	US 11,995,891 B2
	Computer program and method for training artificial neural network model based on time-series biosignal
Seung Wan Kang, Seoul (KR); and Ukeob Park, Seoul (KR)
Assigned to IMEDISYNC, INC., Seoul (KR)
Filed by IMEDISYNC, INC., Seoul (KR)
Filed on Jan. 11, 2021, as Appl. No. 17/146,220.
Application 17/146,220 is a continuation of application No. PCT/KR2020/017907, filed on Dec. 9, 2020.
Claims priority of application No. 10-2020-0089869 (KR), filed on Jul. 20, 2020.
Prior Publication US 2022/0019808 A1, Jan. 20, 2022
Int. Cl. G06V 20/40 (2022.01); G06F 3/01 (2006.01); G06T 7/00 (2017.01)

CPC G06V 20/47 (2022.01) [G06F 3/015 (2013.01); G06T 7/0012 (2013.01); G06F 2218/16 (2023.01); G06T 2207/10016 (2013.01); G06T 2207/20084 (2013.01)]

10 Claims

10. A computing device for generating video data for diagnosing a health condition and a pathological symptom on the basis of a biosignal, the device comprises:

a processor configured to:

receive biosignals of a user;

preprocess the biosignals to generate a plurality of pieces of video sub-data; and

select at least two of the plurality of pieces of video sub-data to generate one or more pieces of video data,

wherein the biosignals are signals acquired in time-series from the user's body and includes one or more of an electroencephalography signal and an electrocardiogram signal acquired through one or more channels, and

wherein the processor is further configured to acquire the biosignals through a plurality of electrodes on the basis of an electric potential difference measured from one or more areas of the user's body.