Particle swarm optimization based spectral transformation for radioactive material detection and classification

摘要

We investigate buried depleted uranium detection and classification using data collected with short sensor dwell time (i.e., less than or equal to 1s). Under this circumstance, the gamma spectroscope collected by a NaI detector can be sparse and random, and may be severely affected by energy counts from the background. Several spectral transformations using binned energy windows can help alleviate the negative effect from background spectral noisy variation. The simplest way for such spectral partition is to use a fixed bin-width for uniform partition. In this paper, we propose a particle swarm optimization (PSO)-based optimization method to automatically determine the varied bin-width for each energy window. The experimental result shows that the spectral transformation methods using PSO-selected bins with variable widths can outperform those with a fixed bin-width.