Adaptive interference classifier for congested radio
This technology uses machine learning — specifically neural networks — to automatically identify and classify radio frequency signals in real time. The system is trained on a dataset of RF signals that have been intentionally distorted to simulate real-world interference and propagation effects, making it robust to noisy environments. Once deployed, it can detect the characteristics of electromagnetic interference present in a communication channel and automatically adjust receiver settings in response. In practical terms, it gives a radio system the ability to 'see' what kind of interference it is dealing with and adapt on the fly.
What you could build
An embedded software module for military radios, commercial base stations, or spectrum monitoring equipment that continuously classifies interference and tunes receiver parameters without human intervention; primary buyers would be defense communications primes, telecom equipment OEMs, and spectrum management agencies.
Who in Virginia should care
Northern Virginia and the Hampton Roads corridor host major defense communications primes (Leidos, SAIC, Booz Allen, L3Harris) and DoD spectrum offices that are active buyers of adaptive RF technologies.
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
- March 24, 2026
- Status
- Granted patent
- Patent number
- 12585953
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.