Author | Sharon, Sone | |
Date Accessioned | 2023-06-05T13:53:42Z | |
Date Available | 2023-06-05T13:53:42Z | |
Date Created | 2023-05 | |
Date of Issue | 2023-05-04 | |
xmlui.metadata.dc.date.submitted | May 2023 | |
Identifier (URI) | http://hdl.handle.net/10342/12849 | |
Description | Time series data is prevalent in many fields, such as finance, weather forecasting, and
economics. Predicting future values of a time series can provide valuable insights
for decision-making, such as identifying trends, detecting anomalies, and improving
resource allocation. Recently, Generative Adversarial Networks (GANs) have been
used to learn from these features to aid in time-series forecasting. We propose a novel
framework that utilizes the unsupervised paradigm of a GAN based on related research called TimeGAN. Instead of using the discriminator as a classification model,
we employ it as a regressive model to learn both temporal and static features. This
framework can help generate synthetic data and facilitate forecasting. Our model
outperforms TimeGAN, which only preserves temporal dynamics and uses the discriminator as a classifier to distinguish between synthetic and real datasets | |
Mimetype | application/pdf | |
Language | en | |
Publisher | East Carolina University | |
Subject | Time-series data | |
Subject | Recurrent neural networks | |
Subject | Generative Adversarial Networks | |
Subject | Forecasting | |
Title | Time Series Forecasting Using Generative Adversarial Networks | |
Type | Master's Thesis | |
xmlui.metadata.dc.date.updated | 2023-06-02T15:40:58Z | |
Department | Computer Science | |
xmlui.metadata.dc.degree.name | M.S. | |
xmlui.metadata.dc.degree.level | Masters | |
xmlui.metadata.dc.degree.discipline | MS-Data Science | |
xmlui.metadata.dc.degree.grantor | East Carolina University | |
xmlui.metadata.dc.degree.department | Computer Science | |
xmlui.metadata.dc.type.material | text | |