Open Access. Powered by Scholars. Published by Universities.®
- Discipline
- Publication
Articles 1 - 2 of 2
Full-Text Articles in Vision Science
Adversarial Robustness In Biomedical Time-Series Models, Rohan Tiwari
Adversarial Robustness In Biomedical Time-Series Models, Rohan Tiwari
Bioengineering Theses
This study investigates adversarial vulnerabilities in deep learning models for biomedical time-series classification across two clinically important modalities: electrocardiography (ECG) and electroencephalography (EEG). Using the MIT-BIH Arrhythmia and CHB-MIT seizure datasets, I evaluate time-domain attacks (FGSM, PGD), Fourier-domain constrained attacks, and learned spectral perturbations designed to reveal modality-specific sensitivity patterns. Across both tasks, a consistent trend emerges low-frequency components (0–5 Hz) constitute a dominant axis of adversarial vulnerability, with perturbations in this range producing the steepest degradation in classification performance. In ECG models, protecting the physiologically relevant QRS band (5–20 Hz) significantly improves robustness, whereas EEG models remain highly sensitive …
A Comparison Of Neural Activity For Peripersonal And Extrapersonal Viewing In Real And Virtual Environments, Olivia Eustice
A Comparison Of Neural Activity For Peripersonal And Extrapersonal Viewing In Real And Virtual Environments, Olivia Eustice
Honors Theses
This study involved a series of tests comparing the similarities and differences in neural activity at a subject’s peripheral and extrapersonal space in the real environment and virtual reality. We hypothesized that there would be similar brain activity at each of these environments depending on the focal distance of an object from the participant. Peripheral space is the visual space that is a reachable distance from a person. It has an overall neural pattern in the dorsal stream of the brain. Extrapersonal space is the visual space that does not directly surround a person and cannot be directly acted on. …