Context Aware Machine Learning Signal System
Vadum is further maturing the Context Aware Machine Learning Signal (CAMLS) classification system, an AI-enabled capability that improves signal identification and aggregates observations from distributed sensors to generate a unified picture of the radio frequency (RF) environment. During this Army SBIR Phase II Sequential award, CAMLS will be integrated with the Army’s Terrestrial Layer System (TLS) to enhance RF situational awareness and provide operators with a more complete understanding of spectrum activity across the battlespace.
Vadum will deliver CAMLS, a hardware agnostic RF signal detection and classification software suite, for distribution across all Army RF capable devices. CAMLS intelligently fuses heterogeneous local sensor data into a unified view of the RF spectrum and is planned for transition to Terrestrial Layer Systems, delivering a real-time actionable RF picture to guide tactical decisions.
Every RF-capable device can become a CAMLS sensor:
- Hardware abstraction layer built onto core CAMLS algorithms
- Provides a consistent and stable RF ecosystem regardless of software defined radio platform
CAMLS algorithms will scale/adapt to varied target hardware compute capabilities:
- Larger set of hardware devices that can provide local RF sensor data
Automated, real-time ID of spectral conditions and mission impact:
- Spatial-spectral-temporal space considerations
- Identifies available spectrum for dynamic spectrum access (DSA) radios
- Simple, interpretable, and accurate machine learning technique