Adaptive Brain Interfacing
Brain-Computer Interface (BCI) is a communication system, which enables the user to control special computer applications by using only his or her thoughts. Different research groups have examined and used different methods to achieve this. Almost all of them are based on electroencephalography (EEG) recorded from the scalp. The EEG is measured and sampled while the user imagines different things (for example, moving the left or the right hand). Depending on the BCI, particular preprocessing and feature extraction methods are applied to the EEG sample of certain length. It is then possible to detect the task-specific EEG signals or patterns from the EEG samples with a certain level of accuracy.
Despite the technological developments numerous problems still exists in building efficient BCIs. The biggest challenges are related to accuracy, speed and usability. Other interfaces are still much more efficient.
BCI could provide a new communication tool for people suffering from so called locked-in syndrome. They are completely paralyzed physically and unable to speak, but cognitively intact and alert. Locked-in syndrome can be caused.
Adaptive Brain Interface (ABI) is a BCI which has been developed under the project Adaptive Brain Interfaces financed by European Commission. The project started in 1998 and ended in 2001. The ABI is based on the pattern recognition approach. In this approach the user concentrates on different mental tasks, for example, moving the left hand or visually rotating a cube. The classifier is trained with EEG data containing the different mental tasks. The trained classifier can then classify EEG online and provide feedback for the user.
In this work basics of Brain-Computer Interface (BCI) are explained. Six different BCI systems (including ABI) are reviewed and then compared with each other. One week training with three subjects was carried out with a new ABI device in the Laboratory of Computational Engineering. Test results are presented and discussed.
In the second chapter, the basics of brain computer interface are described. Functional areas of the brain, EEG and its measurement are described. BCIs are divided into two main approaches called pattern recognition and operant conditioning approaches. BCI components are described briefly. Feedback, training and BCI performance are described in more detail. Finally, several BCI categories are introduced.
The third chapter provides the review and comparison of the six BCI systems, which are BCIs, developed at the Alberta and the Oxford universities, a BCI developed at the Wadsworth Center, a Thought Translation Device and a Graz BCI and the ABI. The ABI is covered in more detail than other five.
The fourth chapter introduces the new ABI system. It presents the experimental methods and the results from five days training with three subjects. It also describes subject reports of mental task strategies and feedback experiences. Finally, it provides discussion on the results, mental tasks and feedback. The fifth chapter provides the conclusions of this work.
Full Seminar Report Download