GANomaly for anomaly detection (w multiple GPU support)
Version 1.0.1 (11,9 KB) von
Da Huang
MATLAB implementation of the GANomaly network architecture for anomaly detection problems.
The code package comes with an example that does the follow: 1. loads data from file, 2. construct GANomaly network, 3. train the GANomaly network, and 4. use trained GANomaly for anomaly detection.
The code comes with multiple GPU support.
The example in the main.m can run on the MNIST datset for readiness check, or on your own dataset.
Condition of use: plese cite the following paper
D. Huang and A. Al-Hourani, "Physical Layer Spoof Detection and Authentication for IoT Devices Using Deep Learning Methods," in IEEE Transactions on Machine Learning in Communications and Networking, vol. 2, pp. 841-854, 2024, doi: 10.1109/TMLCN.2024.3417806.
--------------------------------------------------------------------------------------------------------
P.S.:
1. The MNIST dataset needs to be downloaded and put in the same folder. The dataset can be found in the following link:
2. The helper function for processing the MNIST dataset is modified based on the following MATLAB example:
3. GANomaly is implemented based on the following Github project:
Zitieren als
Huang, Da, and Akram Al-Hourani. “Physical Layer Spoof Detection and Authentication for IoT Devices Using Deep Learning Methods.” IEEE Transactions on Machine Learning in Communications and Networking, vol. 2, Institute of Electrical and Electronics Engineers (IEEE), 2024, pp. 841–54, doi:10.1109/tmlcn.2024.3417806.
Kompatibilität der MATLAB-Version
Erstellt mit
R2023b
Kompatibel mit allen Versionen
Plattform-Kompatibilität
Windows macOS LinuxTags
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!Live Editor erkunden
Erstellen Sie Skripte mit Code, Ausgabe und formatiertem Text in einem einzigen ausführbaren Dokument.
Version | Veröffentlicht | Versionshinweise | |
---|---|---|---|
1.0.1 | Update linked publication |
||
1.0.0 |