Article(id=1304414840076919705, tenantId=1146029695717560320, journalId=1302319053441957962, issueId=1304414798482010221, articleNumber=null, orderNo=null, doi=10.7501/j.issn.0253-2670.2026.05.025, pmid=null, cstr=null, oa=null, hot=0, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1756742400000, receivedDateStr=2025-09-02, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1788926332730, onlineDateStr=2026-09-09, pubDate=null, pubDateStr=null, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1788926332730, onlineIssueDateStr=2026-09-09, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1788926332730, creator=13701087609, updateTime=1788926332730, updator=13701087609, issue=Issue{id=1304414798482010221, tenantId=1146029695717560320, journalId=1302319053441957962, year='2026', volume='57', issue='5', pageStart='1597', pageEnd='2008', issueExtLink='null', onlineDate='null', pubDate='1773244800000', pubDateStr='2026-03-12', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1788926322813, creator='13701087609', updateTime=1788926625459, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1304416067925864795, tenantId=1146029695717560320, journalId=1302319053441957962, issueId=1304414798482010221, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1304416067925864796, tenantId=1146029695717560320, journalId=1302319053441957962, issueId=1304414798482010221, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=1887, endPage=1895, ext={EN=ArticleExt(id=1304414840357938075, articleId=1304414840076919705, tenantId=1146029695717560320, journalId=1302319053441957962, language=EN, title=Hyperspectral imaging technology combined with machine learning and characteristic band screening for Panax ginseng age identification research, columnId=null, journalTitle=Chinese Traditional and Herbal Drugs, columnName=null, runingTitle=null, highlight=null, articleAbstract=Objective To achieve accurate, nondestructive and low-cost identification of Panax ginseng age, a P. ginseng age identification method was established in this study based on hyperspectral imaging technology combined with machine learning. Methods Hyperspectral images of 84 P. ginseng samples and hyperspectral data of 1 680 regions of interest were obtained by acquiring P. ginseng hyperspectral images in the visible-near infrared (VNIR) and short-wave infrared (SWIR) bands from one to seven years old in Tonghua, Jilin, China, respectively. The hyperspectral data of ginseng samples were preprocessed with multiple scattering correction (MSC), standard normal variation (SNV), Savitzky-Golay smoothing, first-order derivative (FD) and second-order derivative (SD) in the VNIR, SWIR and VNIR + SWIR fusion bands, and then combined with partial least squares discriminant analysis (PLS-DA), linear Then, we combined PLS-DA and LinearSVC discriminant analysis methods to establish the identification models of P. ginseng years in two classification scales distinguished by “medicinal food”, three classification scales distinguished by greater than, less than, and equal to five years, and seven classification scales distinguished by seven years, respectively. Results In the VNIR 410—720 nm band range, there was an overall trend of sequential decrease in the average spectral reflectance of P. ginseng from one year to seven years at the same wavelength. The results of confusion matrix evaluation of different classification recognition models showed that the LinearSVC model with FD preprocessing in SWIR band and fusion band had better classification and higher accuracy at three annual scales, and the prediction set accuracy of 2, 3 and 7 classification models were 99.60%, 98.41% and 95.24%, respectively. The recognition models built using the feature bands screened by the continuous projection algorithm (SPA) have higher accuracy at 2 and 3 classifications, and use fewer bands for more efficient classification and recognition. Conclusion Hyperspectral imaging technology combined with machine learning and feature band screening methods can better achieve the identification of the age of P. ginseng of specific origin, and provide a reference for realizing the practical applications of this technology in P. ginseng age identification and quality control., authors=LI Meng, ZHOU Cong, WANG Hui, YANG Jian, ZHANG Xiaobo, authorsList=LI Meng, ZHOU Cong, WANG Hui, YANG Jian, ZHANG Xiaobo, authorCompany=null, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1304414840286634906, articleId=1304414840076919705, tenantId=1146029695717560320, journalId=1302319053441957962, language=CN, title=高光谱成像技术结合机器学习和特征波段筛选的识别人参年限研究, columnId=1304140203967410414, journalTitle=中草药, columnName=药材与资源, runingTitle=null, highlight=null, articleAbstract=目的 为实现对人参Panax ginseng年限的准确、无损、低成本识别,拟建立一种基于高光谱成像技术结合机器学习的人参年限识别方法。方法 以1~7年生吉林通化地区人参为研究对象,分别在可见-近红外波段(visible-near infrared,VNIR)和短波红外波段(short-wave infrared,SWIR)范围内采集人参高光谱图像,共得到84份人参样品的高光谱图像及1 680个感兴趣区域的高光谱数据。在VNIR、SWIR和VNIR+SWIR融合波段范围内,分别对人参样品高光谱数据进行多元散射校正(multiple scattering correction,MSC)、标准正态变化(standard normal variation,SNV)、Savitzky-Golay平滑、一阶导(first-order derivative,FD)、二阶导(second-order derivative,SD)的预处理,然后分别结合偏最小二乘判别分析(partial least squares discriminant analysis,PLS-DA)、线性支持向量机(Linear SVC)判别分析方法,在以“药食”为区分的2分类识别,以大于、小于、等于5年为区分的3分类识别,以7个年份进行逐年区分的7分类识别的3个年限分类尺度,分别建立人参年限的识别模型。结果 在VNIR 410~720 nm内,同一波长下1~7年人参平均光谱反射率整体有依次降低的趋势。不同分类识别模型的混淆矩阵评估结果表明,SWIR波段和融合波段经FD预处理后的LinearSVC模型在3个年限尺度下的分类效果较好,准确率较高,2、3、7分类模型的预测集准确率分别为99.60%、98.41%、95.24%。利用连续投影算法(continuous projection algorithm,SPA)筛选的特征波段建立的识别模型在2分类和3分类时精度较高,且所用波段更少,分类识别效率更高。结论 高光谱成像技术结合机器学习和特征波段筛选方法,可以较好实现对特定产地人参的年限识别,为实现该技术在人参年限识别和质量控制等实际应用方面提供参考。, authors=李梦1,2, 周聪3, 王慧2, 杨健2, 张小波2, authorsList=李梦, 周聪, 王慧, 杨健, 张小波, authorCompany=1 河南中医药大学, 河南 郑州 450046;
2 中国中医科学院中药资源中心 道地药材品质保障与资源持续利用全国重点实验室, 北京 100700;
3 江西省道地药材质量评价研究中心, 江西 赣江 330000, correspAuthors=张小波, authorNote=李梦: 李梦,助理研究员,博士研究生,主要从事中药资源区划与中药质量评价研究。E-mail:limeng0642@163.com, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=3jGj5XkIu7ND3bxhGaADiQ==, pdfFileSize=1781374, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=国家中医药管理局中医药创新团队及人才支持计划项目 (ZYYCXTD-D-202005); 中国中医科学院科技创新工程 (CI2021A03901); 中央本级重大增减支项目 (2060302))}, authors=null, keywords=[Keyword(id=1304414840496350108, tenantId=1146029695717560320, journalId=1302319053441957962, articleId=1304414840076919705, language=CN, orderNo=1, keyword=高光谱成像), Keyword(id=1304414840559264669, tenantId=1146029695717560320, journalId=1302319053441957962, articleId=1304414840076919705, language=CN, orderNo=2, keyword=机器学习), Keyword(id=1304414840634762142, tenantId=1146029695717560320, journalId=1302319053441957962, articleId=1304414840076919705, language=CN, orderNo=3, keyword=特征波段), Keyword(id=1304414840701871007, tenantId=1146029695717560320, journalId=1302319053441957962, articleId=1304414840076919705, language=CN, orderNo=4, keyword=人参), Keyword(id=1304414840773174176, tenantId=1146029695717560320, journalId=1302319053441957962, articleId=1304414840076919705, language=CN, orderNo=5, keyword=年限识别), Keyword(id=1304414840878031777, tenantId=1146029695717560320, journalId=1302319053441957962, articleId=1304414840076919705, language=EN, orderNo=1, keyword=hyperspectral imaging), Keyword(id=1304414840945140642, tenantId=1146029695717560320, journalId=1302319053441957962, articleId=1304414840076919705, language=EN, orderNo=2, keyword=machine learning), Keyword(id=1304414841033221027, tenantId=1146029695717560320, journalId=1302319053441957962, articleId=1304414840076919705, language=EN, orderNo=3, keyword=characteristic bands), Keyword(id=1304414841096135588, tenantId=1146029695717560320, journalId=1302319053441957962, articleId=1304414840076919705, language=EN, orderNo=4, keyword=Panax ginseng C. A. Meyer), Keyword(id=1304414841200993189, tenantId=1146029695717560320, journalId=1302319053441957962, articleId=1304414840076919705, language=EN, orderNo=5, keyword=age identification)], refs=null, funds=null, companyList=null, figs=null, attaches=null, journal=Journal(id=1302309778002903112, delFlag=0, nameCn=中草药, nameEn=Chinese Traditional and Herbal Drugs, nameHistory1=null, nameHistory2=null, issn=0253-2670, eissn=null, cn=12-1108/R, coden=null, periodic=3, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=cGpSKCP11AF8PAOcTXYWfg==, journalPrice=null, startedYear=null, abbrevIsoEn=Chinese Traditional and Herbal Drugs, journalRemark=null, publicationField=null, createdTime=1788424446827, updatedTime=1788949289390, createdBy=18614031015, updatedBy=13041195026, firstLetterCn=Z, firstLetterEn=Z, subjectCode=Medical and Pharmaceutical Sciences, subjectName=null, subjectCodeEn=Medical and Pharmaceutical Sciences, subjectNameEn=null, picCn=cGpSKCP11AF8PAOcTXYWfg==, picEn=Xw//kxUC3ON4eHxev0QLhQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1304511127375863983, language=CN, name=中草药, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1788949289411, updatedTime=1788949289411, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=https://www.tiprpress.com/zcy/author/login, submissionEditorUrl=https://www.tiprpress.com/zcy/editor/login, submissionReviewUrl=https://www.tiprpress.com/zcy/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1304511127442972848, language=EN, name=Chinese Traditional and Herbal Drugs, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1788949289427, updatedTime=1788949289427, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=https://www.tiprpress.com/zcy/author/login, submissionEditorUrl=https://www.tiprpress.com/zcy/editor/login, submissionReviewUrl=https://www.tiprpress.com/zcy/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1302319053441957962, websiteList=[Website(id=1302319176408912052, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1302319053441957962, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/zcy/CN, language=CN, createTime=1788426687576, createBy=18614031015, updateTime=1788427346252, updateBy=18614031015, name=中草药-中文, tplId=1146099689490845704, title=中草药, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1302322043651904087, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1302319176408912052, code=articleTextType, value=kx, createTime=1788427371180, updateTime=1788427371180, creator=18614031015, updator=18614031015), WebsiteProps(id=1302322043593183828, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1302319176408912052, code=banner, value=null, createTime=1788427371166, updateTime=1788427371166, creator=18614031015, updator=18614031015), WebsiteProps(id=1302322043672875610, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1302319176408912052, code=grayFlag, value=0, createTime=1788427371185, updateTime=1788427371185, creator=18614031015, updator=18614031015), WebsiteProps(id=1302322043584795219, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1302319176408912052, code=logo, value=https://castjournals.cast.org.cn/joweb/zcy/CN/file/pic?fileId=uiD1gpiRqR++OLOz4iKzDg==, createTime=1788427371164, updateTime=1788427371164, creator=18614031015, updator=18614031015), WebsiteProps(id=1302322043689652828, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1302319176408912052, code=minRunFlag, value=0, createTime=1788427371189, updateTime=1788427371189, creator=18614031015, updator=18614031015), WebsiteProps(id=1302322043643515478, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1302319176408912052, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/zcy/CN/file/pic, createTime=1788427371178, updateTime=1788427371178, creator=18614031015, updator=18614031015), WebsiteProps(id=1302322043681264219, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1302319176408912052, code=silenceFlag, value=0, createTime=1788427371187, updateTime=1788427371187, creator=18614031015, updator=18614031015), WebsiteProps(id=1302322043601572437, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1302319176408912052, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1788427371168, updateTime=1788427371168, creator=18614031015, updator=18614031015), WebsiteProps(id=1302322043660292696, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1302319176408912052, code=themeColor, value=null, createTime=1788427371182, updateTime=1788427371182, creator=18614031015, updator=18614031015), WebsiteProps(id=1302322043668681305, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1302319176408912052, code=themeStyle, value=null, createTime=1788427371184, updateTime=1788427371184, creator=18614031015, updator=18614031015)]), Website(id=1302319176715096246, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1302319053441957962, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/zcy/EN, language=EN, createTime=1788426687649, createBy=18614031015, updateTime=1788427341161, updateBy=18614031015, name=中草药-英文, tplId=1146101810881728533, title=Chinese Traditional and Herbal Drugs, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1302322015206134340, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1302319176715096246, code=articleTextType, value=kx, createTime=1788427364398, updateTime=1788427364398, creator=18614031015, updator=18614031015), WebsiteProps(id=1302322015185162817, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1302319176715096246, code=banner, value=null, createTime=1788427364393, updateTime=1788427364393, creator=18614031015, updator=18614031015), WebsiteProps(id=1302322015227105863, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1302319176715096246, code=grayFlag, value=0, createTime=1788427364403, updateTime=1788427364403, creator=18614031015, updator=18614031015), WebsiteProps(id=1302322015176774208, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1302319176715096246, code=logo, value=https://castjournals.cast.org.cn/joweb/zcy/EN/file/pic?fileId=uiD1gpiRqR++OLOz4iKzDg==, createTime=1788427364391, updateTime=1788427364391, creator=18614031015, updator=18614031015), WebsiteProps(id=1302322015239688777, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1302319176715096246, code=minRunFlag, value=0, createTime=1788427364406, updateTime=1788427364406, creator=18614031015, updator=18614031015), WebsiteProps(id=1302322015201940035, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1302319176715096246, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/zcy/EN/file/pic, createTime=1788427364397, updateTime=1788427364397, creator=18614031015, updator=18614031015), WebsiteProps(id=1302322015235494472, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1302319176715096246, code=silenceFlag, value=0, createTime=1788427364405, updateTime=1788427364405, creator=18614031015, updator=18614031015), WebsiteProps(id=1302322015193551426, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1302319176715096246, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1788427364395, updateTime=1788427364395, creator=18614031015, updator=18614031015), WebsiteProps(id=1302322015214522949, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1302319176715096246, code=themeColor, value=null, createTime=1788427364400, updateTime=1788427364400, creator=18614031015, updator=18614031015), WebsiteProps(id=1302322015218717254, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1302319176715096246, code=themeStyle, value=null, createTime=1788427364401, updateTime=1788427364401, creator=18614031015, updator=18614031015)])], journalTitle=中草药, weixinUrl=null, journalUrl=https://www.tiprpress.com/zcy, iacademicId=null, status=1, seqNo=null, journalTitleEn=Chinese Traditional and Herbal Drugs, journalPhotoCn=cGpSKCP11AF8PAOcTXYWfg==, journalPhotoEn=Xw//kxUC3ON4eHxev0QLhQ==, journalFirstLetter=Z, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/zcy/CN/10.7501/j.issn.0253-2670.2026.05.025, detailUrlEn=https://castjournals.cast.org.cn/joweb/zcy/EN/10.7501/j.issn.0253-2670.2026.05.025, pdfUrlCn=https://castjournals.cast.org.cn/joweb/zcy/CN/PDF/10.7501/j.issn.0253-2670.2026.05.025, pdfUrlEn=https://castjournals.cast.org.cn/joweb/zcy/EN/PDF/10.7501/j.issn.0253-2670.2026.05.025, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=0, orderTime=1788926332730, fullTextJson=null, articleText=null, reference=林仲凡. 有关人参的历史考证[J]. 中国农史, 1985, 4(4): 78-84.
李向高. 人参加工炮制前后化学成分的变化[J]. 中药通报, 1986, 11(4): 2-7.
张万博, 代月, 廉美兰, 等. 不同栽培年限人参不同部位中皂苷含量的分析[J]. 延边大学农学学报, 2016, 38(1): 13-17.
陈丽雪. 不同年生人参根及5年生人参不同部位免疫活性的对比研究[D]. 长春: 吉林农业大学, 2019.
线小云, 李葵秀, 李满桥, 等. 人参属药用植物种质资源研究进展[J]. 中草药, 2025, 56(1): 360-373.
詹达琦, 张晓明, 孙素琴. 基于小波变换的二维红外相关光谱鉴别人参的生长年限[J]. 光谱学与光谱分析, 2007, 27(8): 1497-1501.
余江锋, 李育平, 何伟, 等. 吉产不同生长年限人参中8种主要人参皂苷与人参皂苷Rg_1比值的变化规律研究[J]. 中国药房, 2019, 30(1): 31-35.
崔绍庆. 基于不同纳米材料修饰的QCM气敏传感器的制备及人工嗅觉系统的实现[D]. 杭州: 浙江大学, 2015.
Tankeu S, Vermaak I, Chen W Y, et al. Differentiation between two “Fang Ji” herbal medicines, Stephania tetrandra and the nephrotoxic Aristolochia fangchi, using hyperspectral imaging[J]. Phytochemistry, 2016, 122: 213-222.
李梦, 李静, 张小波. 高光谱成像技术的发展现状及其在中药领域中的应用前景[J]. 西部中医药, 2021, 34(10): 149-153.
殷文俊, 茹晨雷, 郑洁, 等. 基于高光谱成像技术融合光谱和图像特征鉴别不同产地的甘草[J]. 中国中药杂志, 2021, 46(4): 923-930.
郑洁, 茹晨雷, 张璐, 等. 基于近红外高光谱成像技术对不同产地苦杏仁和桃仁药材的鉴别[J]. 中国中药杂志, 2021, 46(10): 2571-2577.
李梦, 张小波, 刘绍波, 等. 部分可解释机器学习方法的高光谱人参产地识别和分析[J]. 光谱学与光谱分析, 2022, 42(4): 1217-1221.
王磊, 覃鸿, 李静, 等. 近红外高光谱图像的宁夏枸杞产地鉴别[J]. 光谱学与光谱分析, 2020, 40(4): 1270-1275.
鲍一丹, 吕阳阳, 朱红艳, 等. 陈皮年份的高光谱技术鉴别研究[J]. 光谱学与光谱分析, 2017, 37(6): 1866-1871.
陈书媛, 张友超, 杨杰, 等. 基于高光谱成像技术的白茶储藏年份判别[J]. 食品工业科技, 2021, 42(18): 276-283.
孙梅, 黄宇, 陈兴海, 等. 基于高光谱图像的小麦种子年份快速鉴别分析研究[J]. 中国粮油学报, 2022, 37(1): 170-174.
王庆国, 黄敏, 朱启兵, 等. 基于高光谱图像的玉米种子产地与年份鉴别[J]. 食品与生物技术学报, 2014, 33(2): 163-170.
段龙, 鄢天荥, 王江丽, 等. 结合高光谱成像和机器学习的棉种年份鉴别[J]. 光谱学与光谱分析, 2021, 41(12): 3857-3863.
中华人民共和国国家卫生健康委员会(原卫生部).关于批准人参(人工种植)为新资源食品的公告(2012年第17号)[EB/OL]. (2012-09-05)[2023-02-26]. http://www.nhc.gov.cn/sps/s7891/201209/e94e15f2d9384b6795597ff2b101b2f1.shtml.
Zhang L, An D, Wei Y G, et al. Prediction of oil content in single maize kernel based on hyperspectral imaging and attention convolution neural network[J]. Food Chem, 2022, 395: 133563.
Kwon Y K, Ahn M S, Park J S, et al. Discrimination of cultivation ages and cultivars of ginseng leaves using Fourier transform infrared spectroscopy combined with multivariate analysis[J]. J Ginseng Res, 2014, 38(1): 52-58.)
收藏切换
高光谱成像技术结合机器学习和特征波段筛选的识别人参年限研究
收藏切换
PDF下载
中草药 | 药材与资源 2026,57(5): 1887-1895
收起
收藏切换
中草药 |药材与资源 2026 , 57 (5) : 1887 -1895
高光谱成像技术结合机器学习和特征波段筛选的识别人参年限研究
全屏
李梦1,2, 周聪3, 王慧2, 杨健2, 张小波2
作者信息
    1 河南中医药大学, 河南 郑州 450046;
    2 中国中医科学院中药资源中心 道地药材品质保障与资源持续利用全国重点实验室, 北京 100700;
    3 江西省道地药材质量评价研究中心, 江西 赣江 330000
通讯作者:
张小波
作者简介:
李梦: 李梦,助理研究员,博士研究生,主要从事中药资源区划与中药质量评价研究。E-mail:limeng0642@163.com
Hyperspectral imaging technology combined with machine learning and characteristic band screening for Panax ginseng age identification research
  • LI Meng, ZHOU Cong, WANG Hui, YANG Jian, ZHANG Xiaobo
  • Affiliations
    doi: 10.7501/j.issn.0253-2670.2026.05.025
    文章导航
    收藏切换
    目的 为实现对人参Panax ginseng年限的准确、无损、低成本识别,拟建立一种基于高光谱成像技术结合机器学习的人参年限识别方法。方法 以1~7年生吉林通化地区人参为研究对象,分别在可见-近红外波段(visible-near infrared,VNIR)和短波红外波段(short-wave infrared,SWIR)范围内采集人参高光谱图像,共得到84份人参样品的高光谱图像及1 680个感兴趣区域的高光谱数据。在VNIR、SWIR和VNIR+SWIR融合波段范围内,分别对人参样品高光谱数据进行多元散射校正(multiple scattering correction,MSC)、标准正态变化(standard normal variation,SNV)、Savitzky-Golay平滑、一阶导(first-order derivative,FD)、二阶导(second-order derivative,SD)的预处理,然后分别结合偏最小二乘判别分析(partial least squares discriminant analysis,PLS-DA)、线性支持向量机(Linear SVC)判别分析方法,在以“药食”为区分的2分类识别,以大于、小于、等于5年为区分的3分类识别,以7个年份进行逐年区分的7分类识别的3个年限分类尺度,分别建立人参年限的识别模型。结果 在VNIR 410~720 nm内,同一波长下1~7年人参平均光谱反射率整体有依次降低的趋势。不同分类识别模型的混淆矩阵评估结果表明,SWIR波段和融合波段经FD预处理后的LinearSVC模型在3个年限尺度下的分类效果较好,准确率较高,2、3、7分类模型的预测集准确率分别为99.60%、98.41%、95.24%。利用连续投影算法(continuous projection algorithm,SPA)筛选的特征波段建立的识别模型在2分类和3分类时精度较高,且所用波段更少,分类识别效率更高。结论 高光谱成像技术结合机器学习和特征波段筛选方法,可以较好实现对特定产地人参的年限识别,为实现该技术在人参年限识别和质量控制等实际应用方面提供参考。
    高光谱成像  /  机器学习  /  特征波段  /  人参  /  年限识别
    Objective To achieve accurate, nondestructive and low-cost identification of Panax ginseng age, a P. ginseng age identification method was established in this study based on hyperspectral imaging technology combined with machine learning. Methods Hyperspectral images of 84 P. ginseng samples and hyperspectral data of 1 680 regions of interest were obtained by acquiring P. ginseng hyperspectral images in the visible-near infrared (VNIR) and short-wave infrared (SWIR) bands from one to seven years old in Tonghua, Jilin, China, respectively. The hyperspectral data of ginseng samples were preprocessed with multiple scattering correction (MSC), standard normal variation (SNV), Savitzky-Golay smoothing, first-order derivative (FD) and second-order derivative (SD) in the VNIR, SWIR and VNIR + SWIR fusion bands, and then combined with partial least squares discriminant analysis (PLS-DA), linear Then, we combined PLS-DA and LinearSVC discriminant analysis methods to establish the identification models of P. ginseng years in two classification scales distinguished by “medicinal food”, three classification scales distinguished by greater than, less than, and equal to five years, and seven classification scales distinguished by seven years, respectively. Results In the VNIR 410—720 nm band range, there was an overall trend of sequential decrease in the average spectral reflectance of P. ginseng from one year to seven years at the same wavelength. The results of confusion matrix evaluation of different classification recognition models showed that the LinearSVC model with FD preprocessing in SWIR band and fusion band had better classification and higher accuracy at three annual scales, and the prediction set accuracy of 2, 3 and 7 classification models were 99.60%, 98.41% and 95.24%, respectively. The recognition models built using the feature bands screened by the continuous projection algorithm (SPA) have higher accuracy at 2 and 3 classifications, and use fewer bands for more efficient classification and recognition. Conclusion Hyperspectral imaging technology combined with machine learning and feature band screening methods can better achieve the identification of the age of P. ginseng of specific origin, and provide a reference for realizing the practical applications of this technology in P. ginseng age identification and quality control.
    hyperspectral imaging  /  machine learning  /  characteristic bands  /  Panax ginseng C. A. Meyer  /  age identification
    李梦, 周聪, 王慧, 杨健, 张小波. 高光谱成像技术结合机器学习和特征波段筛选的识别人参年限研究. 中草药, 2026 , 57 (5) : 1887 -1895 . DOI: 10.7501/j.issn.0253-2670.2026.05.025
    LI Meng, ZHOU Cong, WANG Hui, YANG Jian, ZHANG Xiaobo. Hyperspectral imaging technology combined with machine learning and characteristic band screening for Panax ginseng age identification research[J]. Chinese Traditional and Herbal Drugs, 2026 , 57 (5) : 1887 -1895 . DOI: 10.7501/j.issn.0253-2670.2026.05.025

      国家中医药管理局中医药创新团队及人才支持计划项目 (ZYYCXTD-D-202005); 中国中医科学院科技创新工程 (CI2021A03901); 中央本级重大增减支项目 (2060302)

    参考文献 引证文献
    排序方式:
    林仲凡. 有关人参的历史考证[J]. 中国农史, 1985, 4(4): 78-84.
    李向高. 人参加工炮制前后化学成分的变化[J]. 中药通报, 1986, 11(4): 2-7.
    张万博, 代月, 廉美兰, 等. 不同栽培年限人参不同部位中皂苷含量的分析[J]. 延边大学农学学报, 2016, 38(1): 13-17.
    陈丽雪. 不同年生人参根及5年生人参不同部位免疫活性的对比研究[D]. 长春: 吉林农业大学, 2019.
    线小云, 李葵秀, 李满桥, 等. 人参属药用植物种质资源研究进展[J]. 中草药, 2025, 56(1): 360-373.
    詹达琦, 张晓明, 孙素琴. 基于小波变换的二维红外相关光谱鉴别人参的生长年限[J]. 光谱学与光谱分析, 2007, 27(8): 1497-1501.
    余江锋, 李育平, 何伟, 等. 吉产不同生长年限人参中8种主要人参皂苷与人参皂苷Rg_1比值的变化规律研究[J]. 中国药房, 2019, 30(1): 31-35.
    崔绍庆. 基于不同纳米材料修饰的QCM气敏传感器的制备及人工嗅觉系统的实现[D]. 杭州: 浙江大学, 2015.
    Tankeu S, Vermaak I, Chen W Y, et al. Differentiation between two “Fang Ji” herbal medicines, Stephania tetrandra and the nephrotoxic Aristolochia fangchi, using hyperspectral imaging[J]. Phytochemistry, 2016, 122: 213-222.
    李梦, 李静, 张小波. 高光谱成像技术的发展现状及其在中药领域中的应用前景[J]. 西部中医药, 2021, 34(10): 149-153.
    殷文俊, 茹晨雷, 郑洁, 等. 基于高光谱成像技术融合光谱和图像特征鉴别不同产地的甘草[J]. 中国中药杂志, 2021, 46(4): 923-930.
    郑洁, 茹晨雷, 张璐, 等. 基于近红外高光谱成像技术对不同产地苦杏仁和桃仁药材的鉴别[J]. 中国中药杂志, 2021, 46(10): 2571-2577.
    李梦, 张小波, 刘绍波, 等. 部分可解释机器学习方法的高光谱人参产地识别和分析[J]. 光谱学与光谱分析, 2022, 42(4): 1217-1221.
    王磊, 覃鸿, 李静, 等. 近红外高光谱图像的宁夏枸杞产地鉴别[J]. 光谱学与光谱分析, 2020, 40(4): 1270-1275.
    鲍一丹, 吕阳阳, 朱红艳, 等. 陈皮年份的高光谱技术鉴别研究[J]. 光谱学与光谱分析, 2017, 37(6): 1866-1871.
    陈书媛, 张友超, 杨杰, 等. 基于高光谱成像技术的白茶储藏年份判别[J]. 食品工业科技, 2021, 42(18): 276-283.
    孙梅, 黄宇, 陈兴海, 等. 基于高光谱图像的小麦种子年份快速鉴别分析研究[J]. 中国粮油学报, 2022, 37(1): 170-174.
    王庆国, 黄敏, 朱启兵, 等. 基于高光谱图像的玉米种子产地与年份鉴别[J]. 食品与生物技术学报, 2014, 33(2): 163-170.
    段龙, 鄢天荥, 王江丽, 等. 结合高光谱成像和机器学习的棉种年份鉴别[J]. 光谱学与光谱分析, 2021, 41(12): 3857-3863.
    中华人民共和国国家卫生健康委员会(原卫生部).关于批准人参(人工种植)为新资源食品的公告(2012年第17号)[EB/OL]. (2012-09-05)[2023-02-26]. http://www.nhc.gov.cn/sps/s7891/201209/e94e15f2d9384b6795597ff2b101b2f1.shtml.
    Zhang L, An D, Wei Y G, et al. Prediction of oil content in single maize kernel based on hyperspectral imaging and attention convolution neural network[J]. Food Chem, 2022, 395: 133563.
    Kwon Y K, Ahn M S, Park J S, et al. Discrimination of cultivation ages and cultivars of ginseng leaves using Fourier transform infrared spectroscopy combined with multivariate analysis[J]. J Ginseng Res, 2014, 38(1): 52-58.
    2026年第57卷第5期
    PDF下载
    27
    6
    引用本文
    BibTeX
    文章信息
    doi: 10.7501/j.issn.0253-2670.2026.05.025
    • 接收时间:2025-09-02
    • 首发时间:2026-09-09
    补充材料
    相关文章
    文章信息
    作者
    出版历史
    • 收稿日期:2025-09-02
    基金
    作者信息
    参考文献
    分享链接
    https://castjournals.cast.org.cn/joweb/zcy/CN/10.7501/j.issn.0253-2670.2026.05.025
    分享至
    全文二维码

    扫描看全文

    引用本文
    BibTeX
    本文的引用情况
    2种不同金属材料的力学参数

    Family
    属数
    Number of
    genus
    种数
    Number of
    species
    占总种数比例
    Percentage of
    total species (%)

    Genus
    种数
    Number of
    species
    占总种数比例
    Percentage of total
    species (%)
    鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
    小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
    多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
    红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
    小菇属 Mycena 11 5.26
    光柄菇属 Pluteus 5 2.39
    红菇属 Russula 17 8.13
    栓菌属 Trametes 5 2.39
    关闭全屏