Adaptive BCI based on software agents
| Autor: | Anibal Cotrina, Denis Delisle-Rodriguez, André Ferreira, Javier Castillo-Garcia, Teodiano Bastos, Eduardo Caicedo, Berthil Longo, Alessandro B. Benevides |
|---|---|
| Rok vydání: | 2014 |
| Předmět: |
Support Vector Machine
Databases Factual Computer science Models Neurological Feature selection Machine learning computer.software_genre Pattern Recognition Automated User-Computer Interface Cohen's kappa Humans Entropy (information theory) Entropy (energy dispersal) Brain–computer interface Neurons business.industry Entropy (statistical thermodynamics) Brain Reproducibility of Results Electroencephalography Pattern recognition Mutual information Software agent Brain-Computer Interfaces Artificial intelligence business computer Algorithms Software |
| Zdroj: | EMBC |
| DOI: | 10.1109/embc.2014.6944861 |
| Popis: | The selection of features is generally the most difficult field to model in BCIs. Therefore, time and effort are invested in individual feature selection prior to data set training. Another great difficulty regarding the model of the BCI topology is the brain signal variability between users. How should this topology be in order to implement a system that can be used by large number of users with an optimal set of features? The proposal presented in this paper allows for obtaining feature reduction and classifier selection based on software agents. The software agents contain Genetic Algorithms (GA) and a cost function. GA used entropy and mutual information to choose the number of features. For the classifier selection a cost function was defined. Success rate and Cohen's Kappa coefficient are used as parameters to evaluate the classifiers performance. The obtained results allow finding a topology represented as a neural model for an adaptive BCI, where the number of the channels, features and the classifier are interrelated. The minimal subset of features and the optimal classifier were obtained with the adaptive BCI. Only three EEG channels were needed to obtain a success rate of 93% for the BCI competition III data set IVa. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|