Seoul National University

Vuno, Inc.

Byeongtak Lee

Sanghyun Kim

Kyung Su Kim

Woong Bae

TaeGyun Kim

Jung Chan Lee

Oyeon Kwon

Woo Sang Cho

Jaeheung Park

Min Ji Park

Sang Hoon Na

Jaesug Jung

Youngjae Song

Byeong Wook Yoo

Jeeseop Kim

Yoon Sun Jung

Woon Yong Kwon

Kyoung Min You

Jin Woo Choi

Gil Joon Suh

Jung-In Ko

A deep neural network pre-training method for classifying electrocardiogram (ECG) data and a device for the same are disclosed. A method for training an ECG feature extraction model may include receiving a ECG signal, extracting one or more first features related to the ECG signal by inputting the ECG signal to a rule-based feature extractor or a neural network model, extracting at least one second feature corresponding to the at least one first feature by inputting the ECG signal to an encoder, and pre-training the ECG feature extraction model by inputting the at least one second feature into at least one of a regression function and a classification function to calculate at least one output value. The pre-training of the ECG feature extraction model may include training the encoder to minimize a loss function that is determined based on the at least one output value and the at least one first feature.

Deep neural network pre-training method for classifying electrocardiogram (ECG) data

An automatic cardiopulmonary resuscitation device includes a movable chest compressor for repeatedly pressing a patient's chest at a preset depth and cycle, a cardiac output measurement unit for measuring a cardiac output of the patient in accordance with the pressurization of the chest compressor and a processor for changing pressing locations by performing control such that the chest compressor moves according to a preset method.

Automatic cardiopulmonary resuscitation device and control method therefor

Growing community of inventors

Seoul, South Korea

Byeongtak Lee