Noise-Adjusted Principal Component Analysis for Buried Radioactive Target Detection and Classification
Noise-Adjusted Principal Component Analysis for Buried Radioactive Target Detection and Classification
复制标题
DOI：
10.1109/tns.2010.2084105
复制
发表时间：
2010-12
影响因子：
1.8
通讯作者：
Q. Du;Wei Wei-Wei;Daniel May;N. Younan
中科院分区：
文献类型：
--
作者：
Q. Du;Wei Wei-Wei;Daniel May;N. Younan
提出了一种基于噪声调整主成分分析（NAPCA）的方法，用于探测和分类埋在地下的放射性目标，传感器驻留时间短。实验中使用的数据是碘化钠（NAI）闪烁探测器收集的伽马光谱。光谱变换方法首先应用于数据，其次是NAPCA。然后对NAPCA变换后的特征子空间进行k近邻（kNN）聚类，实现检测或分类。使用240个光谱测量数据库对该方法进行评估，该数据库包括不同深度的背景（建筑砂）、良性物质测量（铀矿）和目标测量（贫化铀）。与其他广泛使用的贫铀算法相比，所提出的技术可以提供更好的性能。
We present a noise-adjusted principal component analysis (NAPCA)-based approach to the detection and classification of buried radioactive targets with short sensor dwell time. The data used in the experiments is the gamma spectroscopy collected by a Sodium Iodide (NAI) scintillation detector. Spectral transformation methods are first applied to the data, followed by NAPCA. Then k-nearest neighbor (kNN) clustering is applied to the NAPCA-transformed feature subspace to achieve detection or classification. This method is evaluated using a database of 240 spectral measurements consisting of background (construction sand), benign material measurements (uranium ore), and target measurements (depleted uranium) at various depths. Compared to other widely used algorithms for depleted uranium, the proposed technique can provide better performance.