Abstract
We develop a data-driven, regression-based scaling method to synthesize radiation counts for a given source strength in a spectral bin by bootstrapping measurements from Domestic Nuclear Detection Office's Intelligence Radiation Sensors Systems (IRSS) tests. In addition to counts, we also generate network messages using message-skeletons extracted from IRSS tests. We characterize the quality of generated counts using statistical mea- sures and distance metrics, and provide an analytical justification for our method based on the Vapnik-Chervonenkis theory.
| Original language | English |
|---|---|
| Title of host publication | 2017 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2017 - Conference Proceedings |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| ISBN (Electronic) | 9781538622827 |
| DOIs | |
| State | Published - Nov 12 2018 |
| Event | 2017 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2017 - Atlanta, United States Duration: Oct 21 2017 → Oct 28 2017 |
Publication series
| Name | 2017 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2017 - Conference Proceedings |
|---|
Conference
| Conference | 2017 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2017 |
|---|---|
| Country/Territory | United States |
| City | Atlanta |
| Period | 10/21/17 → 10/28/17 |
Funding
This work has been supported by the U.S. Department of Homeland Security, Domestic Nuclear Detection Office, under competitively awarded contract No. IAA HSHQDC-13-X-B0002. This support does not constitute an express or implied endorsement on the part of the Government.