Mostrar el registro sencillo del ítem
Unsupervised learning as a complement to convolutional neural network classification in the analysis of saccadic eye movement in spino-cerebellar ataxia type 2
dc.contributor.author | Stoean, Catalin | |
dc.contributor.author | Stoean, Ruxandra | |
dc.contributor.author | Becerra-García, Roberto Antonio | |
dc.contributor.author | Atencia-Ruiz, Miguel Alejandro | |
dc.contributor.author | García-Lagos, Francisco | |
dc.contributor.author | Velázquez-Pérez, Luis | |
dc.contributor.author | Joya-Caparrós, Gonzalo | |
dc.contributor.author | García-Bermúdez, Rodolfo | |
dc.date.accessioned | 2019-06-17T12:20:35Z | |
dc.date.available | 2019-06-17T12:20:35Z | |
dc.date.created | 2019 | |
dc.date.issued | 2019-06-17 | |
dc.identifier.uri | https://hdl.handle.net/10630/17824 | |
dc.description | IWANN es un congreso internacional que se celebra bienalmente desde 1991. Su campo de estudio se centra en la fundamentación y aplicación de las distintas técnicas de Inteligencia Computacional : Redes Neuronales Artificiales, Algoritmos Genéticos, Lógica Borrosa, Aprendizaje Automático. En esta edición han participado 150 investigadores. | en_US |
dc.description.abstract | 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 neural network applied to the time series of eye movements, called saccades. The problem is exceptionally hard, though, because the recorded saccadic movements for presymptomatic cases often do not substantially di er from those of healthy individuals. Precisely this distinction is of the utmost clinical importance, since early intervention on presymptomatic patients can ameliorate symptoms or at least slow their progression. Yet, each register contains a number of saccades that, although not consistent with the current label, have not been considered indicative of another class by the examining physicians. As a consequence, an unsupervised learning mechanism may be more suitable to handle this form of misclassi cation. Thus, our proposal introduces the k-means approach and the SOM method, as complementary techniques to analyse the time series. The three techniques operating in tandem lead to a well performing solution to this diagnosis problem. | en_US |
dc.description.sponsorship | Universidad de Málaga. Campus de Excelencia Internacional Andalucía Tech. Universidad de Granada, Universitat Politècnica de Catalunya, Universidad de Las Palmas de Gran Canaria, Springer | en_US |
dc.language.iso | eng | en_US |
dc.rights | info:eu-repo/semantics/openAccess | en_US |
dc.subject | Redes neuronales artificiales | en_US |
dc.subject | Congresos y conferencias | en_US |
dc.subject.other | Classi cation; Convolutional Neural Networks; Unsupervised Learning; k-means; Self-Organizing Maps; Saccadic eye movement | en_US |
dc.title | Unsupervised learning as a complement to convolutional neural network classification in the analysis of saccadic eye movement in spino-cerebellar ataxia type 2 | en_US |
dc.type | info:eu-repo/semantics/conferenceObject | en_US |
dc.centro | E.T.S.I. Telecomunicación | en_US |
dc.relation.eventtitle | International Work-Conference on Artificial Neural Networks 2019 | en_US |
dc.relation.eventplace | Maspalomas, Gran Canaria (España) | en_US |
dc.relation.eventdate | 12/06/2019 | en_US |