Transformer-based AI classifier for radio signals and emitter
This technology uses a two-stage AI system to analyze and interpret radio signals more accurately than a single model could alone. The first neural network processes an incoming radio signal and generates an initial estimate of its characteristics. A 'signal transformer' then uses both the original signal and that first estimate to intelligently reshape or pre-process the signal. This transformed version is fed into a second neural network, which produces a final, higher-quality interpretation of the signal — including information about the devices or emitters that transmitted it.
What you could build
A software module or embedded firmware package for spectrum monitoring, signals intelligence, or radio access network equipment that improves automatic modulation classification and emitter fingerprinting — sold to defense contractors, spectrum management firms, or 5G/NextG equipment vendors.
Who in Virginia should care
Virginia's dense concentration of defense contractors and intelligence community integrators (Leidos, SAIC, Booz Allen, ManTech) working on SIGINT, electronic warfare, and spectrum operations would be natural licensing or partnership targets.
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
- October 11, 2022
- Status
- Granted patent
- Patent number
- 11468317
Ready to talk?
Virginia Tech Intellectual Properties handles licensing for this technology.
Prosim summaries are generated from public patent text and are not legal advice.