Rohan Ghantasala
Pronouns: He/They
Research Mentor(s): Jane Huggins
Research Mentor School/College/Department: Physical Medicine and Rehabilitation / Medicine
Program: CG
Session: Session 5 (2:40pm – 3:30pm)
Authors: Rohan S Ghantasala, Jane E Huggins
Abstract
Individuals that have disabilities that impair their motor skills, such as those with cerebral palsy or muscular dystrophy, can have trouble communicating using traditional means such as a keyboard or pencil and paper. BCI2000 (Schalk et al., 2004) is a Brain-Computer Interface system, which is a system that uses EEGs to interpret and translate signals from the brain (Farwell and Donchin, 1988). The BCI2000 uses a P300 classifier, which is a program that applies machine learning algorithms to the data in order to predict what the subject was attempting to say (User Reference:P300 Classifier – BCI2000 Wiki). This project is meant to make the BCI2000 P300 Classifier program easier to use for both researchers and end-users. This is being accomplished by making changes and adding features to the software. The classifier now displays a BCI-Utility metric, which is a measure of how accurate and efficient the prediction was (Seno et al., 2010). Minor improvements such as adding a maximize button to the program window and deactivating buttons that do not work have also been added. Further intended improvements to the classifier include combining the different functions that validate files into one single function, and adding effective, useful error messages. References: Schalk G, McFarland DJ, Hinterberger T, Birbaumer N, Wolpaw JR. BCI2000: a general-purpose brain-computer interface (BCI) system. IEEE Trans Biomed Eng. 2004 Jun;51(6):1034-43. doi: 10.1109/TBME.2004.827072. PMID: 15188875. Farwell LA, Donchin E. Talking off the top of your head: toward a mental prosthesis utilizing event-related brain potentials. Electroencephalogr Clin Neurophysiol. 1988 Dec;70(6):510-23. doi: 10.1016/0013-4694(88)90149-6. PMID: 2461285. Seno, Bernardo & Matteucci, Matteo & Mainardi, Luca. (2010). The Utility Metric: A Novel Method to Assess the Overall Performance of Discrete Brain–Computer Interfaces. IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society. 18. 20-8. 10.1109/TNSRE.2009.2032642.
