Autoencoders for learning template spectrograms in electrocorticographic signals

• Published in: Journal of neural engineering Vol. 16; no. 1; pp. 16025 - 16036
• Main Authors: Pailla, Tejaswy, Miller, Kai J, Gilja, Vikash
• Format: Journal Article
• Language: English
• Published: England IOP Publishing 01.02.2019
• Subjects: autoencoders; Brain Mapping - methods; Brain-Computer Interfaces; brain-machine interfaces; Cerebral Cortex - diagnostic imaging; Cerebral Cortex - physiology; Cerebral Cortex - physiopathology; clustering; Drug Resistant Epilepsy - diagnosis; Drug Resistant Epilepsy - physiopathology; electrocorticography; Electrocorticography - methods; Electrodes, Implanted; Electroencephalography - methods; functional mapping; Humans; Learning - physiology; Magnetic Resonance Imaging - methods; Movement - physiology; neural decoding; neural networks

Objective. Electrocorticography (ECoG) based studies generally analyze features from specific frequency bands selected by manual evaluation of spectral power. However, the definition of these features can vary across subjects, cortical areas, tasks and across time for a given subject. We propose an...