Towards practical EEG-based Brain-Computer Interface Technologies
Fabien LOTTE
2015-10-15
报 告 人:Fabien LOTTE
报告时间:2015年10月15日上午09:00
摘要:
Brain-Computer Interfaces (BCI) are systems that can translate the brain activity patterns of a user into messages or commands for an
interactive application, this brain activity being usually measured using Electroencephalography (EEG). BCI technologies proved to be
promising for a wide range of applications including communication and control for motor impaired users, gaming targeted at the general
public, real-time mental state monitoring or stroke rehabilitation. Despite this promising potential, BCI are still scarcely used outside
laboratories, for practical applications.This is mainly due to the low reliability of current BCI.
In this talk, I will present our research works towards addressing this limitation. First, I will present some EEG signal processing and
classification algorithms we designed for making BCI more robust to noise, non-stationarities and with minimal calibration times.
Then, I will show that making BCI more robust can also be achieved by making BCI users better at BCI control. I will notably try to convince
the audience that principles and guidelines from educational psychology and instructional design should and can be used to enable BCI users to
learn faster and more efficient BCI control. Finally, this talk will present how even not-so-reliable BCI technologies can still be useful for
pratical applications. For this, this talk will describe our work on neuroergonomics, i.e., on the use of brain signals to estimate passively
themental state of users (e.g., mental workload levels) during human-computer interaction, in order to assess the rgonomic qualities of this
user interface.
简介:
Fabien LOTTE obtained a M.Sc., a M.Eng. and a PhD degree in computer sciences, all from the National Institute of Applied Sciences (INSA)
Rennes, France, in 2005 and 2008 respectively. As a PhD candidate he worked on Brain-Computer Interfaces (BCI) design for Virtual Reality
(VR) applications.His PhD Thesis received both the PhD Thesis award 2009 from AFRIF (French Association for PatternRecognition) and the PhD
Thesisaward 2009 accessit (2nd prize) from ASTI (French Association for Information Sciences and Technologies). He is one of the designers
of the OpenViBE platform, a widely used open-source software forthe design of real-time BCI. In 2009 and 2010, he was a research fellow atthe
Institute for Infocomm Research (I2R) in Singapore, working in the Brain-Computer Interface Laboratory. During that time, he explored more
particularly EEG signal processing and machine learning for the design of robust and practical BCI.Since January 2011, he is a Researc
Scientist (with tenure) at Inria Bordeaux Sud-Ouest, in France, where he works on BCI, Human-Computer Interaction, pattern recognition and
signal processing.