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
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.
Stars
129
Forks
29
Language
Jupyter Notebook
License
—
Category
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.
Related frameworks
yzhao062/pyod
A Python Library for Outlier and Anomaly Detection, Integrating Classical and Deep Learning Techniques
unit8co/darts
A python library for user-friendly forecasting and anomaly detection on time series.
elki-project/elki
ELKI Data Mining Toolkit
raphaelvallat/antropy
AntroPy: entropy and complexity of (EEG) time-series in Python
Minqi824/ADBench
Official Implement of "ADBench: Anomaly Detection Benchmark", NeurIPS 2022.