zamanzadeh/CARLA

CARLA: A self-supervised contrastive learning model for time series anomaly detection. Enhances anomaly detection by learning robust representations of time series data.

42
/ 100
Emerging

This project helps operations engineers and data analysts identify unusual patterns in critical system telemetry. By feeding in continuous sensor readings or system logs, it can flag anomalies that might indicate equipment malfunction, security breaches, or performance degradation. The output helps users quickly pinpoint segments of time series data that deviate from normal behavior, allowing for proactive investigation and maintenance.

143 stars. No commits in the last 6 months.

Use this if you need to reliably detect unexpected events or performance issues within large volumes of unlabeled time series data, such as server metrics, sensor readings, or network traffic.

Not ideal if your time series data is already well-labeled with known anomaly types, as this tool is designed for scenarios where explicit anomaly labels are scarce.

IT-operations sensor-monitoring predictive-maintenance cybersecurity system-health
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

143

Forks

19

Language

Jupyter Notebook

License

MIT

Last pushed

Mar 18, 2025

Commits (30d)

0

Get this data via API

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

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