[Research article] Professor Sang Hyun Park's team published a paper in the journal IEEE Transactions on Neural Networks and Learning Systems
페이지 정보
작성자 최고관리자
댓글 0건 조회 64회 작성일 2023-09-16 14:03
본문
- DGIST Professor Sang Hyun Park's research group developed a new-shot learning deep learning model that accurately classifies subjects' brain waves with only a small amount of information.
- If you answer only a few of the brain waves obtained from the target subject, you can accurately classify the remaining brain waves according to the brain wave characteristics of the target subject.- The newly developed deep learning model consists of an embedding module that extracts meaningful features from brain waves, a time-attention module that reduces unnecessary noise features while emphasizing important features, and a relationship module that predicts the relationship between EEG features and class representative vectors.
- The developed deep learning model showed an accuracy of matching the intentions of the target subjects to up to 76% through 20 EEG data in inter-object classification.- The study was published in IEEE Transactions on Neural Networks and Learning Systems (IF=10.4), the top international academic journal in the field of artificial intelligence.
