Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/aminboumerdassi/tgwn-anomalydetection

A convolutional autoencoder trained on transient gravitational wave noise (glitches) from the Gravity Spy database. Its purpose is for anomaly detection (non-anomaly=glitches,anomaly=astrophysical transient events).

https://github.com/aminboumerdassi/tgwn-anomalydetection

Science Score: 23.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ○
    codemeta.json file
  • ○
    .zenodo.json file
  • ✓
    DOI references
    Found 1 DOI reference(s) in README
  • ✓
    Academic publication links
    Links to: arxiv.org, iop.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (3.2%) to scientific vocabulary
Last synced: 6 months ago · JSON representation

Repository

A convolutional autoencoder trained on transient gravitational wave noise (glitches) from the Gravity Spy database. Its purpose is for anomaly detection (non-anomaly=glitches,anomaly=astrophysical transient events).

Basic Info
  • Host: GitHub
  • Owner: AminBoumerdassi
  • Language: Python
  • Default Branch: main
  • Size: 10.7 KB
Statistics
  • Stars: 1
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 3 years ago · Last pushed over 3 years ago

https://github.com/AminBoumerdassi/TGWN-AnomalyDetection/blob/main/ 

# TGWN-AnomalyDetection (read "tee-gwin")
### Transient Gravitational Wave Noise Anomaly Detection
A convolutional autoencoder trained on transient gravitational wave noise (glitches) from the Gravity Spy database.
Its purpose is for anomaly detection (non-anomaly=glitches, anomaly=astrophysical transient events).
If successful, this will form the glitch rejection mechanism for the GW-ML burst detection pipeline MLy.

Paper on the MLy pipeline: https://arxiv.org/abs/2009.14611 

Paper on the Gravity Spy database: https://iopscience.iop.org/article/10.1088/1361-6382/aa5cea


#To train the autoencoder
1. Download or query the Gravity Spy database to retrieve all of the glitchs' metadata
2. Feed these metadata into MLy's generator function to create timeseries of glitches with real noise
3. Train the autoencoder on a given glitch type
4. Test it on simulated transient events

Owner

  • Login: AminBoumerdassi
  • Kind: user

GitHub Events

Total
  • Watch event: 1
Last Year
  • Watch event: 1