Many scientific and industrial domains rely on time-series data (e.g., sensor readings, lab measurements, clinical monitoring). However, datasets are often incomplete, noisy, or sensitive to share due to privacy concerns. Generative AI offers new possibilities to improve data quality and generate realistic synthetic datasets for research, training, or collaboration. Recent advances in Large Language Models (LLMs) suggest they could be used not only for text but also for understanding, cleaning, and generating structured data, when guided by contextual descriptions such as lab protocols or dataset documentation. This project explores the potential of LLMs to act as assistants in time-series data management and synthetic data creation.
This project will investigate how LLMs can support synthetic data generation and data quality improvement in a time-series context. The system should demonstrate how LLMs can:
- Understand and analyze datasets: Use context data (e.g., lab descriptions, metadata) to interpret the characteristics of a given time-series dataset (or multiple datasets). Generate a summary report highlighting key features, ranges, and anomalies.
- Assess and improve data quality: Detect issues such as missing values, outliers, or inconsistencies, and propose or implement fixes to improve the dataset.
- Generate synthetic data: Produce realistic synthetic datasets that preserve statistical and temporal properties of the original while being safe to share.
The project should also include reflection on the suitability and limitations of LLMs for these tasks, and on the ethical aspects of synthetic data generation.