Share Email Print

Proceedings Paper

Preliminary research on organics recognition by x-ray absorption spectroscopy detection and classification
Author(s): Qian Wang; Xiaomei Wu; Wei Zhang; Shuting He; Haifeng Feng; Zheng Fang
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

X-ray Absorption Spectroscopy (XAS) was been applied for the material recognition in this paper. Twelve kinds of plastics were selected as specimens. Each specimen was tested for 100 times by different operators for data processing. Seventy sets of spectral data of each specimen were randomly selected as training set and the other 30 sets were selected as testing set. Training set was calculated with Principal Component Analysis (PCA) to get the first four Principal Components, which totally explain 99% of the original spectrum. The first four Principal Components were built plastic classification model respectively through K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) methods. The classification accuracy reached 89.22%-98.17%. Experimental results demonstrate that organics could be recognized by XAS. It shows that the X-ray absorption spectroscopy contains the potential of other organics recognition or even organisms.

Paper Details

Date Published: 5 January 2017
PDF: 7 pages
Proc. SPIE 10244, International Conference on Optoelectronics and Microelectronics Technology and Application, 102440L (5 January 2017); doi: 10.1117/12.2261804
Show Author Affiliations
Qian Wang, Xiamen Univ. (China)
Xiaomei Wu, Xiamen Univ. (China)
Wei Zhang, Xiamen Univ. (China)
Shuting He, Xiamen Univ. (China)
Haifeng Feng, Xiamen Univ. (China)
Zheng Fang, Xiamen Univ. (China)

Published in SPIE Proceedings Vol. 10244:
International Conference on Optoelectronics and Microelectronics Technology and Application
Shaohua Yu; Jose Capmany; Yi Luo; Yikai Su; Songlin Zhuang; Yue Hao; Akihiko Yoshikawa; Chongjin Xie; Yoshiaki Nakano, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?