ECE professors receive ONR grant to study spectrum intelligence
Two professors from Purdue’s School of Electrical and Computer Engineering have received a $1.5-million, three-year grant from the Office of Naval Research (ONR). The project involving Christopher Brinton, assistant professor of ECE, and David J. Love, the Nick Trbovich Professor of ECE, is titled “Network-Aware Distributed Machine Learning and Sensor Fusion for Spectrum System Intelligence.” Brinton is the PI on the project, which also includes collaborators at the University of Kansas.
Given the growth of wireless devices worldwide, Brinton says there are standard congestion challenges everyone has to deal with in communication. He says these challenges become even more difficult to handle in the circumstance of a malicious attack, especially in a military context.
“When you’re trying to support communications between agents in different locations that are trying to coordinate to carry out a mission, effective communication amongst them is very important,” says Brinton. “Especially if you have an adversary who is trying to thwart your communications or ultimately take down your system.”
Brinton says this ONR grant will enable fundamental research in spectrum intelligence for contemporary communication networks to be able to detect adversarial threats in congested and contested environments, mitigate the threats, and potentially destroy them to prevent them from impacting any other systems being used.
Specifically, the approach will consist of research along the following three vectors:
- compressed and quantized spectrum information fusion via spatially distributed, heterogeneous wireless sensors (led by University of Kansas, Dr. Taejoon Kim (Kansas PI) and Dr. Morteza Hashemi (Kansas co-PI).)
- real-time, distributed understanding and classification of spectrum usage scenarios based on network-aware learning techniques (led by Purdue University, Prof. Brinton)
- rapid detection and adaptation to non-cooperative wireless links based on inferred spectrum usage behaviors (led by Purdue University, Prof. Love).
The program will enable new methodologies that are decentralized in nature, to avoid incurring the large overhead of data centralization, while enabling agile, dynamic spectrum intelligence.
If successful, the proposed research will lead to Naval systems, and more generally Department of Defense networks, that can use available spectrum to operate more efficiently in congested and contested wireless environments. Further, the integration of state-of-the-art machine learning techniques with spectrum sensing and sensor fusion could facilitate future spectrum sharing and operation in regions of the world without strong regulatory infrastructures.