作者: Fabien Lotte
DOI:
关键词:
摘要: This paper introduces the use of a Fuzzy Inference System (FIS) for classification in EEG-based Brain-Computer Interfaces (BCI) systems. We present our FIS algorithm and compare it, on motor imagery signals, with three other popular classifiers, widely used BCI community. Our results show that outperformed Linear Classifier reached same level accuracy as Support Vector Machine neural networks. Thus, FIS-based is suitable design. Furthermore, algorithms have two additionnal advantages: they are readable easily extensible.