公开(公告)号：US10022082B2

公开(公告)日：2018-07-17

申请号：US15356083

申请日：2016-11-18

申请人： HYUNDAI MOTOR COMPANY ,  KIA MOTORS CORPORATION ,  GWANGJU INSTITUTE OF SCIENCE AND TECHNOLOGY

发明人： Nam Woong Hur ,  Seul Ki Jeon ,  Hyun Sang Kim ,  Eung Hwan Kim ,  Sang Tae Ahn ,  Hyo Jung Jang ,  Sung Chan Jun

IPC分类号： A61B5/18 ,  A61B5/0478 ,  A61B5/04 ,  A61B5/0402 ,  A61B5/0476 ,  A61B5/026

摘要： An apparatus and a method is provided for detecting biometric signals of a driver and classifying the driver into a normal state or a fatigued state based on the biometric signals. An apparatus may include: a biometric signal measuring part configured to measure the biometric signals including a blood flow rate of a brain of the driver using an electro-encephalography (EEG), an electro-cardiography (ECG), and a functional near-infrared spectroscopy (fNIRS) of the driver; a biometric signal integral part configured to integrate the measured biometric signals, to extract characteristics of the respective biometric signals from the measured biometric signals and to then integrate the extracted characteristics, or to classify the extracted characteristics of the biometric signals and to then integrate the classified characteristics; and a driver state detecting part configured to detect the state of the driver based on the integrated biometric signals.

公开(公告)号：US10413204B2

公开(公告)日：2019-09-17

申请号：US15362818

申请日：2016-11-29

申请人： GWANGJU INSTITUTE OF SCIENCE AND TECHNOLOGY

发明人： Hohyun Cho ,  Sung Chan Jun

IPC分类号： A61B5/04 ,  A61B5/0482 ,  A61B5/00 ,  A61B5/0476 ,  G06F3/01 ,  G06K9/00

摘要： The present disclosure discloses an apparatus for a brain computer interface (BCI) including a feature extraction filter trainer for training a feature extraction filter which minimizes an influence of a background brain wave while maximizing a difference between intended brain waves; and a classifier trainer for training a classifier for classifying the intended brain waves by using a feature vector obtained by filtering the intended brain wave at the feature extraction filter. With the apparatus, only the background brain wave is additionally measured, such that previous intended brain wave data can be reused and the brain wave can be classified more quickly and accurately.