|Google Classroom コード||bi34bg2|
|講演者||Dr. Fabien Lotte|
|講演タイトル||"Towards understanding and tackling variabilities in Brain-Computer Interactions"
Whereas Brain-Computer Interfaces (BCI) are very promising for various applications, e.g., brain-based wheelchair control or plane pilots’ mental state monitoring, they are not reliable. Their reliability degrades even more across users and when used across contexts (e.g., across days, for changing users’ states or applications used) due to various sources of variabilities. For instance, while some users will be very proficient with BCI control, many will have very poor control performances with the same BCI. Even for a single user, he or she may control the BCI very well one day but completely fail to do so the next day. Unfortunately, such variabilities are 1) often ignored in the literature, as most BCIs are assessed in a single context and with user-specific designs, and 2) poorly understood. Thus, for BCIs to fulfil their promises and be used outside laboratories, we need to make them robust to such variabilities. In this talk I will first present a brief overview of the various known sources of variabilities affecting BCI performances, both between-users (e.g., how different users characteristics or personality are associated to different BCI performances) and within users-variabilities (e.g., how stress or fatigue affect BCI performances). I will then present a few signal processing and machine learning algoritms to address such variabilities and make BCI more robust to them. I will finally present some perspectives about what we could or even should do to optimally tackle such variabilities.
|お問い合わせ窓口||グローバルイノベーション研究院・工学研究院 田中 聡久
e-mail: tanakat(ここに@ を入れてください）cc.tuat.ac.jp