Back to the portfolio

Transformer-based AI module for radio emitter identification

Communications & RFComputing, Software & AIDefense & Aerospace ApplicationsLab validated

This technology uses a two-stage AI system to better understand radio signals being received over a wireless channel. A first neural network analyzes the signal and produces preliminary information, which is then fed—along with the original signal—into a 'signal transformer' that reshapes and conditions the signal based on how the channel is behaving. A second neural network then processes this transformed signal to extract detailed information about where the signal came from and who is transmitting it. The result is a smarter radio receiver that can identify emitters and infer context that traditional signal processing would miss.

What you could build

An AI-powered signal intelligence module embedded in spectrum monitoring systems, software-defined radios, or cellular base stations that can identify and classify radio emitters in real time; primary buyers would be defense contractors, spectrum regulators, and telecom equipment vendors.

Who in Virginia should care

Northern Virginia and the Hampton Roads corridor host major defense primes (Leidos, SAIC, Booz Allen) and Navy/DoD spectrum operations that actively seek AI-enhanced signal intelligence capabilities.

Readiness: Lab validated

Concept — described but not yet demonstrated. Lab validated — supported by experimental results in the patent. Prototype likely — the text describes a built, working embodiment.

Readiness is inferred from the patent text, not from a lab visit.

The record

Inventors
Timothy James O`Shea
Granted
August 13, 2024
Status
Granted patent
Patent number
12061982

Ready to talk?

Virginia Tech Intellectual Properties handles licensing for this technology.

VTIP contact coming shortly

Prosim summaries are generated from public patent text and are not legal advice.