AI-driven RF signal classifier for spectrum monitoring
This technology uses machine learning to automatically identify and classify radio frequency (RF) signals by training neural networks to recognize signal characteristics and the environments in which they operate. The system works by taking an RF signal, extracting known features from it, and then training a neural network to predict those features as classification labels — essentially teaching a computer to 'read' the radio spectrum. The training method measures how far off the network's predictions are from known ground truth and continuously updates the model to improve accuracy. Once trained, the identifier can be deployed to autonomously recognize signal types, modulations, or interference in real time.
What you could build
A software or embedded system module that auto-classifies RF signals for spectrum monitoring, interference detection, or wireless device authentication — sold to defense contractors, telecom network operators, or spectrum management agencies needing automated spectrum awareness.
Who in Virginia should care
Defense primes and government contractors concentrated in Northern Virginia and the Hampton Roads corridor — particularly those supporting DoD spectrum operations, electronic warfare, and signals intelligence — would have direct procurement interest.
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
- May 5, 2020
- Status
- Granted patent
- Patent number
- 10643153
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.