Palacio Baus, Kenneth SamuelMinchala Ávila, Luis IsmaelVázquez Rodas, Andrés MarceloAstudillo Salinas, Darwin Fabián2019-02-062019-02-06201897815386264430000-0000http://dspace.ucuenca.edu.ec/handle/123456789/31938https://www.scopus.com/inward/record.uri?eid=2-s2.0-85050904685&doi=10.1109%2fINCISCOS.2017.10&partnerID=40&md5=4849098634c9d1c16bfd999e67769627This paper presents preliminary results on evaluating the NeuroSky Mindwave headset for upper body motion intention classification. An artificial neural network (ANN) is trained by using a data set built for two different feature extraction methods, one based on the wavelet transform (WT) and another based on the use of spectrograms. Since there are five different types of brain waves,(α, β, γ, Δ, θ) some data aggregation procedures are proposed to reduce the dimensionality of the data set. The classification results show that it is possible to attain a 73.1% of assertion rate. © 2017 IEEE.This paper presents preliminary results on evaluating the NeuroSky Mindwave headset for upper body motion intention classification. An artificial neural network (ANN) is trained by using a data set built for two different feature extraction methods, one based on the wavelet transform (WT) and another based on the use of spectrograms. Since there are five different types of brain waves,(α, β, γ, Δ, θ) some data aggregation procedures are proposed to reduce the dimensionality of the data set. The classification results show that it is possible to attain a 73.1% of assertion rate. © 2017 IEEE.es-ESAnnClassificatorData CompressionMindwaveARTÍCULO DE CONFERENCIA10.1109/INCISCOS.2017.10