and during postural …
Dynamics of real labour productivity and real compensation in Latvia
2019
Relationship between labour productivity and wages is an important issue not only for economists, but also for policy makers. In the last decades, we have witnessed that in the EU15 wage growth has been lagging productivity growth. At the same time in Latvia, also in some other central and eastern European member states, wages increased more than productivity, rising concerns about disbalance in the economy. However, comparison of wage level and productivity level in Latvia and respective levels in the EU15 shows that wage level in Latvia is much below the EU15 average value in absolute terms, but also in relation to productivity level. To understand whether dissimilarities in wage and prod…
Low-Rank Tucker-2 Model for Multi-Subject fMRI Data Decomposition with Spatial Sparsity Constraint
2022
Tucker decomposition can provide an intuitive summary to understand brain function by decomposing multi-subject fMRI data into a core tensor and multiple factor matrices, and was mostly used to extract functional connectivity patterns across time/subjects using orthogonality constraints. However, these algorithms are unsuitable for extracting common spatial and temporal patterns across subjects due to distinct characteristics such as high-level noise. Motivated by a successful application of Tucker decomposition to image denoising and the intrinsic sparsity of spatial activations in fMRI, we propose a low-rank Tucker-2 model with spatial sparsity constraint to analyze multi-subject fMRI dat…