Transfer learning has allowed for more widespread adaptation and expanded use of deep learning models in fields such as computer vision and speech recognition. The radio frequency (RF) domain has lagged behind and has yet to experience similar gains. Yet, at the same time, transfer learning is more relevant to tasks the RF domain. Few large labeled RF datasets exist and when they are available there is typically a difference between the dataset, i.e., the source data, and any target data application due to the myriad of variances that are introduced to RF signals, systems, and environments. Transfer learning focuses directly on this disparity between source and target data and changes in task, making it an ideal candidate to enable more widespread adaptation of deep learning within the RF domain. In this paper we explore several applications of transfer learning to RF signals using both synthetic and real-world communications signals. We focus on an RF fingerprinting task, using our RiftNet model as the base of our deep learning models. This paper presents approaches and results for RF transfer learning in the context of pre-trained models, re-tuning, unsupervised feature learning, and novel device detection. Moving beyond the methods and results presented in this paper, we hope this work motivates others to explore the potential and benefits of RF applications of transfer learning.

Radio transmitters can be identified by their unique radio frequency (RF) fingerprints. Hardware differences and manufacturing variations between different RF devices impart the unique RF fingerprints to their transmitted waveforms, which can be exploited to accurately distinguish them. Most previous work has focused on using expert-defined physics-based features to distinguish between 100 or less individual devices, with more recent trends turning to machine learning, and deep learning in particular. In this paper, we present a deep learning approach that scales to 10,000 devices, across different signal types, with upwards of 95% accuracy, which we call RiftNet (Resampling in Frequency and Time Network). RiftNet is particularly suited to pulling out generic signal features that may be relevant to other RF machine learning tasks, beyond just fingerprinting,

Information transmission through the use of video imagining systems has the potential to build upon the success of imaging communication systems, such as QR Codes and 2D Barcodes. Video communication systems add a temporal dimension to image-based information transmission systems, greatly expanding the amount of data that can be transferred. Such a system allows for secure transfer of data through the use of a line-of-sight (LOS) visual channel, making it attractive for several applications, including in-store purchases, banking, and stealth military missions. The nature of the LOS visual channel also reduces interference from other applications, making it a very attractive option for implementing short range communications systems from a cell phone, computer, tablet, or other device. This paper investigates how a video imaging system can be used for information transmission. A prototype system has been designed and implemented as a proof of concept, and the performance of the prototype is evaluated.