Abstract
Objective: In order to accurately and quickly discriminate cigarettes. Methods: After collecting the near-infrared spectra of different brands and reducing the interference factors through the spectral preprocessing method, the spectral pretreatment method, the population number of firefly algorithm (FA) and the number of iterations on the correct rate of cigarette classification were investigated by using firefly algorithm to optimize support vector machine (SVM) parameters. Results: The standard normal variable transformation (SNV) combined with the first derivative method (1D) was used for near-infrared spectroscopy preprocessing. Under the condition that the number of firefly populations was 20 and the number of iterations was 20, optimized support vector parameters could achieve better recognition. As a result, the classification accuracy rate of the training set was 100%, and the classification accuracy rate of the test set was between 96.67% and 100.00%. Conclusion: It shows that using near-infrared spectroscopy technology combined with FA algorithm to optimize SVM can achieve accurate identification of cigarette brands.
Publication Date
10-16-2022
First Page
85
Last Page
90
DOI
10.13652/j.spjx.1003.5788.2022.90018
Recommended Citation
Xi, Pan; Ran, Li; Min, Wei; Qing, Wei; and Chang-gui, Qiu
(2022)
"Discrimination of cigarette based on near-infrared spectroscopy technology and firefly algorithm optimized support vector machine parameters,"
Food and Machinery: Vol. 38:
Iss.
7, Article 14.
DOI: 10.13652/j.spjx.1003.5788.2022.90018
Available at:
https://www.ifoodmm.cn/journal/vol38/iss7/14
References
[1] 陆龙建,陈磊,余苓,等.多元因子分析在卷烟风格特征剖析中的应用[J].烟草科技,2012（10）:36-40.LU Long-jian,CHEN Lei,YU Ling,et al.Application of multiple factor analysis（MFA）in cigarettes style character analyzing[J].Tobacco Science & Technology,2012（10）:36-40.
[2] 许永,张霞,刘巍,等.国内外卷烟样品主流烟气中氢氰酸释放量的差异[J].烟草科技,2011（10）:58-60.XU Yong,ZHANG Xia,LIU Wei,et al.Differential analysis of hydrogen cyanide delivery in mainstream smoke of different domestic and imported cigarettes[J].Tobacco Science & Technology,2011（10）:58-60.
[3] 文建辉,钟科军,杜文,等.离散粒子群优化算法和主成分投影分析在卷烟烟气色谱指纹分析中的应用[J].烟草科技,2011（12）:43-46.WEN Jian-hui,ZHONG Ke-jun,DU Wen,et al.Application of optimization algorithm for discrete particle swarm and principal component projection analysis in chromatographic fingerprint analysis of cigarette smoke[J].Tobacco Science & Technology,2011（12）:43-46.
[4] 李庆华,王玉,余振华,等.卷烟烟丝化学指标的逐步判别分析[J].中国烟草学报,2009,15（6）:27-30.LI Qing-hua,WANG Yu,YU Zhen-hua,et al.Stepwise discriminatory analysis of chemical components in cut tobacco[J].Acta Tabacaria Sinica,2009,15（6）:27-30.
[5] 郭华诚,张月华,李阳光,等.烟丝挥发性香味物质与卷烟感官质量的相关性研究[J].食品与机械,2019,35（1）:209-212.GUO Hua-cheng,ZHANG Yue-hua,LI Yang-guang,et al.Study on the correlation between volatile aroma substances and sensory quality of cigarettes[J].Food & Machinery,2019,35（1）:209-212.
[6] 吴海云,束茹欣,陈德莉,等.基于近红外光谱的卷烟质量投影模型[J].中国烟草学报,2015（1）:18-21.WU Hai-yun,SHU Ru-xin,CHEN De-li,et al.NIR spectra-based projection model of cigarette quality[J].Acta Tabacaria Sinica,2015（1）:18-21.
[7] 李庆华,陈国辉,段姚俊,等.基于PCA-MD分类法的云烟系列卷烟风格表征及品质维护[J].烟草科技,2009（4）:5-8.LI Qing-hua,CHEN Guo-hui,DUAN Yao-jun,et al.Application of PCA-MD modeling in cigarette style characterizing and quality maintenance of yunyan brand series[J].Tobacco Science & Technology,2009（4）:5-8.
[8] 王小梅,焦龙,刘小丽,等.近红外漫反射光谱法定量分析川芎中的阿魏酸含量[J].药物分析杂志,2011,31（6）:1 016-1 019.WANG Xiao-mei,JIAO Long,LIU Xiao-li,et al.Quantitative ananlysis of ferulic acid in Ligusticum chuanxiong Hort by near infrared diffuse reflectance spectroscopy[J].Chinese Journal of Pharmaceutical Analysis,2011,31（6）:1 016-1 019.
[9] 褚小立,史云颖,陈瀑,等.近五年我国近红外光谱分析技术研究与应用进展[J].分析测试学报,2019,38（5）:603-611.CHU Xiao-li,SHI Yun-ying,CHEN Pu,et al.Research and application progresses of near infrared spectroscopy analytical technique in china in past five years[J].Journal of Instrumental Analysis,2019,38（5）:603-611.
[10] 王家俊.FT-NIR光谱分析技术测定烟草中总氮、总糖和烟碱[J].光谱实验室,2003,20（2）:181-185.WANG Jia-jun.Determination of total-nitrogen,total-sugar and nicotine in tobacco by FT-NIR spectrometry[J].Chinese Journal of Spectroscopy Laboratory,2003,20（2）:181-185.
[11] 冷红琼,郭亚东,刘巍,等.FT-NIR光谱法测定烟草中绿原酸、芸香苷、莨菪亭及总多酚含量[J].光谱学与光谱分析,2013,33（7）:1 801-1 804.LENG Hong-qiong,GUO Ya-dong,LIU Wei,et al.Determination of chlorogenic acid,rutin,scopoletin and total polyphenol in tobacco by fourier transform near infrared spectroscopy[J].Spectroscopy and Spectral Analysis,2013,33（7）:1 801-1 804.
[12] 宋怡,刘巍,段焰青,等.近红外光谱法快速测定烟草中的植物色素[J].中国烟草学报,2009,15（2）:15-18.SHONG Yi,LIU Wei,DUAN Yan-qing,et al.Rapid determination of pigments in tobacco with near infrared spectroscopy[J].Acta Tabacaria Sinica,2009,15（2）:15-18.
[13] 蒋锦锋,赵明月.近红外光谱法快速测定烟草中的总挥发酸与总挥发碱[J].烟草科技,2006（3）:33-37.JIANG Jin-feng,ZHAO Ming-yue.Rapid determination of total volatileacid and base in tobacco with NIR spectroscopy[J].Tobacco Science & Technology,2006（3）:33-37.
[14] 曹均阔,叶水生,丁香乾.模糊Kohonen网络在烟叶分类中的应用[J].计算机工程,2005,31（2）:222-224.CAO Jun-kuo,YE Shui-sheng,DING Xiang-qian.Application of fuzzy kohonen network in tobacco clustering[J].Computer Engineering,2005,31（2）:222-224.
[15] 刘晓萍,李斌,于川芳,等.基于近红外光谱的卷烟配方结构识别[J].烟草科技,2006（10）:16-18,27.LIU Xiao-ping,LI Bin,YU Chuan-fang,et al.Recognition of cigarette blend make-up based on NIR spectrum[J].Tobacco Science & Technology,2006（10）:16-18,27.
[16] 李伟,冯洪涛,周桂圆,等.Hotelling T2结合多组分NIR校正模型在卷烟生产过程质量监测中的应用[J].烟草科技,2014（7）:5-9.LI Wei,FENG Hong-tao,ZHOU Gui-yuang,et al.Quality monitoring in cigarette manufacturing process by combining Hotelling T2 statistics and multicomponent NIR calibration model[J].Tobacco Science & Technology,2014（7）:5-9.
[17] 赵科文,陈实,蒋浩,等.基于近红外光谱技术的烟丝掺配均匀度测定[J].食品与机械,2020,36（11）:183-188.ZHAO Ke-wen,CHEN Shi,JIANG Hao,et al.Determination of blending uniformity of cut tobacco based on near infrared spectroscopy[J].Food & Machinery,2020,36（11）:183-188.
[18] 李瑞丽,刘玉叶,李文伟,等.利用近红外光谱技术快速检测配方烟丝掺配均匀性[J].食品与机械,2019,35（5）:83-87.LI Rui-li,LIU Yu-ye,LI Wen-wei,et al.Study on rapid determination of tobacco blending uniformity by Near Infrared Spectroscopy[J].Food & Machinery,2019,35（5）:83-87.
[19] 唐雪梅,张薇,李慧.卷烟真伪鉴别的近红外定性分析方法[J].烟草科技,2008（11）:5-8.TANG Xue-fei,ZHANG Wei,LI Hui.Application of near-infrared reflectance spectroscopy in discriminating counterfeit cigarettes from genuine[J].Tobacco Science & Technology,2008（11）:5-8.
[20] YANG S Y,HOU Y,YANG L C,et al.Automatic identification of cigarette brand using near-infrared spectroscopy and sparse representation classificationalgorithm[J].Journal of the Brazilian Chemical Society,2018,29（7）:1 480-1 486.
[21] 谢有超,彭黔荣,杨敏,等.基于烟丝近红外光谱的卷烟品牌识别方法[J].烟草科技,2021,54（3）:72-77.XIE You-chao,PENG Qian-rong,YANG Min,et al.Cigarette brand recognition based on NIR spectral data of cut filler[J].Tobacco Science & Technology,2021,54（3）:72-77.
[22] 曹妙玲.基于卷烟常规化学检测数据及近红外信息的卷烟牌号识别[D].上海:华东理工大学,2012:36-41.CAO Miao-ling.Discrimination of cigarettes brands based on their routine testing chemical indicators and near infrared spectra[D].Shanghai:East China University of Science and Technology,2012:36-41.
[23] VAPNIK Vladimir.The Nature of statistical learning theory[M].Berlin:Springer,1995:133-161.
[24] VAPNIk Vladimir.An overview of statistical learning theory[J].IEEE Transactions on Neural Networks,1999,10（5）:988-999.
[25] 杨志民,刘广利.不确定性支持向量机:算法及应用[M].北京:科学出版社,2012:74-84.YANG Zhi-min,LIU Guang-li.Uncertainty support vector machines:Algorithms and applications[M].Beijing:Science Press,2012:74-84.
[26] YANG Xin-she.Nature-inspired algorithms and applied optimization[M].Gewerbestrasse:Springer International Publishing AG,2018:288-308.
[27] FISTER Iztok,FISTER IztokJr,YANG Xin-she,et al.A comprehensive review of firefly algorithms[J].Swarm and Evolutionary Computation,2013（13）:34-46.