Journal
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
Volume 22, Issue 3, Pages 653-663Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JBHI.2017.2690801
Keywords
Asynchronous control; brain computer interface (BCI); control state detection; dynamic stopping; environmental control; P300; region based paradigm (RBP)
Categories
Funding
- Scientific and Research Projects Department of Gazi University (BAP) [07/2012-15, 07/2012-29]
Ask authors/readers for more resources
An asynchronous brain computer interface (A-BCI) determines whether or not a subject is on control state, and produces control commands only in case of subject's being on control state. In this study, we propose a novel P300-based A-BCI algorithm that distinguishes control state and noncontrol state of users. Furthermore, A-BCI algorithm combined with a dynamic stopping function that enables users to select control command independent from a fixed number of intensification sequence. The proposed P300-based A-BCI algorithm uses classification patterns to determine control state and uses optimal operating point of receiver operating characteristics curve for dynamic stopping function. The proposed A-BCI algorithm is also combined with region-based paradigm (RBP) based stimulus interface. The A-BCI algorithm is tested on an internet-based environmental control system. A total of ten nondisabled subjects were participated voluntarily in the experiments. Two-level approach of the RBP-based stimulus interface improves noncontrol state detection accuracy up to 100%. Besides, ratio of incorrect command selection at control state is reduced significantly. At control state, ratio of correct selections, incorrect selections, and missed selections are 93.27%, 1.09%, and 5.63%, respectively. On the other hand, dynamic stopping function enables command selections at least two intensifications. Mean number of intensification sequences to complete the given tasks is 3.15. Thanks to dynamic stopping function, it provides a significant improvement on information transfer rate. The proposed A-BCI algorithm is important in terms of practical BCI systems.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available