Signal Processing for Layered Sensing

As a foundational component of a Layered Sensing architecture, Toyon proposes to develop a Multi-Modal Fusion Module (M2FM) capable ofconfirming detections from Chemical, Biological, and Radiological (CBR) sensing networks by fusing together information from other (non-CBR)sensors. In addition to confirming an initial CBR detection, M2FM will aid in characterizing the threat scenario by estimating key parameters forthe source, namely the location, size and timing of the threat release. The estimated source term will be an input to existing plume modelscapable of predicting the extent of the resulting hazard. All of these results will be provided to an operator as a Decision Aid for guiding theresponse. The M2FM will utilize Bayesian-based sensor fusion algorithms, which have been used on similar "evidence accrual"-type problems.The CBR application involves several unique features that will require adapting the theory and existing tools (e.g., Bayesian Belief Networks) toemphasize real-time accrual based on features related to the CBR threat, and to infer the underlying threat properties based on processedsensor outputs. The scope of Phase II involves developing a functional prototype for the software module capable of implementingalgorithms in existing operational Command and Control systems.