An improved asynchronous brain interface: making use of the temporal history of the LF-ASD feature vectors

• Published in: Journal of neural engineering Vol. 3; no. 2; pp. 87 - 94
• Main Authors: Bashashati, Ali, Mason, Steve, Ward, Rabab K, Birch, Gary E
• Format: Journal Article
• Language: English
• Published: England IOP Publishing 01.06.2006
• Subjects: Adult; Artificial Intelligence; Brain - physiopathology; Communication Aids for Disabled; Electroencephalography - instrumentation; Electroencephalography - methods; Equipment Design; Equipment Failure Analysis; Evoked Potentials, Motor; Female; Humans; Imagination; Male; Middle Aged; Pattern Recognition, Automated - methods; Signal Processing, Computer-Assisted - instrumentation; Spinal Cord Injuries - physiopathology; Spinal Cord Injuries - rehabilitation; User-Computer Interface
• ISSN: 1741-2552; 1741-2560; 1741-2552
• DOI: 10.1088/1741-2560/3/2/002

The low-frequency asynchronous switch design (LF-ASD) has been introduced as a direct brain interface (BI) for asynchronous control applications. Asynchronous interfaces, as opposed to synchronous interfaces, have the advantage of being operational at all times and not only at specific system-defined periods. This paper modifies the LF-ASD design by incorporating into the system more knowledge about the attempted movements. Specifically, the history of feature values extracted from the EEG signal is used to detect a right index finger movement attempt. Using data collected from individuals with high-level spinal cord injuries and able-bodied subjects, it is shown that the error characteristics of the modified design are significantly better than the previous LF-ASD design. The true positive rate percentage increased by up to 15 which corresponds to 50% improvement when the system is operating with false positive rates in the 1-2% range.