TY - GEN
T1 - CNN-Aided Factor Graphs with Estimated Mutual Information Features for Seizure Detection
AU - Salafian, Bahareh
AU - Ben-Knaan, Eyal Fishel
AU - Shlezinger, Nir
AU - de Ribaupierre, Sandrine
AU - Farsad, Nariman
N1 - Funding Information:
This work is supported by Discovery Grant from the Natural Sciences and Engineering Research Council of Canada (NSERC), grant number RGPIN-2020-04926, and Canada Foundation for Innovation (CFI), John R. Evans Leader Fund, grant number 39767.
Publisher Copyright:
© 2022 IEEE
PY - 2022
Y1 - 2022
N2 - We propose a convolutional neural network (CNN) aided factor graphs assisted by mutual information features estimated by a neural network for seizure detection. Specifically, we use neural mutual information estimation to evaluate the correlation between different electroencephalogram (EEG) channels as features. We then use a 1D-CNN to extract extra features from the EEG signals and use both features to estimate the probability of a seizure event. Finally, learned factor graphs are employed to capture the temporal correlation in the signal. Both sets of features from the neural mutual estimation and the 1D-CNN are used to learn the factor nodes. We show that the proposed method achieves state-of-the-art performance using 6-fold leave-four-patients-out cross-validation.
AB - We propose a convolutional neural network (CNN) aided factor graphs assisted by mutual information features estimated by a neural network for seizure detection. Specifically, we use neural mutual information estimation to evaluate the correlation between different electroencephalogram (EEG) channels as features. We then use a 1D-CNN to extract extra features from the EEG signals and use both features to estimate the probability of a seizure event. Finally, learned factor graphs are employed to capture the temporal correlation in the signal. Both sets of features from the neural mutual estimation and the 1D-CNN are used to learn the factor nodes. We show that the proposed method achieves state-of-the-art performance using 6-fold leave-four-patients-out cross-validation.
UR - http://www.scopus.com/inward/record.url?scp=85131234760&partnerID=8YFLogxK
U2 - 10.1109/ICASSP43922.2022.9746730
DO - 10.1109/ICASSP43922.2022.9746730
M3 - Conference contribution
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 8677
EP - 8681
BT - 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
PB - Institute of Electrical and Electronics Engineers
T2 - 47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022
Y2 - 23 May 2022 through 27 May 2022
ER -