1.陕西科技大学 电子信息与人工智能学院,陕西 西安 710021
2.广东药科大学 中医药研究院,广东 广州 510006
3.暨南大学 光电工程系,广东 广州 510632
4.上海交通大学 药学院,上海 200240
5.山东中医药大学 药物研究院,山东 济南 250355
郭拓,硕士生导师,讲师,研究方向:机器学习与过程分析技术研究,E-mail:guotuonwpu@126.com
肖雪,硕士生导师,副研究员,研究方向:中药分析与质量评价研究,E-mail:erxiaohappy@163.com
扫 描 看 全 文
梁小娟,王娅妮,马晋芳等.基于稀疏主成分分析特征选择算法的山楂叶产地判别模型研究[J].分析测试学报,2023,42(03):307-314.
LIANG Xiao-juan,WANG Ya-ni,MA Jin-fang,et al.Origin Discrimination Model of Crataegi Folium Based on Sparse Principal Component Analysis for Feature Selection[J].Journal of Instrumental Analysis,2023,42(03):307-314.
梁小娟,王娅妮,马晋芳等.基于稀疏主成分分析特征选择算法的山楂叶产地判别模型研究[J].分析测试学报,2023,42(03):307-314. DOI: 10.19969/j.fxcsxb.22102901.
LIANG Xiao-juan,WANG Ya-ni,MA Jin-fang,et al.Origin Discrimination Model of Crataegi Folium Based on Sparse Principal Component Analysis for Feature Selection[J].Journal of Instrumental Analysis,2023,42(03):307-314. DOI: 10.19969/j.fxcsxb.22102901.
为实现山楂叶产地的快速判别,提出一种基于稀疏主成分分析特征选择(SPCAFS)与支持向量机(SVM)建模的定性分析方法。采用近红外积分球漫反射光谱法采集6个产地共41批山楂叶123份样品的近红外光谱图,经数据预处理后,通过SPCAFS对代表性特征波段进行选择,并采用SVM建立山楂叶近红外产地判别模型。模型与连续投影(SPA),正则化自表示(RSR)和稀疏子空间聚类(SSC)3种特征选择算法进行对比,以准确率、精确度和灵敏度作为评价标准,评估所提模型的预测性能。结果显示,SPCAFS的特征波段数相比于全波长建模从1 500减少到21,预测结果的准确率和精确度分别从78%、76%提升至97%、100%。同时,相比于SPA、RSR、SSC算法,准确率分别提升了6%、3%、3%,精确度分别提升了13%、10%、5%,模型的预测能力得到显著提升,基于SPCAFS的SVM判别模型可实现山楂叶南北产地的快速判别。
A qualitative analysis method based on sparse principal component analysis feature selection(SPCAFS) and support vector machine(SVM) modeling was proposed in this paper,in order to realize the rapid discrimination on the origin of Crataegi Folium. Near infrared integrative sphere diffuse reflection spectroscopy was used to collect the near-infrared spectrograms of 123 Crataegi Folium samples from 6 regions in 41 batches. After data preprocessing,the representative characteristic bands were selected by SPCAFS,and the near infrared origin discrimination model for Crataegi Folium was established by SVM. The model was compared with three feature selection algorithms,i.e. continuous projection algorithm(SPA),regularized self representation algorithm(RSR) and sparse subspace clustering(SSC),to evaluate the prediction performance of the proposed model with accuracy,precision and sensitivity as evaluation criteria. The results showed that the numbers of characteristic band for SPCAFS were reduced from 1 500 to 21 compared with those for full wavelength modeling,but the accuracy and precision of prediction results were improved from 78% and 76% to 97% and 100%,respectively. Meanwhile,compared with those of SPA,RSR and SSC algorithms,the accuracy was improved by 6%,3% and 3%,while the precision was improved by 13%,10% and 5%,respectively. The prediction ability of the model was significantly improved. The SVM discrimination model based on SPCAFS could realize the rapid discrimination on the northern and southern geographic origins of Crataegi Folium.
近红外光谱特征选择山楂叶产地判别稀疏主成分分析特征选择算法支持向量机
near infrared spectroscopyfeature selectionCrataegi Foliumgeographic origin discriminationsparse principal component analysis for feature selectionsupport vector machines
Qi C,Zhong Z,Harrison F,Moses S S C.J. Clin. Pharmacol.,2002,42(6):605-612.
Yu J Q,Zhang K,Liu P,Xu M D,Xu Y N,Yang Q,Zhang N.Chin. J. New Drugs (俞洁琼,张锴,留萍,徐蒙蝶,徐英楠,杨群,张娜. 中国新药杂志),2016,25(15):1758-1764.
Li Y R,Zhou W W,Wang Z Y,Zhao S N,Pan H F.Chin. Pharm. J. (李艳荣,周维维,王子怡,赵胜男,潘海峰.中国药学杂志),2020,55(20):1673-1679.
Huang B C.Guihaia(黄燮才.广西植物),1989,(4):303-310.
Gao J,Wang L D,Li Y R,Pan H F.Anhui Med. Pharm. J. (高婧,王领弟,李艳荣,潘海峰.安徽医药),2018,22(1):38-42.
Xu B X,Yang M Y,Du Y L,Zhao S N,Li Y R,Pan H F.Rev. Bras. Farmacogn.,2018,28 (3):369-373.
Liu X P,Qin Y H,Zhang F M,Jiang W,Yin Z J.J. Instrum. Anal. (刘鑫鹏,秦玉华,张凤梅,蒋薇,尹志豇.分析测试学报),2022,41(11):1621-1628.
Mudge E M,Liu Y,Lund J A,Brown P N.Planta Med.,2016,82(17):1487-1492.
Zhu S R,Yan H Y,Niu K,Zhang S X.J. Chromatogr. Sci.,2015,53(6):909-914.
Yan Y L,Chen B,Zhu D Z.Principles,Technology and Application of NIR Spectral Analysis.Beijing:China Light Industry Press(严衍禄,陈斌,朱大洲.近红外光谱分析的原理、技术与应用.北京:中国轻工业出版社),2013:24-28.
Lu H X,Zhang J,Li L Q,Liu Z B,Yang H H,Feng Y C,Yin L H.Spectrosc. Spectral Anal. 路皓翔,张静,李灵巧,刘振丙,杨辉华,冯艳春,尹利辉.光谱学与光谱分析),2021,41(6):1782-1788.
Dai S Y,Ma Q Q,Jiang S H,Liu J,Guo L N,Qiao F,Zhou J,Qiao Y J,Zheng J,Ma S S.J. Instrum. Anal. 戴胜云,马青青,蒋双慧,刘杰,过立农,乔菲,周娟,乔延江,郑健,马双成.分析测试学报),2021,40(1):57-64.
Pontes M J C,Galvao R K H,Araújo M C U,Moreira P N T,Neto O D P,Jose G E,Saldanha T C B.Chemometr. Intell. Lab. Syst.,2005,78(1/2):11-18.
Zhang R Q,Zhang F Y,Chen W C,Yao H M,Ge J,Wu S C,Wu T,Du Y P.Chemometr. Intell. Lab. Syst.,2018,17547-17554.
Hu X N,Peng Y F,Luo H P,Luo X N,Zhan Y,Dai X J.Food Ind. (胡晓男,彭云发,罗华平,罗雪宁,詹映,代希君.食品工业),2015,36(5):232-235.
Nørgaard L,Saudland A,Wagner J,Nielsen J P,Munck L,Engelsen S B.Appl. Spectrosc.,2000,54(3):413-419.
Zhu P F,Zuo W M,Zhang L,Hu Q H,Shiu S C K.Pattern Recognit.,2015,48(2):438-446.
Wei X H,Zhu W,Liao B,Cai L J.IEEE Trans. Geosci. Remote Sens.,2019,57(7):4360-4374.
Xi P,Lei Z,Zhang Y.IEEE Conference on Computer Vision and Pattern Recognition,Portland,OR,USA,June 23-28,2013.
Chen L W,Zhang Y H,Wang L G.J. Harbin Eng.Univ. (陈立伟,张雅涵,王立国.哈尔滨工程大学学报),42(8):1230-1236.
Long Y H,Deng X Q,Wang Z W,Liu Y L.J. Data Acquis. Process. (龙咏红,邓秀勤,王卓薇,刘玉兰.数据采集与处理),2021,36(3):544-555.
Guo T,Liang X J,Ma J F,Yuan K,Ge F H,Xiao H X.J. Instrum. Anal. (郭拓,梁小娟,马晋芳,袁凯,葛发欢,肖环贤.分析测试学报),2022,41(8):1214-1220.
Li Z X,Nie F P,Bian J T,Wu D Y,Li X L.IEEE Trans. Pattern Anal. Mach. Intell.,2021,doi:10.1109/TPAMI.2021.312132http://dx.doi.org/10.1109/TPAMI.2021.312132.
Ni C,Li ZY,Zhang X,Sun X Y,Huang Y P,Zhao L,Zhu T T.Trans. Chin. Soc. Agric. Mach.,2019,50(12):170-179.
Yu Y X,Li L,Wang Y Z.Spectrosc. Spectral Anal. (于叶霞,李鹂,王元忠.光谱学与光谱分析),2020,40(8):2440-2446.
Zhang L X,Zhang N N,Zhang X.Laser Optoelectron. Prog. (张立欣,张楠楠,张晓.激光与光电子学进展),2022,59(4):451-457.
Abolfazl A,Peyman S,Nima A,Ali S,Serena A,Hamid H M,Mahdi A.Int. J. Food Prop.,2018,21(1):452-470.
0
浏览量
5
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构