This paper explores the convenience of using additional signals apart fromelectroencephalograms . The best overall model, an ensemble of Depth-wiseSeparational Convolutional Neural Networks, has achieved an accuracy of 86.06\% with a Cohen’s Kappa of 0.80 and a $F_{1}$ of $F_1 of $1.77 . It shows a significant improvement inthe precision and recall for the most uncommon class in the dataset . Up to date, those are the best results on the complete dataset and it shows a . significant improvement in the precision and . recall of the most common class in . the dataset and, its performance has beencompared showing the . convenience of . using these multi-signal models to improve the classification. The best models obtained for each combination of one or moresignals have been used in an ensemble models have been found to be used in the . most uncommonclass in the datasets. Up to Date, those were the best models on the . complete dataset. up to date,. those are

Author(s) : Enrique Fernandez-Blanco, Carlos Fernandez-Lozano, Alejandro Pazos, Daniel Rivero

Links : PDF - Abstract

Code :

Keywords : models - dataset - date - ensemble - f -

Leave a Reply

Your email address will not be published. Required fields are marked *