Examinando por Materia "CLASIFICACION"
Mostrando 1 - 4 de 4
Resultados por página
Opciones de ordenación
Trabajo final de especializaciónAnalysis and benchmarking for gravitational waves spectrogram’s classification by usage of machine learning techniques(2020-09-06) Martínez, Ezequiel H.; Ramele, Rodrigo"Gravitatonal waves, the seed of the 2015 Nobel’s prize are the cause of several complex celestial phenomena that is non-observable for the naked eye. Their identification, classification and study is s(ll a handmade work which is s(ll nascent. There has been several approaches to produce novel tools to aid the scientists behind the discovery of these deep space events. One of the most thrilling examples has been the usage of artificial intelligence classification to aid in the preiden identification of certain signals. We took one of these tools, Gravity Spy, and study its base paper, trying to reproduce some of their classification results using the very same base dataset. This research aims to compare the results obtained from the original paper, with a binary classification approach and several different algorithms taken from the knowledge base of machine learning and deep learning, alike. We confirmed the original paper results and obtained a new approach for the same solution. In this study we trained several models that could be used for further development of an eventual alternative engines for gravita(onal waves signal’s classification or any other sort of signal heavily influenced by noise and analysed by spectrograms." Ponencia en CongresoComparative study of robust methods for motor imagery classification based on CSP and LDA(2017-10) Villar, Ana Julia" Common spatial patterns analysis and linear discriminant analysis are popular algorithms for spatial filtering and classifying in motor imagery. These algorithms are very sensitive to noise and artifacts which affect the classification accuracy. To deal with this issue, it is proposed to replace the usual estimators of covariance and scale used in the algorithms for robust versions. The performance of the methods are evaluated and compared on EGG data from BCI competition data sets; results show that robust methods outperformed classical techniques for subjects with poor classification accuracy. " Trabajo final de especializaciónLa prisión preventiva y su relación con el tipo de delito y la superpoblación en el Servicio Penitenciario Federal Argentino(2020-04-06) Recalde Chamorro, Carlos Gustavo; Soliani, Valeria"En el presente trabajo, se propone analizar y estudiar las distintas variables de la población carcelaria aplicando distintas metodologías de análisis como algoritmos de clasificación, obteniendo así patrones y conductas que determinen en conclusiones para prevenir y mejorar del sistema carcelario." Artículo de Publicación PeriódicaA simple and fast representation space for classifying complex time series(2017-03) Zunino, Luciano; Olivares, Felipe; Fernández Bariviera, Aurelio; Rosso, Osvaldo A."In the context of time series analysis considerable effort has been directed towards the implementation of efficient discriminating statistical quantifiers. Very recently, a simple and fast representation space has been introduced, namely the number of turning points versus the Abbe value. It is able to separate time series from stationary and non-stationary processes with long-range dependences. In this work we show that this bidimensional approach is useful for distinguishing complex time series: different sets of financial and physiological data are efficiently discriminated. Additionally, a multiscale generalization that takes into account the multiple time scales often involved in complex systems has been also proposed. This multiscale analysis is essential to reach a higher discriminative power between physiological time series in health and disease. "