Unsupervised training dataset curation for deep-neural-net RF signal classification

George Sklivanitis; Jose A. Sanchez Viloria; Konstantinos Tountas; Dimitris A. Pados; Elizabeth Serena Bentley; Michael J. Medley

doi:10.1117/12.2665151

13 June 2023 Unsupervised training dataset curation for deep-neural-net RF signal classification

George Sklivanitis, Jose A. Sanchez Viloria, Konstantinos Tountas, Dimitris A. Pados, Elizabeth Serena Bentley, Michael J. Medley

Author Affiliations +

Proceedings Volume 12522, Big Data V: Learning, Analytics, and Applications ; 125220C (2023) https://doi.org/10.1117/12.2665151
Event: SPIE Defense + Commercial Sensing, 2023, Orlando, Florida, United States

Abstract

We consider the problem of unsupervised (blind) evaluation and assessment of the quality of data used for deep neural network (DNN) RF signal classification. When neural networks train on noisy or mislabeled data, they often (over-) fit to the noise measurements and faulty labels, which leads to significant performance degradation. Also, DNNs are vulnerable to adversarial attacks, which can considerably reduce their classification performance, with extremely small perturbations of their input. In this paper, we consider a new method based on L1-norm principal-component analysis (PCA) to improve the quality of labeled wireless datasets that are used for training a convolutional neural network (CNN), and a deep residual network (ResNet) for RF signal classification. Experiments with data generated for eleven classes of digital and analog modulated signals show that L1-norm tensor conformity curation of the data identifies and removes from the training dataset inappropriate class instances that appear due to mislabeling and universal black-box adversarial attacks and drastically improves/restores the classification accuracy of the identified deep neural network architectures.

Conference Presentation

Citation Download Citation

George Sklivanitis, Jose A. Sanchez Viloria, Konstantinos Tountas, Dimitris A. Pados, Elizabeth Serena Bentley, and Michael J. Medley "Unsupervised training dataset curation for deep-neural-net RF signal classification", Proc. SPIE 12522, Big Data V: Learning, Analytics, and Applications , 125220C (13 June 2023); https://doi.org/10.1117/12.2665151

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available