On the need for alternative feedback training approaches for BCI
Abstract
While recent research on Brain-Computer Interfaces (BCI) has highlighted their potential for many applications, they remain barely used in practice, outside laboratories. The main reason is their lack of reliability and robustness. Indeed, with current BCI, mental state recognition is usually slow and too often incorrect. These poor performances are due in part to the EEG signal processing algorithms used since they are not yet able to deal appropriately with their noisy, complex and non-stationary nature. However, there is another component of the BCI loop that may also be deficient: the user him/herself who may not be able to produce reliable EEG patterns. Indeed, it is widely acknowledged that "BCI use is a skill" [1], which means the user must be properly trained to be able to successfully use the BCI. If the BCI user is indeed unable to correctly perform the desired mental commands, whatever the signal processing algorithms used, there would be no way to properly identify them. Despite this, the BCI community has focused the majority of its research effort on signal processing and machine learning, mostly neglecting the human in the loop. In this work, we argue that the user is one of the most critical components of the BCI loop that may explain the limited reliability of current BCI. It does not mean that BCI users are per se poor performers or incompetent. It means that the way current BCI training protocols are designed is inappropriate, making BCI users unable to properly learn and use the BCI skill.
Origin | Files produced by the author(s) |
---|
Loading...