ajayarunachalam/msda

Library for multi-dimensional, multi-sensor, uni/multivariate time series data analysis, unsupervised feature selection, unsupervised deep anomaly detection, and prototype of explainable AI for anomaly detector

55
/ 100
Established

This tool helps engineers and data analysts quickly identify unusual behavior or critical changes within complex systems monitored by many sensors. It takes raw, high-dimensional time series data from multiple sensors and helps you understand which sensor readings are most important, ultimately providing real-time alerts for anomalies and explanations for why an anomaly was flagged. It's designed for data scientists, researchers, and engineers working with sensor data.

129 stars. No commits in the last 6 months. Available on PyPI.

Use this if you need to rapidly prototype and deploy systems for detecting unusual patterns or anomalies in streaming, multi-sensor time series data and want to understand the factors contributing to those anomalies.

Not ideal if your data is not time-series based, if you are looking for general forecasting without anomaly detection, or if you prefer a no-code solution without any Python scripting.

industrial-iot predictive-maintenance sensor-monitoring system-health operations-analytics
Stale 6m No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 20 / 25

How are scores calculated?

Stars

129

Forks

29

Language

Jupyter Notebook

License

Last pushed

Oct 07, 2021

Commits (30d)

0

Get this data via API

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

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