Noise-Adjusted Principal Component Analysis for Buried Radioactive Target Detection and Classification

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.