Poster + Paper
14 June 2023 Epilepsy seizure detection with a majority voting classifier using logistic regression
Author Affiliations +
Conference Poster
Abstract
Epilepsy is a neurological condition caused by sudden onsets of electrical activity in the brain. This results in frequent, uncommon seizures, which can lead to severe physical consequences. In a clinical setting, data recorded using EEG (Electroencephalogram) is used to help diagnose the condition. This research focuses on the use of Short-Term Fourier transform (STFT) and feature extraction in the EEG data for the use in a majority voting model using logistic regression (LR) to detect the presence of epileptic seizures in the five EEG frequency bands ( i.e. Alpha, Beta, Gamma, Delta, and Theta). To quantify, a number of evaluation metrics have been calculated. Overall, the model was able to achieve an accuracy of up to 92%.
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Paul Oswald, Nida Nasir, Feras Barneih, Omar Alshaltone, Mohammad AlShabi, Talal Bonny, and Ahmed Al-shammaa "Epilepsy seizure detection with a majority voting classifier using logistic regression", Proc. SPIE 12548, Smart Biomedical and Physiological Sensor Technology XX, 125480J (14 June 2023); https://doi.org/10.1117/12.2664003
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Electroencephalography

Artificial neural networks

Time-frequency analysis

Data modeling

Feature extraction

Epilepsy

Brain

Back to Top