Improved virtual keyboard design for P300-based brain-computer interface

• Main Author: Tay, Abel Ping Liang.
• Other Authors: Vinod Achutavarrier Prasad
• Format: Final Year Project
• Language: English
• Published: 2009
• Subjects: DRNTU::Engineering::Computer science and engineering::Computer applications::Life and medical sciences
• Online Access: http://hdl.handle.net/10356/16939
• Institution: Nanyang Technological University

Amyotrophic lateral sclerosis (ALS), brainstem stroke, brain or spinal cord injury, cerebral palsy, muscular dystrophies, multiple sclerosis, and numerous other diseases impair the neural pathways that control muscles or impair the muscles themselves. Those most severely affected may lose all voluntary muscle control, including eye movements and respiration, and may be completely locked in to their bodies, unable to communicate in any way. The locked-in syndrome is a condition in which patients are fully conscious and aware of what is happening in their environment but are not able to communicate or move. Modern life-support technology can allow most individuals, even those who are locked-in, to live long lives, so that the personal, social, and economic burdens of their disabilities are prolonged and severe. Brain computer interfaces are used for patients who are locked-in, unable to use their limbs. It allows them to communicate with other people using solely brain signals. There is an existing brainy communicator interface that works by having the user focus on the alphabet that he wants to spell and P300 signals are read from the user’s scalp. A C# program written as part of the final year project has shown that the algorithm for word predictions as well as multiple button flashing simultaneously works and can be integrated into the P300 system to speed up word entry. The current program flashes all buttons randomly in a round for a few rounds, and then takes all values to determine which character has the highest probability. Algorithms for both word predictions and multiple letter flashing has been written and tested without integration. Both methods can be employed for testing of speed of entering letters and words into the system. However, having word predictions may increase the number of flashes as the number of buttons has been increased. Word predictions and multiple letter flashing are currently disabled in order to integrate with the P300 interface. Integration has been done incrementally and tested at every stage. Steps that help toward integration include spacing the characters with a bigger gap on the screen, changing non-flashing colours to blend into the background and making the flashing character as contrasting as possible. Experiments have shown that the speed has been improved by more than 30%. This will reduce fatigue in the user and allow the user to key in more characters. However, the accuracy is lowered by about 7% on the new program.