One-dimensional Convolution Neural Network for Improved Training Time and Standardization in Spectral Class
Physical Sciences Inc. (PSI) has been awarded a contract from the U.S. Department of Homeland Security Science and Technology Directorate to participate in Phase II of the DHS Small Business Innovation Research Program. PSI will develop a deep-learning based classification algorithm for detection and classification of trace explosives, opioids and narcotics on surfaces for optical spectroscopic systems.
PSI’s sensor-customizable algorithm will be trained using a module consisting of a standard desktop CPU and GPU for accelerated training times. The algorithm will be deployable on a smaller, hardened operational module containing a single-board computer with low SWAP that can be integrated with a spectrometer system. The algorithm uses a one-dimensional convolutional neural network architecture (1D-CNN) that is trained using synthetic data produced by a data injector model to negate the need for a large data collection effort.
During this program, PSI will extend the algorithms capabilities from infrared (IR) reflectance spectroscopy to include Raman spectroscopy. Feasibility of the algorithm was established in a previous program though demonstrations of training models using synthetic IR data produced by the injector, and achieving classification accuracies >90% against evaluation data sets comprised of real spectra and synthetic spectra.
For more information, contact:
Dr. Jay Giblin
Group Leader, Exploitation Technologies
Physical Sciences Inc.
Telephone: (978) 689-0003