JonathanCrabbe/FourierDiffusion

This repository implements time series diffusion in the frequency domain.

39
/ 100
Emerging

This tool helps researchers and data scientists generate realistic synthetic time series data by training diffusion models in the frequency domain. You input existing time series datasets (like ECG or financial data), and it outputs new, synthetic time series samples that mimic the characteristics of your original data. It's designed for anyone working with time series data who needs to augment datasets or understand underlying data generation processes.

No commits in the last 6 months.

Use this if you need to generate high-quality synthetic time series data for tasks like anomaly detection, forecasting, or privacy-preserving data sharing.

Not ideal if you're looking for a simple, off-the-shelf solution for basic time series analysis without model training.

time-series-analysis synthetic-data-generation machine-learning-research signal-processing data-augmentation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

61

Forks

10

Language

Jupyter Notebook

License

MIT

Last pushed

Mar 02, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/JonathanCrabbe/FourierDiffusion"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.