nASR is an end-to-end trainable Keras layer for channel-level EEG artifact subspace reconstruction that outperforms traditional ASR with 6-8x faster inference on BCI Competition IV data.
Blind channel estimation based on maximizing the eigenvalue spread of cumulant matrices in (2 × 1) Alamouti’s coding schemes,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SP 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
nASR: An End-to-End Trainable Neural Layer for Channel-Level EEG Artifact Subspace Reconstruction in Real-Time BCI
nASR is an end-to-end trainable Keras layer for channel-level EEG artifact subspace reconstruction that outperforms traditional ASR with 6-8x faster inference on BCI Competition IV data.