基于太赫兹时域光谱技术的红木检测方法

提出了一种基于随机森林预测模型的太赫兹时域光谱的木材鉴别方法。对4种木材(2种红木、2种非红木)在0.2～1.2 THz频率范围的吸收光谱的差异进行分析；对得到的光谱吸光度数据进行主成分分析的数据降维处理,并提取方差贡献率最高的五种主成分(总贡献率高达99.65%)；将其代入随机森林预测模型预测鉴别红木的真伪，得出相应训练集和测试集的识别率。实验结果表明，与传统的支持向量机预测模型和单一决策树模型比较，使用时域光谱技术结合随机森林预测模型能够得到更高的识别率,识别率可达91.25%，能够准确对红木和非红木进行检测。

Abstract

A method to identify wood based on random forests prediction model of terahertz time-domain spectroscopy is proposed. We analyzed the differences of the absorption spectrum of four kinds of the woods (two kinds of real red wood and two kinds of false red wood) in the frequency range of 0.2～1.2 THz. Then the principal component analysis was applied to decrease the dimension of the spectral absorbance data, and the five principal components with top cumulative variance contribution rates were extracted (the total contribution rate is up to 99.65%). The processed spectral data were substituted into the random forest prediction model to identify real red wood and false red wood, and then the recognition rate of the training set and test set were obtained. The experimental results show that the terahertz time-domain spectroscopy combined with random forest prediction model can obtain a higher recognition rate, the recognition rate can reach 91.25%, when comparing with that using the traditional support vector machine prediction model and single decision tree model. The research results show that it is feasible to apply the terahertz time-domain spectroscopy combined with random forest prediction model into the identification of red wood.

参考文献

[1] 康胜武, 汪继平, 刘侃, 等. 太赫兹波光谱特性分析［J］. 光学学报, 2012, 32(6): 0612001.

Kang Shengwu, Wang Jiping, Liu Kan, et al. Analysis of the spectral characters of terahertz-wave［J］. Acta Optica Sinica,2012, 32(6): 0612001.

[2] Siegel P H. Terahertz technology in biology and medicine［C］. MTT-S International Microwave Symposium Digest, 2004: 1575-1578.

[3] Zhang X C. Terahertz wave imaging: horizons and hurdles［J］. Physics in Medicine and Biology, 2002, 47(21): 3667.

[4] 姚建铨, 迟楠, 杨鹏飞, 等. 太赫兹通信技术的研究与展望［J］. 中国激光, 2009, 36(9): 2213-2233.

Yao Jianquan, Chi Nan, Yang Pengfei, et al. Study and outlook of terahertz communication technology［J］. Chinese J Lasers, 2009, 36(9): 2213-2233.

[5] 孙雅茹, 史同璐, 刘建军, 等. 太赫兹超材料类EIT谐振无标记生物传感［J］. 光学学报, 2016, 36(3): 0328001.

Sun Yaru, Shi Tonglu, Liu Jianjun, et al. Terahertz label-free bio-sensing with EIT-like metamaterials［J］. Acta Optica Sinica, 2016, 36(3): 0328001.

[6] Ferguson B, Zhang X C. Materials for terahertz science and technology［J］. Nature Materials, 2002, 1(1): 26-33.

[7] Li N, Shen J L, Sun J H, et al. Study on the THz spectrum of methamphetamine［J］. Optics Express, 2005, 13(18): 6750-6755.

[8] Mickan S, Abbott D, Munch J, et al. Analysis of system trade-offs for terahertz imaging［J］. Microelectronics Journal, 2000, 31(7): 503-514.

[9] 沈京玲, 张存林. 太赫兹波无损检测新技术及其应用［J］. 无损检测, 2005, 27(3): 146-147.

Shen Jingling, Zhang Cunlin. Terahertz nondestructive imaging technology and its application［J］. Nondestructive Testing, 2005, 27(3): 146-147.

[10] 王露. 正确解析红木标准--访红木流通专业委员会秘书长车畅［J］. 中国市场, 2012 (34): 16-17.

[11] 王克奇, 杨少春, 戴天虹, 等. 基于均匀颜色空间的木材分类研究［J］. 计算机工程与设计, 2008, 29(7): 1780-1784.

Wang Keqi, Yang Shaochun, Dai Tianhong, et al. Research on wood classification using uniform color space［J］. Computer Engineering and Design, 2008, 29(7): 1780-1784.

[12] 李艳艳, 孙多永, 朱仲良, 等. 基于气相色谱-主成分分析的红木分类识别方法研究［J］. 计算机与应用化学, 2010, 27(2): 237-240.

Li Yanyan, Sun Duoyong, Zhu Zhongliang, et al. Study on the classification and recognition of mahogany based on gas chromatograph-principle component analysis［J］. Computers and Applied Chemistry, 2010, 27(2): 237-240.

[13] 李敏华, 刘红清, 李桂兰, 等. 红木家具与工艺品木材无损检测方法研究［J］. 家具与室内装饰, 2013(9): 96-98.

Li Minhua, Liu Hongqing, Li Guilan, et al. A study on wood non-destructive testing method of hongmu furniture and crafts［J］. Furniture & Interior Design, 2013(9): 96-98.

[14] 杨忠, 江泽慧, 吕斌. 红木的近红外光谱分析［J］. 光谱学和光谱分析, 2012, 32(9): 2045-2408.

Yang Zhong, Jiang Zehui, Lü bin. Investigation of near infrared spectroscopy of rosewood［J］. Spectroscopy and Spectral Analysis, 2012, 32(9): 2405-2408.

[15] 陈涛, 李智, 莫玮. 基于模糊模式识别的爆炸物THz光谱识别［J］. 仪器仪表学报, 2012, 33(11): 2480-2486.

Chen Tao, Li Zhi, Mo Wei. Identification of terahertz absorption spectra of explosives based on fuzzy pattern recognition［J］. Chinese Journal of Scientific Instrument, 2012, 33(11): 2480-2486.

[16] Liu X, Chen X, Wu W, et al. Process control based on principal component analysis for maize drying［J］. Food control, 2006, 17(11): 894-899.

[17] 陈扬, 张太宁, 郭澎, 等. 基于主成分分析的复杂光谱定量分析方法的研究［J］. 光学学报, 2009, 29(5): 1285-1291.

Chen Yang, Zhang Taining, Guo Peng, et al. Quantitative analysis for nonlinear fluoreseent spectra based on principal component analysis［J］. Acta Optica Sinica, 2009, 29(5):1285-1291.

[18] 吴一全, 周杨, 龙云淋. 基于自适应参数支持向量机的高光谱遥感图像小目标检测［J］. 光学学报, 2015, 35(9): 0928001.

Wu Yiquan, Zhou Yang, Long Yunlin. Small target detection in hyperspectral remote sensing image based on adaptive parameter SVM［J］. Acta Optica Sinica, 2015, 35(9): 0928001.

[19] Breiman L. Random forests［J］. Machine Learning, 2001, 45(1): 5-32.

[20] 蔡加欣, 冯国灿, 汤鑫, 等. 基于局部轮廓和随机森林的人体行为识别［J］. 光学学报, 2014, 34(10): 1015006.

Cai Jiaxin, Feng Guocan, Tang Xin, et al. Human action recognition based on local image contour and random forest［J］. Acta Optica Sinica, 2014, 34(10): 1015006.

[21] 涂闪, 张文涛, 熊显名, 等. 基于太赫兹时域光谱系统的转基因棉花种子主成分特性分析［J］. 光子学报, 2015, 44(4): 0430001.

Tu Shan, Zhang Wentao, Xiong Xianming, et al. Principal component analysis for transgenic cotton seeds based on terahertz time domain spectroscopy system［J］. Acta Photonica Sinica, 2015, 44(4): 0430001.

[22] Ryniec R, Zagrajek P, Paka N. Terahertz frequency domain spectroscopy identification system based on decision trees［J］. Acta Physica Polonica A, 2012, 122(5): 891-895.

[23] Alba E, García-Nieto J, Jourdan L, et al. Gene selection in cancer classification using PSO/SVM and GA/SVM hybrid algorithms［C］. IEEE Congress on Evolutionary Computation, 2007: 284-290.

张文涛, 王思远, 占平平, 韩莹莹. 基于太赫兹时域光谱技术的红木检测方法[J]. 光学学报, 2017, 37(2): 0230006. Zhang Wentao, Wang Siyuan, Zhan Pingping, Han Yingying. Method of Identifying Red Wood Based on Terahertz Time-Domain Spectroscopy[J]. Acta Optica Sinica, 2017, 37(2): 0230006.

基于太赫兹时域光谱技术的红木检测方法

关于本站 Cookie 的使用提示

全站搜索

基于太赫兹时域光谱技术的红木检测方法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索