Optimized Spectral Transformation for Detection and Classification of Buried Radioactive Waste - 11310

We investigate detection and classification of buried radioactive materials of interest using data collected by a Sodium Iodide (NaI) detector with short sensor dwell time (i.e., less than or equal to 1s). The objective of detection is to detect a target from background or non-target materials, while the objective of classification is to classify targets buried at different depths. Three spectral transforms using binned energy windows can help alleviate the negative impact from background and suppress trivial spectral variation. However, their performance is sensitive to bin partition parameters including the number of bins and their bin-widths. We have developed a particle swarm optimization (PSO)based automatic algorithm to determine these parameters. In this paper, we propose to apply multi-objective PSO to optimize both the detection and classification accuracy simultaneously. The experimental results demonstrate that the multi-objective PSO can achieve the balance between these two objectives, and it may provide even better individual performance than a single-objective PSO.