Search

This paper analyzes and evaluates various denoising techniques, including Wavelet Transform and Moving Average Filter methods for removing ocular and motion artifacts from EEG signals. The performance of each technique is benchmarked in terms of signal-to-noise ratio (SNR) and normalized mean squared error (NMSE) on available EEG databases, including Bonn and Motion-Artifact Contaminated EEG databases. Simulation results show that the Wavelet Transform using the SURE Shrink algorithm with the hard thresholding rule has the best performance for removing ocular artifacts in intracranial EEG. In contrast, the Wavelet Transform using the universal threshold shrinkage rule with hard thresholding is the preferred method for removing motion artifacts in scalp EEGs. This study is an essential step toward more advanced work to achieve real-time, and low-cost denoising methods for energy-constrained devices.

We propose an efficient seizure prediction model based on a two-layer LSTM using the Swish activation function. The proposed structure performs feature extraction based on the time and frequency domains and uses the minimum distance algorithm as a post-processing step. The proposed model is evaluated on the Melbourne dataset and achieves the highest Area Under Curve (AUC) score of 0.92 and the lowest False Positive Rate (FPR) of 0.147 compared to previous work while having sensitivity and accuracy of 86.8 and 85.1, respectively. The proposed system has a low number of trainable parameters, and thus reducing the complexity of resource-constrained applications.

This paper provides a comprehensive analysis of the available EEG datasets that are used for epilepsy prediction systems, including Melbourne, CHB-MIT, American Epilepsy Society, Bonn, and European Epilepsy datasets. These datasets are compared in terms of the sampling rate, number of patients, recording time, number of channels, artifacts, and types of EEG signals. We also provide details on the challenges of using one dataset over the others in predicting epilepsy. Subsequently, we compare the performance of various machine learning models that use these datasets for epileptic seizure prediction. This is the first work that provides a comprehensive analysis of various EEG datasets and should be of great importance for researchers in EEG-based systems for epileptic seizure prediction.