Dr. Smith holds a Ph.D. in Physics from the University of Central Florida and has been part of Physical Sciences Inc. (PSI) since 2015. At PSI, he has worked on various challenges, including standoff and proximal CBRNE sensing, distributed sensor networks, sensor fusion, and machine learning.
Dr. Smith was successful in applying state-of-the-art deep learning methods for spectral identification using Bruker’s Ion Mobility Spectrometer line (RAID-P/RAID-M), demonstrating improved sensitivity to a custom set of chemical targets and a significant reduction in operational false alarms. Dr. Smith’s work also encompasses several advanced algorithms for PSI’s CB-SIGMA network fusion capability, a real-time dispersion modeling and Bayesian estimation framework for distributed sensor fusion. Additionally, he has contributed to the development of custom convolutional neural networks for airborne chemical and biological threat detection in infrared imagery and elastic backscatter LIDAR returns.
