Degree Name
MS (Master of Science)
Program
Mathematical Sciences
Date of Award
12-2025
Committee Chair or Co-Chairs
Jeff R Knisley
Committee Members
Mostafa Zahed, Robert A. Beeler
Abstract
Generative Adversarial Networks (GANs) are a class of deep learning models capable of producing realistic synthetic data that preserve the statistical and temporal characteristics of real datasets. The DoppelGANger (DGAN) framework extends this approach to time series data by jointly modeling temporal dependencies and contextual metadata. However, synthetic sequences generated by GAN may show temporal misalignment, resulting in inconsistencies when compared with real data. This study presents a postprocessing framework based on Dynamic Time Warping (DTW) and its differentiable extension Soft-DTW to improve the temporal alignment of synthetic time series. The framework is evaluated using quantitative measures of alignment and similarity. Results show that Soft-DTW enhances temporal coherence and statistical fidelity, demonstrating that the proposed postprocessing approach refines GAN-generated time series and improves their interpretability.
Document Type
Dissertation - unrestricted
Recommended Citation
Roni, Md Raisul Islam, "Postprocessing GAN-Generated Synthetic Time Series Using Dynamic Time Warping" (2025). Electronic Theses and Dissertations. Paper 4635. https://dc.etsu.edu/etd/4635
Copyright
Copyright by the authors.
