Machine learning for standoff detection of Special Nuclear Material (SNM)

Award Information
Agency: Department of Defense
Branch: Defense Threat Reduction Agency
Contract: HDTRA1-17-P-0021
Agency Tracking Number: T162-001-0109
Amount: $149,965.00
Phase: Phase I
Program: SBIR
Solicitation Topic Code: DTRA162-001
Solicitation Number: 2016.2
Timeline
Solicitation Year: 2016
Award Year: 2017
Award Start Date (Proposal Award Date): 2017-03-23
Award End Date (Contract End Date): 2017-10-29
Small Business Information
93 S JACKSON ST, SEATTLE, WA, 98104
DUNS: 079640621
HUBZone Owned: N
Woman Owned: N
Socially and Economically Disadvantaged: N
Principal Investigator
 Stanislav Shalunov
 CEO
 (415) 601-7021
 shalunov@shlang.com
Business Contact
 Stanislav Shalunov
Phone: (415) 601-7021
Email: shalunov@shlang.com
Research Institution
N/A
Abstract
"Deep Learning for standoff detection of Special Nuclear Material (DLeN) applies the same deep learning techniques that allow computers to beat human performance in image recognition and the game of Go to detecting Special Nuclear Material. Spectral analysis and signal processing can in some cases be augmented by the use of much larger neural nets that conduct much deeper analysis of features of the sensor data. This may enable the extraction of information indicating presence of SNM from a standoff distance and with a shorter amount of time. Training a deep neural net is very computationally intensive and requires specialized hardware. Execution is very computationally inexpensive and can easily happen in JVM even with very modest CPU and memory. Phase 1 of the project determines feasibility by training a deep neural net to analyze sensor data. The success metrics are the false negative and false positive rates."

* Information listed above is at the time of submission. *

US Flag An Official Website of the United States Government