| EPSRC Reference: |
GR/T09903/01 |
| Title: |
Mining for Novel Signatures in Multi-Channel EEG for Brain-Computer Interfaces |
| Principal Investigator: |
Sepulveda, Professor F |
| Other Investigators: |
|
| Researcher Co-Investigators: |
|
| Project Partners: |
|
| Department: |
Computer Sci and Electronic Engineering |
| Organisation: |
University of Essex |
| Scheme: |
First Grant Scheme Pre-FEC |
| Starts: |
01 August 2005 |
Ends: |
31 August 2007 |
Value (£): |
122,984
|
| EPSRC Research Topic Classifications: |
| Biomedical neuroscience |
Cognitive Science Appl. in ICT |
| Fundamentals of Computing |
Med.Instrument.Device& Equip. |
|
| EPSRC Industrial Sector Classifications: |
|
| Related Grants: |
|
| Panel History: |
|
|
Summary on Grant Application Form |
|
Electroencephalography (EEG) has been used for a number of years as a source of signals for enabling subjects with severe disabilities to communicate with computers and other devices. Solid, yet only limited success has been reached. It is possible that this is partly due to the localized approach most researchers have taken so far. Le., current brain computer interfaces have looked mostly at signals from areas of the cortex that are expected to manifest activity that is directly related to a particular type of intention (e.g., movement intention). However, the rich interconnectivity between the various cortical areas may allow for events in one area to be preceded or accompanied by detectable signatures patterns in other seemingly unrelated areas. This fact has been only scarcely explored in connection with BCls. Thus, the main purpose of this project is to explore the functional time-related cortical interconnectivity both as an alternative and as an extra source of information for detecting a person's motor intentions within EEG signals. Though risky, this will be an important novel approach that may yield EEG-based features with a shorter latency time than iscurrently available, thus addressing one of the two limiting factors in current BCIs (the other one is classification performance). The other two novel elements aimed at in this project are: i) to create neurophysiologically inspired pseudo wavelets for the joint time-frequency analysis of brain signals, and ii) to establish which areas of the cortex may carry information that may improve on the pattern classification performance of current BCls. All major problems with current BCls will hence be addressed and attempts will be made to reduce the problems.
|
|
Key Findings |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
|
Potential use in non-academic contexts |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
|
Impacts |
|
| Description |
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk |
| Summary |
|
| Date Materialised |
|
|
|
|
Sectors submitted by the Researcher |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
| Project URL: |
|
| Further Information: |
|
| Organisation Website: |
http://www.sx.ac.uk |