MACHINE-LEARNING ALGORITHM FOR SHIELDED SPECIAL NUCLEAR MATERIALS DETECTION

doi:10.12943/cnr.2018.00004

MACHINE-LEARNING ALGORITHM FOR SHIELDED SPECIAL NUCLEAR MATERIALS DETECTION

2019-12-01

0

OA

AI

DOI：10.12943/cnr.2018.00004

原文链接

原文求助

摘要

En 中文

A machine-learning algorithm has been implemented by use of a neural network as a preliminary study on the applicability of this method to special nuclear materials detection. The algorithm predicts the presence of the 238U isotope when learning from a gamma spectrum data measured with a high-purity germanium detector from a sample of depleted uranium. In this work, both a fully connected neural network and a convolutional neural network have been implemented, and the performance of different configurations of the network has been studied. The use of convolutional network showed better performance over the fully connected network, with cost function and success rate values supporting a better prediction while avoiding overfitting. Furthermore, implemented network features such as filtering, max-pooling, dropout regularization, and momentum optimization also showed improved prediction performance.

MACHINE-LEARNING ALGORITHM FOR SHIELDED SPECIAL NUCLEAR MATERIALS DETECTION

摘要

期刊

机构

引用论文