Application of support vector machine to rapid classification of uranium waste drums using low-resolution γ-ray spectra. (October 2015)

• Record Type: Journal Article
• Authors: Hata, Haruhi; Yokoyama, Kaoru; Ishimori, Yuu; Ohara, Yoshiyuki; Tanaka, Yoshio; Sugitsue, Noritake
• Is Part Of: Applied radiation and isotopes. Volume 104(2015:Oct.)
• Page Start: 143
• Page End: 146
• Publication Date: 2015-10
• Subjects: γ-Ray spectra -- Uranium waste -- Support vector machine -- Uranium waste management; Radiology -- Periodicals; Radiation -- Industrial applications -- Periodicals; Nuclear chemistry -- Periodicals; Internet resource; Periodical; 660.298
• DOI: 10.1016/j.apradiso.2015.06.030
• Languages: English
• ISSNs: 0969-8043

Abstract

Abstract: We investigated the feasibility of using support vector machine (SVM), a computer learning method, to classify uranium waste drums as natural uranium or reprocessed uranium based on their origins. The method was trained using 12 training datasets were used and tested on 955 datasets of γ -ray spectra obtained with NaI(Tl) scintillation detectors. The results showed that only 4 out of 955 test datasets were different from the original labels—one of them was mislabeled and the other three were misclassified by SVM. These findings suggest that SVM is an effective method to classify a large quantity of data within a short period of time. Consequently, SVM is a feasible method for supporting the scaling factor method and as a supplemental tool to check original labels. Highlights: A support vector machine was applied for the rapid classification of γ -ray spectra from 955 uranium waste drums. Waste drums were classified as either containing natural uranium or reprocessed uranium. Only four drums were found to be different from their original labels.