Research
Generative models for synthetic data, matrix manifolds, and GenAI for VR-based brain-injury rehabilitation.
- Thesis Completed
M.S. Thesis: Synthetic Data Generation (StatGenAI)
California State University Channel Islands
Statistical and deep generative approaches (GANs, CTGANs, VAEs, KDE, multivariate Gaussians) for synthetic tabular data, reaching up to 99% accuracy at 15 dimensions.
- Preprint In progress
Manifold-based Data Generation
Generative models that operate on matrix manifolds, so synthetic data respects the intrinsic geometry of real data.
- Preprint In progress
AIENs: Adaptive Initializer Enhancer Networks
Replaces the Gaussian prior in a VAE's KL-divergence loss with adaptive kernel density estimation, cutting training time by 19% and improving synthetic-data fidelity by 9%.
- Publication Under review
Virtual Reality Rehabilitation for a Post-ICU Hospitalized Patient with a Traumatic Brain Injury: A Case Report
Neuropsychological Rehabilitation
A case report on VR-based cognitive rehabilitation for a post-ICU patient with traumatic brain injury, using focus, memory and GenAI communication scenarios.