akash13singh/lstm_anomaly_thesis

Anomaly detection for temporal data using LSTMs

49
/ 100
Emerging

This project helps you identify unusual patterns or events within continuous streams of data, like sensor readings or usage logs, even without prior examples of what an 'anomaly' looks like. It takes your historical time series data and outputs scores that highlight points in time that deviate significantly from learned normal behavior. This is ideal for analysts, operations managers, or scientists who monitor equipment, systems, or natural phenomena and need to flag irregular occurrences.

226 stars. No commits in the last 6 months.

Use this if you have continuous, sequential data and need to automatically detect deviations or outliers without having pre-labeled examples of anomalies.

Not ideal if your data isn't sequential, if you already have a comprehensive set of labeled anomalies for training, or if you're dealing with very simple time series where basic methods might suffice.

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

How are scores calculated?

Stars

226

Forks

85

Language

Jupyter Notebook

License

MIT

Last pushed

Oct 05, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/akash13singh/lstm_anomaly_thesis"

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