Training Data Augmentation for Deep Learning RF Systems

10/01/2020
by   William H. Clark IV, et al.
0

Applications of machine learning are subject to three major components that contribute to the final performance metrics. Within the specifics of neural networks, and deep learning specifically, the first two are the architecture for the model being trained and the training approach used. This work focuses on the third component, the data being used during training. The questions that arise are then "what is in the data" and "what within the data matters?" Looking into the Radio Frequency Machine Learning (RFML) field of Modulation Classification, the use of synthetic, captured, and augmented data are examined and compared to provide insights about the quantity and quality of the available data presented. In general, all three data types have useful contributions to a final application, but captured data germane to the intended use case will always provide more significant information and enable the greatest performance. Despite the benefit of captured data, the difficulties that arise from collection often make the quantity of data needed to achieve peak performance impractical. This paper helps quantify the balance between real and synthetic data, offering concrete examples where training data is parametrically varied in size and source.

READ FULL TEXT

page 3

page 7

page 8

research
05/07/2022

Quantifying and Extrapolating Data Needs in Radio Frequency Machine Learning

Understanding the relationship between training data and a model's perfo...
research
06/27/2023

On the Usefulness of Synthetic Tabular Data Generation

Despite recent advances in synthetic data generation, the scientific com...
research
04/02/2018

Generative Adversarial Learning for Spectrum Sensing

A novel approach of training data augmentation and domain adaptation is ...
research
06/26/2022

RF Signal Classification with Synthetic Training Data and its Real-World Performance

Neural nets are a powerful method for the classification of radio signal...
research
03/26/2019

Augmented Ultrasonic Data for Machine Learning

Flaw detection in non-destructive testing, especially in complex signals...
research
11/11/2020

Where to drive: free space detection with one fisheye camera

The development in the field of autonomous driving goes hand in hand wit...
research
10/12/2022

Projective Transformation Rectification for Camera-captured Chest X-ray Photograph Interpretation with Synthetic Data

Automatic interpretation on smartphone-captured chest X-ray (CXR) photog...

Please sign up or login with your details

Forgot password? Click here to reset