Subject-specific CNNs on EEG spectrograms reach 80% accuracy detecting A-phases and 72-79% classifying subtypes using only 25% labeled data per person.
Automatic detection of cyclic alter- nating pattern
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SP 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A-Phase classification using convolutional neural networks
Subject-specific CNNs on EEG spectrograms reach 80% accuracy detecting A-phases and 72-79% classifying subtypes using only 25% labeled data per person.