AI-driven automatic RF signal classification for spectrum
This technology uses machine learning to automatically identify and classify radio frequency signals based on their modulation type and transmission characteristics. It works by breaking an incoming RF signal into mathematical components, then running those components through a neural network trained to recognize signal patterns. The system continuously improves by comparing its predictions against known signal labels and adjusting itself accordingly. Essentially, it is a self-improving radio signal fingerprinting engine that can be trained and then deployed in real-world RF environments.
What you could build
A software module or embedded system for automatic modulation recognition and spectrum monitoring, sold to defense electronics integrators, telecom network operators, and spectrum management agencies that need to identify interfering or unauthorized signals in real time.
Who in Virginia should care
Defense and intelligence contractors concentrated in Northern Virginia—such as SAIC, Leidos, Booz Allen, and Peraton—actively seek RF signal intelligence and spectrum awareness capabilities for government customers.
Readiness: Prototype likely
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 10, 2023
- Status
- Granted patent
- Patent number
- 11783196
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.