A medium-weight deep convolutional neural network-based approach for onset epileptic seizures classification in EEG signals

Abstract

Introduction: Epileptic condition can be detected in EEG data seconds before it occurs, according to evidence. To overcome the related long-term mortality and morbidity from epileptic seizures, it is critical to make an initial diagnosis, uncover underlying causes, and avoid applicable risk factors. Progress in diagnosing onset epileptic seizures can ensure that seizures and destroyed damages are detectable at the time of manifestation. Previous seizure detection models had problems with the presence of multiple features, the lack of an appropriate signal descriptor, and the time-consuming analysis, all of which led to uncertainty and different interpretations. Deep learning has recently made tremendous progress in categorizing and detecting epilepsy.

Method: This work proposes an effective classification strategy in response to these issues. The discrete wavelet transform (DWT) is used to breakdown the EEG signal, and a deep convolutional neural network (DCNN) is used to diagnose epileptic seizures in the first phase. Using a medium-weight DCNN (mw-DCNN) architecture, we use a preprocess phase to improve the decision-maker method. The proposed approach was tested on the CHEG-MIT Scalp EEG database's collected EEG signals.

Result: The results of the studies reveal that the mw-DCNN algorithm produces proper classification results under various conditions. To solve the uncertainty challenge, K-fold cross-validation was used to assess the algorithm's repeatability at the test level, and the accuracies were evaluated in the range of 99%-100%.

Conclusion: The suggested structure can assist medical specialistsin analyzing epileptic seizures' EEG signals more precisely.

Keywords: EEG; convolutional neural network; discrete wavelet decomposition; early seizure detection; medium-weight structure.

FIGURE 1

We have used discrete wavelet decomposition (DWT) method to decompose EEG signals into multiple subbands. The down arrow is downsampling by 2

FIGURE 2

The schematic of introduced approach for identifying the onset epileptic seizures

FIGURE 3

Utilization of h[n] and g[n] filters to decompose EEG signals (x[n]) into subbands

FIGURE 4

Proposed medium‐weight structure of the deep convolutional network

FIGURE 5

This figure depicts correlation maps of decomposed EEG signal for a patient

FIGURE 6

The ROC curve of two test EEG signals

FIGURE 7

The ROC curve of two unseen EEG signals

FIGURE 8

Similar methods were compared to the recommended strategy in order to determine the onset of an epileptic episode

FIGURE 9

This figure shows the comparison of the accuracy of the classification with three classes. Experiment 1 has been performed without decomposition of input signals. Experiment 2 has been carried out with decomposition by DWT on input signals, and also, the network has a large number of layers. Finally, Experiment 3 has been conducted with decomposition by DWT on input signals, and also, the network structure has a low number of layers

FIGURE 10

mw‐DCNN convergence in reducing the error in training data—random data 1 after 31 iterations and reaching the minimum value of zero in the classifier cost function

FIGURE 11

mw‐DCNN convergence in reducing the error in training data—random data 2 after 14 iterations and reaching the minimum value of zero in the classifier cost function

FIGURE 12

mw‐DCNN convergence in reducing the error in training data—random data 3 after 8 iterations and reaching the minimum value of zero in the classifier cost function