2017 Fiscal Year Final Research Report
Study of radiation measurements based on machine learning
| Project/Area Number |
15K16303
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Social systems engineering/Safety system
|
|---|
| Research Institution | National Research Institute of Police Science |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2015-04-01 – 2018-03-31
|
| Keywords | 放射線計測 / 核検知 / 核鑑識 / リスク評価 / 放射線損傷 / ガンマ線スペクトロスコピ |
|---|
| Outline of Final Research Achievements |
We propose two methods as means to counter radiological terrorist acts such as dirty-bomb or silent-source attacks. The first proposal concerns a nuclear detection system using the security cameras already installed in public spaces. Our method is based on counting the number of hot pixels, impacts on the device’s image sensor (CCD or CMOS) that produced constantly bright pixels.The proposed nuclear detection system using security cameras has been demonstrated to be effective in detecting radiation emanating from devices containing lead-shielded nuclear material and assessing criticality. The second proposal is to study a novel nuclear-identification method using prior probability (information), spectral shape, and peak energy. The method is usuful for in-situ measurements using gamma-ray detectors with low-energy resolution.
|
| Free Research Field |
放射線計測
|
