Main Article Content
Epilepsy is one of the world's most common neurological diseases. Early prediction of the incoming seizures has a great influence on epileptic patients’ life. In this, a seizure prediction technique based on CNN and applied to long-term scalp EEG recordings is proposed. The goal is to accurately detect the preictal brain state and differentiate it from the prevailing interictal state as early as possible and make it suitable for real-time. The raw EEG signals instead of manual feature extraction was used to distinguish ictal, preictal, and interictal segments for epileptic seizure detection. . In our model, we used time or frequency domain signals as inputs for classification. The frequency domain is a coordinate system that describes the frequency features of the signals. A frequency spectrogram reflects the relationship between the frequency and amplitude of a signal and is often used to analyze signal features. We compared the performances of time and frequency domain signals in the detection of epileptic signals. In our study, we used a very simple CNN structure. the CNN included only three main layers, and the network was very simple compared with the deep network. Meanwhile, satisfactory results were obtained. The achieved highest accuracy over 90% and the algorithm can be modified in a way that it works online and alerts in real time.
This work is licensed under a Creative Commons Attribution-NoDerivatives 4.0 International License.
CC Attribution-NoDerivatives 4.0