ML4ITS/mtad-gat-pytorch

PyTorch implementation of MTAD-GAT (Multivariate Time-Series Anomaly Detection via Graph Attention Networks) by Zhao et. al (2020, https://arxiv.org/abs/2009.02040).

49
/ 100
Emerging

This tool helps engineers and operators identify unusual behavior in complex systems by analyzing multiple sensor readings or operational metrics over time. You input raw, multivariate time-series data from machinery, spacecraft, or IT infrastructure, and it outputs visual charts highlighting detected anomalies. It's designed for professionals managing the health and performance of critical systems.

389 stars. No commits in the last 6 months.

Use this if you need to automatically detect unexpected patterns or malfunctions in streams of interconnected operational data to prevent failures or understand system incidents.

Not ideal if you are working with simple, single-stream data or if you require real-time, ultra-low-latency anomaly detection in a production environment.

predictive-maintenance IT-operations-monitoring industrial-IoT system-health time-series-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

389

Forks

88

Language

Python

License

MIT

Last pushed

Jan 16, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ML4ITS/mtad-gat-pytorch"

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