US 12,260,850 B2
Brain computer interface running a trained associative model applying multiway regression to simulate electrocorticography signal features from sensed EEG signals, and corresponding method
Pawel Piotr Pazderski, Leuven (BE); and Hannes Flora Jan De Wachter, Herent (BE)
Assigned to MINDSPELLER BCI BV, Leuven (BE)
Appl. No. 17/788,566
Filed by MINDSPELLER BCI BV, Leuven (BE)
PCT Filed Dec. 18, 2020, PCT No. PCT/EP2020/087040
§ 371(c)(1), (2) Date Jun. 23, 2022,
PCT Pub. No. WO2021/130115, PCT Pub. Date Jul. 1, 2021.
Claims priority of application No. 2024573 (NL), filed on Dec. 24, 2019.
Prior Publication US 2023/0025518 A1, Jan. 26, 2023
Int. Cl. G10L 13/027 (2013.01); G06F 3/01 (2006.01); G10L 13/04 (2013.01)
CPC G10L 13/027 (2013.01) [G06F 3/015 (2013.01); G10L 13/04 (2013.01)] 12 Claims
OG exemplary drawing
 
1. Brain computer interface (“BCI”) comprising an input connected to at least one electroencephalography (“EEG”) sensor and receiving EEG signals generated by the at least one EEG sensor, the BCI further comprising a processor running an associative model applying a multiway regression approach trained to simulate electrocorticography (“ECOG”) signal features from the received EEG signals, the BCI comprising an output to transmit the simulated ECOG signal features.