low-power MCU

Reducing False Alarms in Wearable Seizure Detection With EEGformer: A Compact Transformer Model for MCUs
Compact transformer seizure detector that achieves 73% sensitivity with 0.15 FP/h and runs in 13.7 ms at 0.31 mJ on GAP9.
Paola Busia, Andrea Cossettini, Thorir Mar Ingolfsson, Simone Benatti, Alessio Burrello, Victor J. B. Jung, Moritz Scherer, Matteo A. Scrugli, Adriano Bernini, Pauline Ducouret, Philippe Ryvlin, Paolo Meloni, Luca Benini
PDF Cite Dataset IEEE Xplore CHB-MIT Dataset
Reducing False Alarms in Wearable Seizure Detection With EEGformer: A Compact Transformer Model for MCUs