Current time in Korea 23:22 Sep 22 (Tue) Year 2020 KCS KCS Publications
KCS Publications
My Journal  Log In  Register
HOME > Search > Browsing(BKCS) > Archives

Bulletin of the Korean Chemical Society (BKCS)

ISSN 0253-2964(Print)
ISSN 1229-5949(Online)
Volume 11, Number 5
BKCSDE 11(5)
May 20, 1990 

A Classification of Obsidian Artifacts by Applying Pattern Recognition to Trace Element Data
Chul Lee*, Myung-Zoo Czae, Seungwon Kim, Hyung Tae Kang, Jong Du Lee
Fifty eight obsidian artifacts and four obsidian source samples have been analyzed by instrumental neutron activation analysis. Artifact samples have been classified into classes by unsupervised learning techniques such as eigenvector projection and nonlinear mapping. The source samples have thereafter been connected to the classes by the supervised learning techniques such as SLDA and SIMCA so as to characterize each class by possible source sites. Some difference attributable to different nonlinear mapping techniques and the elemental effects on the separation between classes have been discussed.
450 - 455
Full Text