The objective of this project is to demonstrate the feasibility of seamlessly inferring radio capabilities and creating situational awareness. The radios may belong to multiple different operators, have varying levels of spectrum sensing and access capabilities, as well as be manufactured by different vendors. The set of tasks that the radios may be assigned to perform may change over time, and may even involve unknown situations that are not known at the time of deployment. If it relied on predefined property-value pairs (like a database schema) or XML, then the introduction of a new device would require modifications to the code, recompilation, and possibly, re-certification of the software. Instead, we adopt an approach of using descriptions expressed in a language with formal, computer- processable semantics, like Web Ontology Language (OWL). Using a language with formal semantics guarantees that inference is sound and complete, and with OWL, tractable.

This is a joint project with Vistology and Northeastern University. Vistology is building the inference engine to perform the above mentioned tasks, while Northeastern is supporting the creation of the radio-parameter dataset that will be used to train the engine, its evaluation and implementation.

Personnel:
Yanji Chen
Rahman Doost