None

;

JNC TN6700 2001-001, 96 Pages, 2001/08

JNC-TN6700-2001-001.pdf:1.63MB

no abstracts in English

None

; ; Ohara, Yoshiyuki;

PNC TN6700 98-004, 23 Pages, 1998/01

PNC-TN6700-98-004.pdf:0.56MB

None

None

;

PNC TN6700 95-008, , 1995/01

PNC-TN6700-95-008.pdf:0.25MB

no abstracts in English

None

;

PNC TN6700 95-006, , 1995/01

PNC-TN6700-95-006.pdf:1.34MB

no abstracts in English

None

;

PNC TN6700 95-004, , 1995/01

PNC-TN6700-95-004.pdf:0.33MB

no abstracts in English

None

;

PNC TN6700 95-002, , 1995/01

PNC-TN6700-95-002.pdf:0.37MB

no abstracts in English

Classification of radioactive waste drums using -ray spectra

Uechi, Yasufumi; Tanaka, Yoshio; Hata, Haruhi*; Yokoyama, Kaoru*

no journal, , 

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 and tested on 955 datasets of -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 as a supplemental tool to check original labels.