eth-siplab/Unsupervised_Periodicity_Detection

Official code for ICML 2024 paper "An Unsupervised Approach for Periodic Source Detection in Time Series"

28
/ 100
Experimental

This helps researchers and analysts automatically identify repeating patterns within noisy time series data, like heart rate or respiration, without needing pre-labeled examples or carefully crafted data. It takes raw, unlabeled time series data as input and highlights the underlying periodic components. This is ideal for scientists, medical researchers, or behavioral analysts working with physiological or activity sensor data.

No commits in the last 6 months.

Use this if you need to find recurring cycles in time series data without the burden of manually labeling data or struggling with complex data augmentation techniques.

Not ideal if your data is not time series, or if you already have perfectly labeled data and prefer traditional supervised learning methods.

health-monitoring behavior-analysis physiological-sensing signal-processing biometric-data
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 15 / 25

How are scores calculated?

Stars

13

Forks

5

Language

Python

License

Last pushed

Feb 21, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/eth-siplab/Unsupervised_Periodicity_Detection"

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