A Brain-Computer Interface (BCI) is a communication system that does not depend on the brain’s normal output pathways of peripheral nerves and muscles. Thus, it constitutes a new output channel for the brain. In completely disabled patients, it may be used to recognize the patients’ “will” directly from the brain in order to command a device, e.g., prosthesis. The purpose of this project is to develop a BCI system capable of providing a control output based on different ways of movement execution, enhancing the quality of the command to external systems to propitiate the restoration of more complex motor functions than the two-choice commands currently available. The system will be based on classification of electroencephalographic (EEG) recordings. The project will be divided into four sub-tasks: 1) experimental recording of a data bank of electroencephalographic (EEG) signals for testing the BCI; 2) development of a method for detection of the presence of a command (asynchronous BCI) from EEG recordings; 3) development of a multi-class, multi-channel translation algorithm that associates an application-dependent device command (e.g., a prosthesis) to specific EEG signals; 4) implementation of the system in a DSP-based device. The final goal is the production of a prototype DSP system with up to 90 inputs (multichannel EEG recordings) and a 5-stage digital output (force high or low, speed high or low, no command). The development of such a system would constitute a breakthrough in BCI technology. Indeed, on the one hand, this system would prove that signals from the brain can be used as inputs for reproducing complex movements. On the other hand, it would have important practical application for fully disabled people.
|Effective start/end date||16/09/2003 → 02/02/2009|
- <ingen navn>