CNN-Aided Factor Graphs with Estimated Mutual Information Features for\n Seizure Detection

2022/03/11 by Bahareh Salafian, Eyal Fishel Ben-Knaan, Salafian, Bahareh +7
Computer Science · Neuroscience · #Blind Source Separation Techniques #Brain Tumor Detection and Classification #EEG and Brain-Computer Interfaces #FOS: Electrical engineering #Signal Processing (eess.SP) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2203.05950

openalex publication_date 2022/03/11 · openalex created_date 2022/05/05 · openalex updated_date 2026/07/28

Abstract

We propose a convolutional neural network (CNN) aided factor graphs assisted\nby mutual information features estimated by a neural network for seizure\ndetection. Specifically, we use neural mutual information estimation to\nevaluate the correlation between different electroencephalogram (EEG) channels\nas features. We then use a 1D-CNN to extract extra features from the EEG\nsignals and use both features to estimate the probability of a seizure\nevent.~Finally, learned factor graphs are employed to capture the temporal\ncorrelation in the signal. Both sets of features from the neural mutual\nestimation and the 1D-CNN are used to learn the factor nodes. We show that the\nproposed method achieves state-of-the-art performance using 6-fold\nleave-four-patients-out cross-validation.\n

Related

• MICAL: Mutual Information-Based CNN-Aided Learned Factor Graphs for Seizure Detection from EEG Signals
• Efficient Epileptic Seizure Detection Using CNN-Aided Factor Graphs
• An Explainable Model for EEG Seizure Detection based on Connectivity Features
• Temporal Graph Convolutional Networks for Automatic Seizure Detection
• A framework for seizure detection using effective connectivity, graph theory and deep modular neural networks