Identification of illicit drugs by using SOM neural networks

被引：29

作者：

Liang, Meiyan ^{[1
]}

Shen, Jingling ^{[1
]}

Wang, Guangqin ^{[1
]}

机构：

[1] Capital Normal Univ, Dept Phys, Beijing Key Lab Terahertz Spect & Imaging, Key Lab Terahertz Optoelect,Minist Educ, Beijing 100037, Peoples R China

来源：

JOURNAL OF PHYSICS D-APPLIED PHYSICS | 2008年 / 41卷 / 13期

关键词：

D O I：

10.1088/0022-3727/41/13/135306

中图分类号：

O59 [应用物理学];

学科分类号：

摘要：

Absorption spectra of six illicit drugs were measured by using the terahertz time-domain spectroscopy technique in the range 0.2-2.6 THz and then clustered with self-organization feature map (SOM) artificial neural network. After the network training process, the spectra collected at another time were identified successfully by the well-trained SOM network. An effective distance was introduced as a quantitative criterion to decide which cluster the new spectra were affiliated with.

引用

页数：12

共 18 条

[1]

[Anonymous], 2006, MAT SURF PROCESS DIR

[2]

Born M., 1997, PRINCIPLES OPTICS

[3]

COWAN RS, 2001, MODERN TRIBOLOGY HDB, P1611

[4] THE INFLUENCE OF PREPARATION CONDITIONS ON THE OPTICAL-PROPERTIES OF TITANIUM NITRIDE BASED SOLAR CONTROL FILMS [J].