24–28 Jun 2019
Europe/Vienna timezone

Machine Learning to Categorize Radionuclide Spectra

26 Jun 2019, 17:00
15m
Forum (Hofburg)

Forum

Hofburg

Oral Theme 3. Verification Technologies and Technique Application T3.5 Data Analysis Algorithms, Artificial Intelligence, Big Data and Deep Learning

Speaker

Tryggvi Edwald (CTBTO)

Description

The poster briefly describes work using one- and two-dimensional Convolutional Neural Networks (CNNs) to categorize radionuclide spectra. The aim of this work is to automatically recognize 'normal' spectra and thus possibly reduce the work of the human analysts, which would need to focus on the unusual spectra which are more difficult to categorize.

Primary author

Presentation materials

There are no materials yet.