English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We develop a hybrid model-based data-driven seizure detection algorithmcalled Mutual Information-based CNNAided Learned factor graphs (MICAL) fordetection of eclectic seizures from EEG signals. Our proposed method containsthree main components: a neural mutual information (MI) estimator, 1Dconvolutional neural network (CNN), and factor graph inference. Since duringseizure the electrical activity in one or more regions in the brain becomescorrelated, we use neural MI estimators to measure inter-channel statisticaldependence. We also design a 1D CNN to extract additional features from raw EEGsignals. Since the soft estimates obtained as the combined features from theneural MI estimator and the CNN do not capture the temporal correlation betweendifferent EEG blocks, we use them not as estimates of the seizure state, but tocompute the function nodes of a factor graph. The resulting factor graphsallows structured inference which exploits the temporal correlation for furtherimproving the detection performance. On public CHB-MIT database, We conductthree evaluation approaches using the public CHB-MIT database, including 6-foldleave-four-patients-out cross-validation, all patient training; and per patienttraining. Our evaluations systematically demonstrate the impact of each elementin MICAL through a complete ablation study and measuring six performancemetrics. It is shown that the proposed method obtains state-of-the-artperformance specifically in 6-fold leave-four-patients-out cross-validation andall patient training, demonstrating a superior generalizability.

MICAL: Mutual Information-Based CNN-Aided Learned Factor Graphs for Seizure Detection from EEG Signals