Brain-Computer Interfaces

Brain-computer interfaces (BCIs) are hardware and software systems that sample electroencephalogram (EEG) signals from electrodes placed on the scalp and extract patterns from EEG that indicate the mental activity being performed by the person. The long-term goal of this line of research is a new mode of communication for victims of diseases and injuries resulting in the loss of voluntary muscle control, such as amyotrophic lateral sclerosis (ALS), high-level spinal cord injuries or severe cerebral palsy. The autonomic and intellectual functions of such subjects continue to be active. This can result in a locked-in syndrome in which a person is unable to communicate to the outside world. The interpretation of information contained in EEG may lead to a new mode of communication with which subjects can communicate with their care givers or directly control devices such as televisions, wheel chairs, speech synthesizers and computers.


The objectives of this project are to

  • develop open-source software for on-line EEG analysis and brain-computer interfaces;
  • compare signal quality and BCI performance of various EEG systems in users' homes;
  • develop new algorithms for identifying cognitive components in spontaneous EEG related to mental tasks as a basis for new BCI protocols;
  • improve BCI reliability by allowing users to adapt through real-time feedback and by adapting the BCI algorithms using error-related EEG components;
  • experiment with interaction of two people using BCIs.

Results are evaluated by the accuracy of EEG classification, the speed with which the classification can be performed, and the expense of the EEG system and of its maintenance and extendibility.

Research Issues

EEG signals are noisy and variable over time. Noise arises from slight shifts in the position of electrodes and changes in the conductance through the skin and interference by hair. Variability is due to changes in electrical activity moment to moment and day to day, even as the subject is performing the same mental task. The quantity of EEG data available for training is limited, especially if a BCI system must be trained every time an electrode cap is placed on a subject. Most BCI experiments deal only with classification and have ignored the detection problem of identifying when a subject has produced a BCI command and is not performing any other mental activity.


The most significant impact of this project to the disabled community will be an easier to use, affordable BCI system. The inclusion of a wide range of mental tasks will result in a better understanding of which mental tasks are easiest for subjects to consistently perform and for detection algorithms to reliably identify. Better BCI systems will also be significant for other classes of users who can benefit from augmented communication interfaces in applications that require extremely fast commands. The significance of this project to the BCI research community is the specification and testing of the inexpensive system for experimentation with EEG signal analysis. The system based on off-the-shelf components and software to be developed and made publicly available is expected to allow a number of additional research groups to enter the BCI field. Also, this project's results on the analysis of cognitive components in EEG measured during a wide range of mental tasks will broaden the set of mental activities available to users of BCI systems.


This work has been supported by the National Science Foundation through grants numbered 1065513, 0542947, 0328269, 0208958, 9202100 and by the Science Foundation of Ireland through an E.T.S. Walton grant in 2007.