zamanzadeh/DACAD

Domain Adaptation Contrastive learning model for Anomaly Detection in multivariate time series (DACAD), combining UDA with contrastive learning. DACAD utilizes an anomaly injection mechanism that enhances generalization across unseen anomalous classes, improving adaptability and robustness.

33
/ 100
Emerging

This helps operations engineers, data scientists, and systems administrators identify unusual behavior in complex systems that generate lots of data over time. You provide historical sensor readings, system logs, or other time-series data, and it tells you where anomalies (like equipment failure or cyberattacks) are likely occurring. This is especially useful when you have plenty of labeled anomaly data from one system but want to detect new, unseen anomalies in a similar, but unlabeled, system.

No commits in the last 6 months.

Use this if you need to detect anomalies in multivariate time series data from a new system, but only have labeled examples of anomalies from a different, related system.

Not ideal if you have extensive labeled anomaly data for your specific target system, or if your systems are vastly different with no shared characteristics.

system-monitoring predictive-maintenance fraud-detection industrial-iot cybersecurity-analytics
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

34

Forks

3

Language

Python

License

MIT

Last pushed

Aug 15, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/zamanzadeh/DACAD"

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