Listar por autor "Stoean, Catalin"
Mostrando ítems 1-5 de 5
-
Dynamic clustering of time series with Echo State Networks
Atencia-Ruiz, Miguel Alejandro
; Stoean, Catalin; Stoean, Ruxandra; Rodriguez Labrada, Roberto; Joya-Caparrós, Gonzalo (2019-06-05)
In this paper we introduce a novel methodology for unsupervised analysis of time series, based upon the iterative implementation of a clustering algorithm embedded into the evolution of a recurrent Echo State Network. The ... -
On Boosting the Accuracy of Medical Image Diagnosis through Cooperation between Classifiers
(2017-07-13)Each classifier has special inner workings that conduct to a specific separation between the samples that belong to various classes. Although two classifiers might lead to a similar prediction accuracy, the items from ... -
On classifying images using Keras and Tensorflow in Python
(2019-04-18)This hands-on presentation will be focused on practical, essential aspects that are necessary in order to build a custom classifier. The tutorial will start from prerequisites, like the libraries that are necessary to ... -
On Using Perceptual Loss within the U-Net Architecture for the Semantic Inpainting of Textile Artefacts with Traditional Motifs
Stoean, Catalin; Bacanin, Nebojsa; Stoean, Ruxandra; Ionescu, Leonard; Alecsa, Cristian; Hotoleanu, Mircea; Atencia-Ruiz, Miguel Alejandro; Joya-Caparrós, Gonzalo[et al.] (SYNACS Conference Publishing Service (CPS), 2022)
It is impressive when one gets to see a hundreds or thousands years old artefact exhibited in the museum, whose appearance seems to have been untouched by centuries. Its restoration had been in the hands of a multidisciplinary ... -
Unsupervised learning as a complement to convolutional neural network classification in the analysis of saccadic eye movement in spino-cerebellar ataxia type 2
Stoean, Catalin; Stoean, Ruxandra; Becerra-García, Roberto Antonio; Atencia-Ruiz, Miguel Alejandro; García-Lagos, Francisco; Velázquez-Pérez, Luis; Joya-Caparrós, Gonzalo; García-Bermúdez, Rodolfo[et al.] (2019-06-17)
This paper aims at assessing spino-cerebellar type 2 ataxiaby classifying electrooculography records into registers corresponding to healthy, presymptomatic and ill individuals. The primary used technique is the convolutional ...