Application of LVQ clustering algorithm to identification of explosive by THz spectroscopy

doi:10.3778/j.issn.1002-8331.2009.18.072

Computer Engineering and Applications ›› 2009, Vol. 45 ›› Issue (18): 239-241.DOI: 10.3778/j.issn.1002-8331.2009.18.072

• 工程与应用 • Previous Articles Next Articles

Application of LVQ clustering algorithm to identification of explosive by THz spectroscopy

ZHAO Jing-jing¹,GE Qing-ping¹,ZHANG Cun-lin²

1.College of Information Engineering，Capital Normal University，Beijing 100037，China
2.Department of Physics，Capital Normal University，Beijing 100037，China

Received:2008-04-22 Revised:2008-07-11 Online:2009-06-21 Published:2009-06-21
Contact: ZHAO Jing-jing

LVQ聚类算法在爆炸物THz光谱识别中的应用

赵晶晶¹,葛庆平¹,张存林²

1.首都师范大学信息工程学院，北京 100037
2.首都师范大学物理系，北京 100037

通讯作者: 赵晶晶

Abstract

Abstract: The terahertz（THz） technologies is one research hotspot in the domain of detecting explosive.Because the result gotten by clustered with original frequency-domain pattern is not satisfactory.This paper introduces second derivative curve that transformed from frequency-domain THz spectrum.Based on LVQ clustering algorithm and the new characteristic curve，an automatic detection system is designed and finished by VC++6.0.Appling LVQ to identification of explosive by THz spectroscopy.Experiment to the four kinds of explosive：RDX，DNT，TNT and HMX，trained with original frequency-domain pattern，the correct rate is 96%.After computing effective feature from transformed data，input to the same network，the correct rate up to 100%.The result shows that the system based on LVQ can be very capable of similar character clustering and has higher rate of identification.

Key words: The terahertz（THz）, neural network, Learning Vector Quantization（LVQ） clustering algorithm

摘要： 运用THz光谱特性进行爆炸物的识别，是现代检测技术研究的一个热点。由于直接对原始数据进行聚类的识别率并不理想，首先对实验样本的THz频域光谱数据曲线进行二阶导数变换，得到了更能表现数据变化趋势和峰值的特征曲线，然后基于该特征曲线利用LVQ神经网络聚类算法，设计并用VC++6.0实现了THz光谱自动分类识别系统。分别对RDX、DNT、TNT、HMX四种爆炸物进行识别对比实验，运用原始数据训练出的分类器，识别率为96％，运用变换过后的特征数据训练出的LVQ分类器，识别率可以达到100％。实验证明，所设计的基于LVQ的神经网络分类器具有强大相似特征聚类功能和较高的识别率。

关键词: THz技术, 神经网络, 学习矢量化网络（LVQ）聚类算法

ZHAO Jing-jing¹,GE Qing-ping¹,ZHANG Cun-lin². Application of LVQ clustering algorithm to identification of explosive by THz spectroscopy[J]. Computer Engineering and Applications, 2009, 45(18): 239-241.

赵晶晶¹,葛庆平¹,张存林². LVQ聚类算法在爆炸物THz光谱识别中的应用[J]. 计算机工程与应用, 2009, 45(18): 239-241.

[1]	XU Hao, ZHANG Kai, TIAN Yingjie, CHONG Faguang, WANG Zichao. Review of Deep Neural Network-Based Image Caption [J]. Computer Engineering and Applications, 2021, 57(9): 9-22.
[2]	RAN Rong, XU Xinghua, QIU Shaohua, CUI Xiaopeng, OUYANG Bin. Review of Crack Detection Methods Based on Deep Convolutional Neural Networks [J]. Computer Engineering and Applications, 2021, 57(9): 23-35.
[3]	MOU Qingping, ZHANG Ying, ZHANG Dongbo, WANG Xinjie, YANG Zhiqiao. Research on Visual Tracking Algorithm and Application of Target Loss Discrimination Mechanism [J]. Computer Engineering and Applications, 2021, 57(9): 140-147.
[4]	BAO Zhiqiang, XING Yu, LYU Shaoqing, HUANG Qiongdan. Improved YOLO V2 6D Object Pose Estimation Algorithm [J]. Computer Engineering and Applications, 2021, 57(9): 148-153.
[5]	WANG Lin, CHAI Jiangyun. Research on Deep Neural Network in Multi-scene Vehicle Attribute Recognition [J]. Computer Engineering and Applications, 2021, 57(9): 162-167.
[6]	HUANG Dongyi, YANG Bing, WU Zihao, KUANG Jiayi, YAN Zeming. Spatio-Temporal Fully Connected Convolutional Neural Networks for Citywide Cellular Prediction [J]. Computer Engineering and Applications, 2021, 57(9): 168-175.
[7]	ZHAO Zhiyan, YANG Hua, HU Zhiwei, YU Haiping. Identification Model of Pests on Yuluxiang Pear Leaves Based on TACNN [J]. Computer Engineering and Applications, 2021, 57(9): 176-181.
[8]	ZHOU Lungang, SUN Yifeng, WANG Kun, WU Jiang, HUANG Weigui, LI Binglong. End to End Object Recognition Algorithm for Multi-attributes of Multi-values [J]. Computer Engineering and Applications, 2021, 57(9): 182-190.
[9]	ZHANG Cheng, DAI Junfeng, XIONG Wenxin. Improved Handwritten Date Recognition in Scanned Documents Combined with LeNet-5 [J]. Computer Engineering and Applications, 2021, 57(9): 207-211.
[10]	MA Zhexu, YANG Feng, QIAO Xu. Intelligent Detection Method of Railway Subgrade Defect [J]. Computer Engineering and Applications, 2021, 57(9): 272-278.
[11]	JIANG Bin, ZHONG Rui, ZHANG Qiuwen, ZHANG Huanlong. Survey of Non-frontal Facial Expression Recognition by Using Deep Learning Methods [J]. Computer Engineering and Applications, 2021, 57(8): 48-61.
[12]	LI Zhenxiao, SUN Wei, LIU Mingming, ZHENG Lili, CHEN Shaoying. Research on Vehicle Detection and Tracking Algorithms in Traffic Monitoring Scenes [J]. Computer Engineering and Applications, 2021, 57(8): 103-111.
[13]	ZHANG Yue, HUANG Yourui, LIU Pengkun. Research on Multi-resolution Human Pose Estimation with Attention Mechanism [J]. Computer Engineering and Applications, 2021, 57(8): 126-132.
[14]	ZHAI Zhengli, LI Penghui, FENG Shu. Research Overview of Adversarial Attacks on Graphs [J]. Computer Engineering and Applications, 2021, 57(7): 14-21.
[15]	ZHU Juntao, YAO Guangle, ZHANG Gexiang, LI Jun, YANG Qiang, WANG Sheng, YE Shaoze. Survey of Few Shot Learning of Deep Neural Network [J]. Computer Engineering and Applications, 2021, 57(7): 22-33.

Application of LVQ clustering algorithm to identification of explosive by THz spectroscopy

LVQ聚类算法在爆炸物THz光谱识别中的应用

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics