Theoretical Analysis of CNNs for Automatic Seizure Detection in EEG Signals

Built a 1D CNN with Butterworth bandpass filtering for automatic seizure detection in EEG signals, achieving 97% accuracy and 0.99 AUC on the University of Bonn EEG dataset. Formally proved Lipschitz stability bounds (L = 24.72) to establish robustness against real-world signal noise — bridging deep learning application with mathematical theory. Advised by Dr. Chudamani Poudyal (SDMSS, UCF).

Recommended citation: Small, J. T. (2025). "Theoretical Analysis of CNNs for Automatic Seizure Detection in EEG Signals." UCF STARS Honors Undergraduate Theses, No. 462.
Download Paper