Towards Long-term Non-invasive Monitoring for Epilepsy via Wearable EEG Devices

We present the implementation of seizure detection algorithms based on a minimal number of EEG channels on a parallel ultra-low-power embedded platform. The analyses are based on the CHB-MIT dataset, and include explorations of different classification approaches (Support Vector Machines, Random For...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2021 IEEE Biomedical Circuits and Systems Conference (BioCAS) s. 01 - 04
Hlavní autoři: Ingolfsson, Thorir Mar, Cossettini, Andrea, Wang, Xiaying, Tabanelli, Enrico, Tagliavini, Giuseppe, Ryvlin, Philippe, Benini, Luca, Benatti, Simone
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 07.10.2021
Témata:
deep learning
Electroencephalography
Epilepsy
healthcare
Inference algorithms
machine learning
Prediction algorithms
Sensitivity
smart edge computing
Support vector machines
time series classification
Wearable computers
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:We present the implementation of seizure detection algorithms based on a minimal number of EEG channels on a parallel ultra-low-power embedded platform. The analyses are based on the CHB-MIT dataset, and include explorations of different classification approaches (Support Vector Machines, Random Forest, Extra Trees, AdaBoost) and different pre/post-processing techniques to maximize sensitivity while guaranteeing no false alarms. We analyze global and subject-specific approaches, considering all 23-electrodes or only 4 temporal channels. For 8 s window size and subject-specific approach, we report zero false positives and 100% sensitivity. These algorithms are parallelized and optimized for a parallel ultra-low power (PULP) platform, enabling 300h of continuous monitoring on a 300 mAh battery, in a wearable form factor and power budget. These results pave the way for the implementation of affordable, wearable, long-term epilepsy monitoring solutions with low false-positive rates and high sensitivity, meeting both patient and caregiver requirements.
DOI:10.1109/BioCAS49922.2021.9644949