Epileptic seizure prediction from multivariate EEG data using Multidimensional convolution network

Background: The ability to predict coming seizures will improve the quality of life of patients with epilepsy. Analysis of brain electrical activity using electroencephalogram (EEG) signals can be used to predict seizures.Method:Seizure prediction can be regarded as a binary classification problem between interictal and preictal EEG signals. In this work, we used multidimensional convolutional neural network models to predict seizures. Hospital multivariate EEG data is used in the study. We extracted 22 channels, 10 seconds EEG segments from the interictal and pre-ictal time durations and fed them to the proposed deep learning models.Result:The average accuracy of multidimensional deep network model for multi-channel EEG data is about 94%, the average sensitivity is 88.47%, and the average specificity is 89.75%. Conclusion:The normalized multivariable EEG signals are sent to the multidimensional convolution network to effectively predict seizures.