US 10,890,972 B2
Prefrontal-based cognitive brain-machine interfacing apparatus and method thereof
Byoung-Kyong Min, Seoul (KR); and Kyuwan Choi, Seoul (KR)
Assigned to Korea University Research and Business Foundation, Seoul (KR)
Filed by KOREA UNIVERSITY RESEARCH AND BUSINESS FOUNDATION, Seoul (KR)
Filed on Apr. 6, 2018, as Appl. No. 15/946,882.
Claims priority of application No. 10-2017-0044695 (KR), filed on Apr. 6, 2017; and application No. 10-2018-0032121 (KR), filed on Mar. 20, 2018.
Prior Publication US 2018/0292902 A1, Oct. 11, 2018
Int. Cl. G06F 3/01 (2006.01); A61B 5/0482 (2006.01); A61B 5/0478 (2006.01); A61B 5/00 (2006.01); A61B 5/16 (2006.01); A61B 5/048 (2006.01)
CPC G06F 3/015 (2013.01) [A61B 5/0478 (2013.01); A61B 5/0482 (2013.01); A61B 5/4064 (2013.01); A61B 5/048 (2013.01); A61B 5/16 (2013.01)] 14 Claims
OG exemplary drawing
 
1. A prefrontal-based cognitive brain-machine interfacing apparatus, comprising:
a brainwave measurement device configured to measure a prefrontal brainwave signal of a subject;
a memory in which a cognitive brain-machine interface program is stored; and
a processor configured to execute the program stored in the memory,
wherein upon execution of the cognitive brain-machine interface program, the processor pinpoints a brain cortical region corresponding to the prefrontal brainwave signal among previously assigned multiple subdivisions of a prefrontal area, measures a degree of corresponding brain activities, extracts a prefrontal activity pattern by measuring the degree of corresponding brain activities and calculating causal connectivity among two or more previously assigned brain regions based on a corresponding sensor-level brain activity, inputs the extracted prefrontal activity pattern into a classifier which is previously generated by machine learning of multiple prefrontal activity patterns of the subject to identify any of preset control conditions corresponding to the extracted prefrontal activity pattern among preset brain-machine interface control conditions, and generates and outputs a machine regulating signal corresponding to one of the preset control conditions identified by the classifier, and
the classifier is generated by machine learning of the prefrontal activity patterns labelled for contents of multiple intentions, respectively, based on the prefrontal brainwave signals of the subject.