{"title":"Sparse Graph-based Representations of SSVEP Responses Under the Variational Bayesian Framework","authors":"V. Oikonomou, S. Nikolopoulos, Y. Kompatsiaris","doi":"10.1109/BIBE52308.2021.9635427","DOIUrl":null,"url":null,"abstract":"The recognition of Steady State Visual Evoked Potentials (SSVEP) constitutes a challenging problem in Brain Computer Interfaces (BCI), especially when the number of EEG sensors is limited. In this work, we propose a new sparse representation classification scheme that extends current schemes by exploiting the graph properties of relevant features. Based on this scheme each test signal is represented as a linear combination of train signals. Our expectation is that this constrained linear combination, exploiting the graph's structure of the training data, will lead to representations that are more robust. Moreover, in order to avoid overfitting and provide a model with good generalization abilities we adopt the bayesian framework and, in particular, the Variational Bayesian Framework since we use a specific prior distribution to exploit the graph structure of the data. The proposed algorithm has been evaluated on two SSVEP datasets achieving state-of- the-art performance against well known classification methods in SSVEP literature.","PeriodicalId":343724,"journal":{"name":"2021 IEEE 21st International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"512 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 IEEE 21st International Conference on Bioinformatics and Bioengineering (BIBE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/BIBE52308.2021.9635427","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2
Abstract
The recognition of Steady State Visual Evoked Potentials (SSVEP) constitutes a challenging problem in Brain Computer Interfaces (BCI), especially when the number of EEG sensors is limited. In this work, we propose a new sparse representation classification scheme that extends current schemes by exploiting the graph properties of relevant features. Based on this scheme each test signal is represented as a linear combination of train signals. Our expectation is that this constrained linear combination, exploiting the graph's structure of the training data, will lead to representations that are more robust. Moreover, in order to avoid overfitting and provide a model with good generalization abilities we adopt the bayesian framework and, in particular, the Variational Bayesian Framework since we use a specific prior distribution to exploit the graph structure of the data. The proposed algorithm has been evaluated on two SSVEP datasets achieving state-of- the-art performance against well known classification methods in SSVEP literature.