Jeong, Ji Hyeok Kim, Dong-Joo Kim, Hyungmin 2026-03-03T09:30:04Z 2026-03-03T09:30:04Z 2026-02-25 2026-02-05 https://pubs.kist.re.kr/handle/201004/154393 A CNN-based interpretable channel selection framework is proposed to reduce data complexity in session-transfer motor imagery (MI) brain–computer interface (BCI) scenarios. Experiments conducted on the BCI Competition IV-2a dataset with nine healthy subjects demonstrate that the proposed Input-Aware Gradient approach effectively preserves classification performance even when the number of channels is reduced to 10 (p = 0.11). These findings indicate that the proposed framework can identify a compact, subject-specific channel subset while retaining session-invariant neural features, thereby enabling the development of efficient and practical BCI systems. Korean 한국뇌공학회 CNN-based Input-Aware Gradient Channel Selection for Motor Imagery Classification 운동 상상 분류를 위한 CNN 기반의 입력 인지형 그라디언트 채널 선택 Conference 2 2026 뇌와 인공지능 심포지엄 2026 뇌와 인공지능 심포지엄 KO 웰리힐리파크 2026-02-04 2026 뇌와 인공지능 심포지엄