Towards Second Generation Brain-computer Interfaces
Duration of project
12/1/2007 – 11/30/2010
Swiss National Science Foundation
A brain-computer interface (BCI) is a system that allows a user to communicate with the environment only through cerebral activity, without using muscular output channels. To establish a direct link between the brain and a computer, the cerebral activity is measured and then analyzed with the help of signal processing and machine learning algorithms. Once a certain mental activity has been detected by the computer, a response can be displayed on a screen or a command can be sent to a device – for example a robot or a remote control. The main application area for BCI is assistive technology for handicapped persons.
During the last years, it has been convincingly shown that communication via a BCI is feasible for able-bodied as well as handicapped subjects. However, so far no practical, commercially available systems suited for use in everyday life by handicapped persons are available.
The goal of this project is to develop a second-generation BCI which overcomes some of the problems inherent in current system. To achieve this goal it is planned to develop new machine learning algorithms that allow users to immediately use a BCI without going through a training phase. In contrast to many other BCI systems the developed system will be asynchronous. This means the system will continuously analyze cerebral activity but will react only when it detects that the user is actually trying to send a command. The motivation for performing the proposed research is to extend the functionality of current BCI systems and thus to move towards practical BCI systems for disabled users. Generally speaking many applications that rely on the categorization of brain-activity could possibly profit from the methods developed in this project. Among the potential applications are driver-monitoring (mapping EEG to vigilance levels), interrogative polygraphs (“lie detection”), and clinical applications, for example coma outcome prognosis and depth of anesthesia monitoring.
Results and resources
- A. Yazdani, J.-M. Vesin, D. Izzo, C. Ampatzis and T. Ebrahimi, IMPLICIT RETRIEVAL OF SALIENT IMAGES USING BRAIN COMPUTER INTERFACE, Proceedings of International Conference on Image Processing (ICIP), 2010.
- A. Yazdani, J.-M. Vesin, D. Izzo, C. Ampatzis and T. Ebrahimi, The Impact of Expertise on Brain Computer Interface Based Salient Image Retrieval, Proceedings of 32nd Annual International Conference of the IEEE EMBS, pp. 1646-1649, 2010.
- S. Koelstra, A. Yazdani, M. Soleymani, C. Muehl, J.S. Lee, A. Nijholt, T. Pun, T. Ebrahimi and I. Patras, Single trial classification of EEG and peripheral physiological signals for recognition of emotions induced by music videos, Proceedings of the International Conference on Brain Informatics, 2010.
- D. Izzo, L. Rossini, M. Rucinski, C. Ampatzis, G. Healy, P. Wilkins, A. Smeaton, A. Yazdani and T. Ebrahimi, Curiosity Cloning: Neural Analysis of Scientific Knowledge, Proceedings of the International Joint Conference on Artificial Intelligence 2009, Workshop on Artificial Intelligence in Space, 2009.
- A. Yazdani, J.-S. Lee and T. Ebrahimi, Implicit emotional tagging of multimedia using EEG signals and brain computer interface, Proceedings of ACM Multimedia, Workshop on Social Media, 2009.
- A. Yazdani, U. Hoffmann and T. Ebrahimi , Classification of EEG Signals Using Dempster Shafer Theory and a K-Nearest Neighbor Classiﬁer, The 4th International IEEE EMBS Conference on Neural Engineering, pp. 327-330, 2009. [poster]
- U. Hoffmann, A. Yazdani, J.M. Vesin and T. Ebrahimi, “Bayesian Feature Selection Applied In a P300 Brain-Computer Interface“, 16th European Signal Processing Conference, EUSIPCO 2008, August 25-29, 2008, Lausanne –Switzerland.