Investigation of the trade-off between time window length, classifier update rate and classification accuracy for restorative brain-computer interfaces

摘要: Recently, the application of restorative brain-computer interfaces (BCIs) has received significant interest in many BCI labs. However, there are a number challenges, that need to be tackled achieve efficient performance such systems. For instance, any needs an optimum trade-off between time window length, classification accuracy and classifier update rate. In this study, we have investigated possible solutions these problems by using dataset provided University Graz, Austria. We used continuous wavelet transform Student t-test for feature extraction support vector machine (SVM) classification. find improved results, BCIs rehabilitation, may achieved 750 milliseconds with average 67% updates every 32 milliseconds.