Search results for "ComputingMethodologies_PATTERNRECOGNITION"
showing 10 items of 296 documents
Exploring Multi-Objective Optimization for Multi-Label Classifier Ensembles
2019
Multi-label classification deals with the task of predicting multiple class labels for a given sample. Several performance metrics are designed in the literature to measure the quality of any multi-label classification technique. In general existing multi-label classification approaches focus on optimizing only a single performance measure. The current work builds on the hypothesis that a weighted ensemble of multiple multi-label classifiers will lead to obtain improved results. The appropriate weight combinations for combining the outputs of multiple classifiers can be selected after simultaneously optimizing different multi-label classification metrics like micro F1, hamming loss, 0/1 los…
Deformable object segmentation in ultra-sound images
2013
Breast cancer is the second most common type of cancer being the leading cause of cancer death among females both in western and in economically developing countries. Medical imaging is key for early detection, diagnosis and treatment follow-up. Despite Digital Mammography (DM) remains the reference imaging modality, Ultra-Sound (US) imaging has proven to be a successful adjunct image modality for breast cancer screening, specially as a consequence of the discriminative capabilities that US offers for differentiating between solid lesions that are benign or malignant. Despite US usability,US suffers inconveniences due to its natural noise that compromises the diagnosis capabilities of radio…
Hybrid CPU/GPU Acceleration of Detection of 2-SNP Epistatic Interactions in GWAS
2014
This is a post-peer-review, pre-copyedit version of an article published in Lecture Notes in Computer Science. The final authenticated version is available online at: https://doi.org/10.1007/978-3-319-09873-9_57 [Abstract] High-throughput genotyping technologies allow the collection of up to a few million genetic markers (such as SNPs) of an individual within a few minutes of time. Detecting epistasis, such as 2-SNP interactions, in Genome-Wide Association Studies is an important but time consuming operation since statistical computations have to be performed for each pair of measured markers. In this work we present EpistSearch, a parallelized tool that, following the log-linear model appr…
Classification of Pollen Apertures Using Bag of Words
2013
International audience; The taxonomical recognition of microscopic biological parti- cles such as pollen and spores is relevant for medical and aerobiological applications. Focusing on an accurate and automatic vision-based pollen recognition system, we propose a method for classification of pollen aper- tures based on bag-of-words strategy, with the ability of learning new types from different taxa without the need of new algorithms. Results demonstrate suitable performance and ability to add new taxa.
Measurement of the Charged-Pion Polarizability
2015
The COMPASS collaboration at CERN has investigated pion Compton scattering, $\pi^-\gamma\rightarrow \pi^-\gamma$, at centre-of-mass energy below 3.5 pion masses. The process is embedded in the reaction $\pi^-\mathrm{Ni}\rightarrow\pi^-\gamma\;\mathrm{Ni}$, which is initiated by 190\,GeV pions impinging on a nickel target. The exchange of quasi-real photons is selected by isolating the sharp Coulomb peak observed at smallest momentum transfers, $Q^2<0.0015$\,(GeV/$c$)$^2$. From a sample of 63\,000 events the pion electric polarisability is determined to be $\alpha_\pi\ =\ (\,2.0\ \pm\ 0.6_{\mbox{\scriptsize stat}}\ \pm\ 0.7_{\mbox{\scriptsize syst}}\,) \times 10^{-4}\,\mbox{fm}^3$ under the …
Neural Networks in ECG Classification
2011
In this chapter, we review the vast field of application of artificial neural networks in cardiac pathology discrimination based on electrocardiographic signals. We discuss advantages and drawbacks of neural and adaptive systems in cardiovascular medicine and catch a glimpse of forthcoming developments in machine learning models for the real clinical environment. Some problems are identified in the learning tasks of beat detection, feature selection/extraction, and classification, and some proposals and suggestions are given to alleviate the problems of interpretability, overfitting, and adaptation. These have become important problems in recent years and will surely constitute the basis of…
Shrinkage and spectral filtering of correlation matrices: A comparison via the Kullback-Leibler distance
2007
The problem of filtering information from large correlation matrices is of great importance in many applications. We have recently proposed the use of the Kullback-Leibler distance to measure the performance of filtering algorithms in recovering the underlying correlation matrix when the variables are described by a multivariate Gaussian distribution. Here we use the Kullback-Leibler distance to investigate the performance of filtering methods based on Random Matrix Theory and on the shrinkage technique. We also present some results on the application of the Kullback-Leibler distance to multivariate data which are non Gaussian distributed.
Precision Measurement of the Branching Fractions of η′ Decays
2019
PubMed ID: 31050481
Measurement of the Dynamics of the Decays Ds+→η(′)e+νe
2019
PubMed ID: 30978074
Models and solution methods for the uncapacitatedr-allocationp-hub equitable center problem
2017
Hub networks are commonly used in telecommunications and logistics to connect origins to destinations in situations where a direct connection between each origin–destination (o-d) pair is impractical or too costly. Hubs serve as switching points to consolidate and route traffic in order to realize economies of scale. The main decisions associated with hub-network problems include (1) determining the number of hubs (p), (2) selecting the p-nodes in the network that will serve as hubs, (3) allocating non-hub nodes (terminals) to up to r-hubs, and (4) routing the pairwise o-d traffic. Typically, hub location problems include all four decisions while hub allocation problems assume that the valu…