Article(id=1241035820849746360, tenantId=1146029695717560320, journalId=1227665162245664772, issueId=1241035810628235909, articleNumber=null, orderNo=null, doi=10.20043/j.cnki.MPM.202406385, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1718985600000, receivedDateStr=2024-06-22, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1773815597021, onlineDateStr=2026-03-18, pubDate=1733760000000, pubDateStr=2024-12-10, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1773815597021, onlineIssueDateStr=2026-03-18, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1773815597021, creator=13701087609, updateTime=1773815597021, updator=13701087609, issue=Issue{id=1241035810628235909, tenantId=1146029695717560320, journalId=1227665162245664772, year='2024', volume='51', issue='23', pageStart='4225', pageEnd='4416', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1773815594584, creator=13701087609, updateTime=1773815743629, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1241036435843764756, tenantId=1146029695717560320, journalId=1227665162245664772, issueId=1241035810628235909, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1241036435843764757, tenantId=1146029695717560320, journalId=1227665162245664772, issueId=1241035810628235909, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=4260, endPage=4265, ext={EN=ArticleExt(id=1241035821252399569, articleId=1241035820849746360, tenantId=1146029695717560320, journalId=1227665162245664772, language=EN, title=Application of time series generalized regression neural network model in predicting the incidence of viral hepatitis, columnId=1240413921954295836, journalTitle=Modern Preventive Medicine, columnName=Epidemiology and Statistical Methods, runingTitle=null, highlight=null, articleAbstract=
Objective

To introduce the application of the time series generalized regression neural network (GRNN) model in predicting the incidence of viral hepatitis in China and to evaluate its fitting and predictive accuracy.

Methods

Monthly incidence data of viral hepatitis from 2004 to 2019 were collected to construct time series. Data from January 2004 to June 2019 were used as training data, while data from July to December 2019 served as testing data. Both GRNN and SARIMA models were established to predict the incidence from July to December 2019, and the predictions were compared with the testing data. The mean absolute percentage error (MAPE) was employed to assess the model’s fitting and predictive performance.

Results

The fitting MAPE for the GRNN model across various types of hepatitis ranged from 1.67% to 21.22%, while the predictive MAPE ranged from 2.26% to 17.17%. In comparison, the SARIMA model’s fitting MAPE for various types of hepatitis ranged from 3.84% to 7.87%, with a predictive MAPE ranging from 2.54% to 48.89%. Notably, the predictive MAPE for hepatitis A was 48.89%, indicating a significant prediction error.

Conclusion

The GRNN model outperformed the SARIMA model in predicting the monthly incidence of viral hepatitis in China, suggesting its suitability for broader application.

, 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, authorCompany=null, fund=null, authors=null, authorsList=Ya-jun SUN, Tian LIU, Yuan YAO), CN=ArticleExt(id=1241035824565899842, articleId=1241035820849746360, tenantId=1146029695717560320, journalId=1227665162245664772, language=CN, title=时间序列广义回归神经网络模型在病毒性肝炎发病率预测中的应用, columnId=1228016567632462653, journalTitle=现代预防医学, columnName=流行病与统计方法, runingTitle=null, highlight=null, articleAbstract=
目的

本研究旨在介绍基于时间序列广义回归神经网络(generalized regression neural network, GRNN)模型在中国病毒性肝炎发病率预测中的应用,评估其拟合及预测精度。

方法

收集全国2004—2019年病毒性肝炎逐月发病率数据构建时间序列,以2004年1月—2019年6月数据为训练数据,2019年7—12月数据为测试数据,分别建立GRNN和SARIMA模型,预测2019年7—12月发病率并与测试数据比较。采用平均绝对百分比误差(MAPE)评价模型拟合及预测效果。

结果

GRNN模型对各类肝炎的拟合MAPE在1.67%~21.22%之间,预测MAPE在2.26%~17.17%之间。与之相比,SARIMA模型对各类肝炎的拟合MAPE在3.84%~7.87%之间,预测MAPE在2.54%~48.89%之间,其中甲肝的预测MAPE为48.89%,显示出较大的预测误差。

结论

GRNN模型在我国病毒性肝炎月发病率预测中表现优于SARIMA模型,适合推广应用。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
姚远,E-mail:
, copyrightStatement=本刊刊出的所有文章不代表中华预防医学会和本刊编委会的观点,除非特别声明。, copyrightOwner=中华预防医学会和四川大学华西公共卫生学院, extLink=null, articleAbsUrl=null, sourceXml=xc48GgmaFlHe7030SjdmpQ==, magXml=5m1CoxdlPU/QXappImtOoA==, pdfUrl=null, pdf=s2tveepN5mT7mR3jOHLjYA==, pdfFileSize=1054826, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=1UM7u+x0J54QdcLZHs1iwA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=6Ei8MRIwbCWkqV+9jlNMyQ==, mapNumber=null, authorCompany=null, fund=null, authors=

孙亚军(1978—),男,硕士,主任医师,研究方向:疾病监测与数据分析

, authorsList=孙亚军, 刘天, 姚远)}, authors=[Author(id=1241069115624969037, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241069115759186782, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, authorId=1241069115624969037, language=EN, stringName=Ya-jun SUN, firstName=Ya-jun, middleName=null, lastName=SUN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 3, address=The Third People’s Hospital of Zhuhai, Zhuhai, Guangdong 519000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241069115885015910, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, authorId=1241069115624969037, language=CN, stringName=孙亚军, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 3, address=1.珠海市第三人民医院,广东 珠海 519000
3.重庆市九龙坡区疾病预防控制中心,重庆 400050, bio={"content":"

孙亚军(1978—),男,硕士,主任医师,研究方向:疾病监测与数据分析

"}, bioImg=null, bioContent=

孙亚军(1978—),男,硕士,主任医师,研究方向:疾病监测与数据分析

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241069115260064559, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, xref=1., ext=[AuthorCompanyExt(id=1241069115268453166, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, companyId=1241069115260064559, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=The Third People’s Hospital of Zhuhai, Zhuhai, Guangdong 519000, China), AuthorCompanyExt(id=1241069115276841775, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, companyId=1241069115260064559, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.珠海市第三人民医院,广东 珠海 519000)]), AuthorCompany(id=1241069115520111427, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, xref=3., ext=[AuthorCompanyExt(id=1241069115528500036, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, companyId=1241069115520111427, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.重庆市九龙坡区疾病预防控制中心,重庆 400050)])]), Author(id=1241069115989873520, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241069116111508346, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, authorId=1241069115989873520, language=EN, stringName=Tian LIU, firstName=Tian, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=null, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241069116266697603, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, authorId=1241069115989873520, language=CN, stringName=刘天, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.荆州市疾病预防控制中心, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241069115415253821, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, xref=2., ext=[AuthorCompanyExt(id=1241069115419448126, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, companyId=1241069115415253821, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.荆州市疾病预防控制中心)])]), Author(id=1241069116354777998, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=71165057@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241069116493190046, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, authorId=1241069116354777998, language=EN, stringName=Yuan YAO, firstName=Yuan, middleName=null, lastName=YAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=null, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241069116593853348, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, authorId=1241069116354777998, language=CN, stringName=姚远, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3.重庆市九龙坡区疾病预防控制中心,重庆 400050, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241069115520111427, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, xref=3., ext=[AuthorCompanyExt(id=1241069115528500036, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, companyId=1241069115520111427, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.重庆市九龙坡区疾病预防控制中心,重庆 400050)])])], keywords=[Keyword(id=1241069116828734385, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, language=EN, orderNo=1, keyword=GRNN), Keyword(id=1241069116967146425, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, language=EN, orderNo=2, keyword=SARIMA), Keyword(id=1241069117092975555, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, language=EN, orderNo=3, keyword=Prediction), Keyword(id=1241069117172667340, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, language=EN, orderNo=4, keyword=Viral hepatitis), Keyword(id=1241069117298496471, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, language=EN, orderNo=5, keyword=Time series), Keyword(id=1241069117390771165, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, language=CN, orderNo=1, keyword=GRNN), Keyword(id=1241069117487240168, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, language=CN, orderNo=2, keyword=SARIMA), Keyword(id=1241069117600486387, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, language=CN, orderNo=3, keyword=预测), Keyword(id=1241069117705343995, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, language=CN, orderNo=4, keyword=病毒性肝炎), Keyword(id=1241069118800056326, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, language=CN, orderNo=5, keyword=时间序列)], refs=[Reference(id=1241069120905597108, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, doi=null, pmid=null, pmcid=null, year=2024, volume=30, issue=18, pageStart=2402, pageEnd=2417, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=Usuda D, Kaneoka Y, Ono R, journalName=World Journal of Gastroenterology, refType=null, unstructuredReference=Usuda D, Kaneoka Y, Ono R, et al. Current perspectives of viral hepatitis[J]. World Journal of Gastroenterology, 2024, 30(18): 2402-2417., articleTitle=Current perspectives of viral hepatitis, refAbstract=null), Reference(id=1241069121023037629, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=1, pageStart=1229, pageEnd=null, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=Black AP, Wallace J, Binka M, journalName=BMC Public Health, refType=null, unstructuredReference=Black AP, Wallace J, Binka M, et al. Correction: the challenges of viral hepatitis elimination: a global response to a global problem[J].BMC Public Health, 2023, 23(1): 1229., articleTitle=Correction: the challenges of viral hepatitis elimination: a global response to a global problem, refAbstract=null), Reference(id=1241069121153061061, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, doi=null, pmid=null, pmcid=null, year=2022, volume=17, issue=4, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=Xia ZH, Qin L, Ning Z, journalName=PLOS One, refType=null, unstructuredReference=Xia ZH, Qin L, Ning Z, et al. Deep learning time series prediction models in surveillance data of hepatitis incidence in China[J]. PLOS One, 2022, 17(4): e0265660., articleTitle=Deep learning time series prediction models in surveillance data of hepatitis incidence in China, refAbstract=null), Reference(id=1241069121278890191, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=1, pageStart=280, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=Zhai MM, Li WH, Tie P, journalName=BMC Infectious Diseases, refType=null, unstructuredReference=Zhai MM, Li WH, Tie P, et al. Research on the predictive effect of a combined model of ARIMA and neural networks on human brucellosis in Shanxi Province, China: a time series predictive analysis[J]. BMC Infectious Diseases, 2021, 21(1): 280., articleTitle=Research on the predictive effect of a combined model of ARIMA and neural networks on human brucellosis in Shanxi Province, China: a time series predictive analysis, refAbstract=null), Reference(id=1241069121396330709, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, doi=null, pmid=null, pmcid=null, year=2019, volume=12, issue=null, pageStart=1011, pageEnd=1020, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=Li ZQ, Wang ZZ, Song H, journalName=Infection and Drug Resistance, refType=null, unstructuredReference=Li ZQ, Wang ZZ, Song H, et al. Application of a hybrid model in predicting the incidence of tuberculosis in a Chinese population[J].Infection and Drug Resistance, 2019, 12: 1011-1020., articleTitle=Application of a hybrid model in predicting the incidence of tuberculosis in a Chinese population, refAbstract=null), Reference(id=1241069121496994013, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, doi=null, pmid=null, pmcid=null, year=2023, volume=18, issue=3, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=5, authorNames=Feng Y, Cui X, Lv J, journalName=PLOS One, refType=null, unstructuredReference=Feng Y, Cui X, Lv J, et al. Deep learning models for hepatitis E incidence prediction leveraging meteorological factors[J]. PLOS One,2023, 18(3): e0282928., articleTitle=Deep learning models for hepatitis E incidence prediction leveraging meteorological factors, refAbstract=null), Reference(id=1241069121610240231, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, doi=null, pmid=null, pmcid=null, year=2020, volume=17, issue=12, pageStart=4204, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=6, authorNames=Mollalo A, Rivera KM, Vahedi B, journalName=International Journal of Environmental Research and Public Health, refType=null, unstructuredReference=Mollalo A, Rivera KM, Vahedi B. Artificial neural network modeling of novel coronavirus (COVID-19) incidence rates across the continental United States[J]. International Journal of Environmental Research and Public Health, 2020, 17(12): 4204., articleTitle=Artificial neural network modeling of novel coronavirus (COVID-19) incidence rates across the continental United States, refAbstract=null), Reference(id=1241069121761235180, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=7, authorNames=Zhu XX, Zheng YM, Zheng YL, journalName=null, refType=null, unstructuredReference=Zhu XX, Zheng YM, Zheng YL, et al. Application of generalized regression neural network and sarima model in prediction of AIDS[EB/OL]. [2024-10-20]. https://ieeexplore.ieee.org/document/9988161., articleTitle=Application of generalized regression neural network and sarima model in prediction of AIDS, refAbstract=null), Reference(id=1241069121866092789, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, doi=null, pmid=null, pmcid=null, year=2020, volume=37, issue=6, pageStart=851, pageEnd=854, url=null, language=null, rfNumber=[9], rfOrder=8, authorNames=冯佳宁, 肖宇飞, 王晓璇, journalName=中国卫生统计, refType=null, unstructuredReference=冯佳宁,肖宇飞,王晓璇,等.ARIMA乘积季节模型与GRNN模型在猩红热发病预测中的比较[J].中国卫生统计202037(6):851-854., articleTitle=ARIMA乘积季节模型与GRNN模型在猩红热发病预测中的比较, refAbstract=null), Reference(id=1241069121979339003, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, doi=null, pmid=null, pmcid=null, year=2020, volume=37, issue=6, pageStart=851, pageEnd=854, url=null, language=null, rfNumber=[9], rfOrder=9, authorNames=Feng JN, Xiao YF, Wang XX, journalName=Chinese Journal of Health Statistics, refType=null, unstructuredReference=Feng JN, Xiao YF, Wang XX, et al. A comparative study of multiplicative seasonal ARIMA model and GRNN for scarlet fever incidence forecasting[J]. Chinese Journal of Health Statistics, 2020, 37(6): 851-854.(In Chinese), articleTitle=A comparative study of multiplicative seasonal ARIMA model and GRNN for scarlet fever incidence forecasting, refAbstract=null), Reference(id=1241069122063225089, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=10, authorNames=Martínez F, Charte F, Rivera AJ, journalName=null, refType=null, unstructuredReference=Martínez F, Charte F, Rivera AJ, et al. Automatic time series forecasting with GRNN: A comparison with other models[EB/OL].[2024-10-20]. https://link.springer.com/chapter/10.1007/978-3-030-20521-8_17., articleTitle=Automatic time series forecasting with GRNN: A comparison with other models, refAbstract=null), Reference(id=1241069122189054220, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, doi=null, pmid=null, pmcid=null, year=2020, volume=47, issue=21, pageStart=3863, pageEnd=3866, 3923, url=null, language=null, rfNumber=[11], rfOrder=11, authorNames=李于于, 曾令城, 柳巍, journalName=现代预防医学, refType=null, unstructuredReference=李于于,曾令城,柳巍.遗传优化的广义回归神经网络在肺结核发病预测中的应用[J].现代预防医学202047(21):3863-3866, 3923., articleTitle=遗传优化的广义回归神经网络在肺结核发病预测中的应用, refAbstract=null), Reference(id=1241069122298106133, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, doi=null, pmid=null, pmcid=null, year=2020, volume=47, issue=21, pageStart=3863, pageEnd=3866, 3923, url=null, language=null, rfNumber=[11], rfOrder=12, authorNames=Li YY, Zeng LC, Liu W, journalName=Modern Preventive Medicine, refType=null, unstructuredReference=Li YY, Zeng LC, Liu W. Application of genetic-optimized generalized regression neural network in the prediction of tuberculosis[J]. Modern Preventive Medicine, 2020, 47(21): 3863-3866, 3923.(In Chinese), articleTitle=Application of genetic-optimized generalized regression neural network in the prediction of tuberculosis, refAbstract=null), Reference(id=1241069122436518173, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, doi=null, pmid=null, pmcid=null, year=2022, volume=491, issue=null, pageStart=509, pageEnd=521, url=null, language=null, rfNumber=[12], rfOrder=13, authorNames=Martínez F, Charte F, Frías MP, journalName=Neurocomputing, refType=null, unstructuredReference=Martínez F, Charte F, Frías MP, et al. Strategies for time series forecasting with generalized regression neural networks[J].Neurocomputing, 2022, 491: 509-521., articleTitle=Strategies for time series forecasting with generalized regression neural networks, refAbstract=null), Reference(id=1241069123954856226, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=14, authorNames=汪宗正, journalName=null, refType=null, unstructuredReference=汪宗正.基于广义回归神经网络的动态光散射粒度反演研究[D].淄博:山东理工大学,2023., articleTitle=基于广义回归神经网络的动态光散射粒度反演研究, refAbstract=null), Reference(id=1241069124114239789, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=15, authorNames=Wang ZZ, journalName=null, refType=null, unstructuredReference=Wang ZZ. Study on particle size distribution inversion of dynamic light scattering based on generalized regression neural network[D]. Zibo:Shandong University of Technology, 2023.(In Chinese), articleTitle=Study on particle size distribution inversion of dynamic light scattering based on generalized regression neural network, refAbstract=null), Reference(id=1241069124214903093, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, doi=null, pmid=null, pmcid=null, year=2015, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=16, authorNames=Box G, Jenkins GM, Reinsel GC, journalName=Time series analysis: forecasting and control, refType=null, unstructuredReference=Box G, Jenkins GM, Reinsel GC, et al. Time series analysis: forecasting and control(5th ed.)[M]. New Jersey: John Wiley&Sons, 2015., articleTitle=null, refAbstract=null), Reference(id=1241069124307177788, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=17, authorNames=Hyndman R, Athanasopoulos G, Bergmeir C, journalName=null, refType=null, unstructuredReference=Hyndman R, Athanasopoulos G, Bergmeir C, et al. 2024. Forecast: forecasting functions for time series and linear models[EB/OL]. [2024-10-20]. https://pkg.robjhyndman.com/forecast/., articleTitle=2024. Forecast: forecasting functions for time series and linear models, refAbstract=null), Reference(id=1241069124391063873, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, doi=null, pmid=null, pmcid=null, year=2020, volume=249, issue=null, pageStart=1, pageEnd=13, url=null, language=null, rfNumber=[16], rfOrder=18, authorNames=Dun M, Xu ZC, Chen Y, journalName=Mathematical Problems in Engineering, refType=null, unstructuredReference=Dun M, Xu ZC, Chen Y, et al.Short-term air quality prediction based on fractional grey linear regression and support vector machine[J]. Mathematical Problems in Engineering, 2020, 249: 1-13., articleTitle=Short-term air quality prediction based on fractional grey linear regression and support vector machine, refAbstract=null), Reference(id=1241069124495921477, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, doi=null, pmid=null, pmcid=null, year=2016, volume=11, issue=6, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=19, authorNames=Wei WD, Jiang JJ, Liang H, journalName=PLOS One, refType=null, unstructuredReference=Wei WD, Jiang JJ, Liang H, et al. Application of a combined model with autoregressive integrated moving average (ARIMA) and generalized regression neural network (GRNN) in forecasting hepatitis incidence in Heng county, China[J]. PLOS One, 2016, 11(6):e0156768., articleTitle=Application of a combined model with autoregressive integrated moving average (ARIMA) and generalized regression neural network (GRNN) in forecasting hepatitis incidence in Heng county, China, refAbstract=null), Reference(id=1241069124672082256, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, doi=null, pmid=null, pmcid=null, year=2019, volume=9, issue=6, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=20, authorNames=Wang YW, Shen ZZ, Jiang Y, journalName=BMJ Open, refType=null, unstructuredReference=Wang YW, Shen ZZ, Jiang Y.Comparison of autoregressive integrated moving average model and generalised regression neural network model for prediction of haemorrhagic fever with renal syndrome in China: a time-series study[J]. BMJ Open, 2019, 9(6):e025773., articleTitle=Comparison of autoregressive integrated moving average model and generalised regression neural network model for prediction of haemorrhagic fever with renal syndrome in China: a time-series study, refAbstract=null), Reference(id=1241069124760162644, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, doi=null, pmid=null, pmcid=null, year=2022, volume=33, issue=4, pageStart=548, pageEnd=554, url=null, language=null, rfNumber=[19], rfOrder=21, authorNames=刘天, 姚梦雷, 侯清波, journalName=中国媒介生物学及控制杂志, refType=null, unstructuredReference=刘天,姚梦雷,侯清波,等.7种时间序列模型对全国肾综合征出血热发病率预测效果比较[J].中国媒介生物学及控制杂志202233(4):548-554., articleTitle=7种时间序列模型对全国肾综合征出血热发病率预测效果比较, refAbstract=null), Reference(id=1241069124906963288, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, doi=null, pmid=null, pmcid=null, year=2022, volume=33, issue=4, pageStart=548, pageEnd=554, url=null, language=null, rfNumber=[19], rfOrder=22, authorNames=Liu T, Yao ML, Hou QB, journalName=Chinese Journal of Vector Biology and Control, refType=null, unstructuredReference=Liu T, Yao ML, Hou QB, et al. Comparison of seven time series models in fitting and predicting the incidence of hemorrhagic fever with renal syndrome in China[J]. Chinese Journal of Vector Biology and Control,2022, 33(4): 548-554.(In Chinese), articleTitle=Comparison of seven time series models in fitting and predicting the incidence of hemorrhagic fever with renal syndrome in China, refAbstract=null), Reference(id=1241069125024403805, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, doi=null, pmid=null, pmcid=null, year=2021, volume=149, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[20], rfOrder=23, authorNames=Wang G, Wu T, Wei W, journalName=Epidemiology and Infection, refType=null, unstructuredReference=Wang G, Wu T, Wei W, et al. Comparison of ARIMA, ES, GRNN and ARIMA-GRNN hybrid models to forecast the second wave of COVID-19 in India and the United States[J]. Epidemiology and Infection, 2021, 149: e240., articleTitle=Comparison of ARIMA, ES, GRNN and ARIMA-GRNN hybrid models to forecast the second wave of COVID-19 in India and the United States, refAbstract=null), Reference(id=1241069125133455714, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, doi=null, pmid=null, pmcid=null, year=2020, volume=15, issue=9, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[21], rfOrder=24, authorNames=Guo YH, Feng Y, Qu FL, journalName=PLOS One, refType=null, unstructuredReference=Guo YH, Feng Y, Qu FL, et al. Prediction of hepatitis E using machine learning models[J]. PLOS One, 2020, 15(9): e0237750., articleTitle=Prediction of hepatitis E using machine learning models, refAbstract=null), Reference(id=1241069125263479141, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, doi=null, pmid=null, pmcid=null, year=2020, volume=37, issue=2, pageStart=249, pageEnd=252, url=null, language=null, rfNumber=[22], rfOrder=25, authorNames=李峰, 陈国清, 徐士林, journalName=中国卫生统计, refType=null, unstructuredReference=李峰,陈国清,徐士林,等.三种时间序列模型在盐城市肾综合征出血热发病预测应用中的比较研究[J].中国卫生统计202037(2):249-252., articleTitle=三种时间序列模型在盐城市肾综合征出血热发病预测应用中的比较研究, refAbstract=null), Reference(id=1241069125368336744, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, doi=null, pmid=null, pmcid=null, year=2020, volume=37, issue=2, pageStart=249, pageEnd=252, url=null, language=null, rfNumber=[22], rfOrder=26, authorNames=Li F, Chen GQ, Xu SL, journalName=Chinese Journal of Health Statistics, refType=null, unstructuredReference=Li F, Chen GQ, Xu SL, et al. Comparative analysis of three time series models for predicting hemorrhagic fever with renal syndrome incidence in Yancheng City[J]. Chinese Journal of Health Statistics, 2020, 37(2): 249-252.(In Chinese), articleTitle=Comparative analysis of three time series models for predicting hemorrhagic fever with renal syndrome incidence in Yancheng City, refAbstract=null), Reference(id=1241069125498360175, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, doi=null, pmid=null, pmcid=null, year=2021, volume=25, issue=11, pageStart=1341, pageEnd=1346, url=null, language=null, rfNumber=[23], rfOrder=27, authorNames=李文豪, 曾昱兴, 李笑颜, journalName=中华疾病控制杂志, refType=null, unstructuredReference=李文豪,曾昱兴,李笑颜,等.SARIMA-GRNN组合模型在伤寒与副伤寒逐月发病数预测中的应用[J].中华疾病控制杂志202125(11):1341-1346., articleTitle=SARIMA-GRNN组合模型在伤寒与副伤寒逐月发病数预测中的应用, refAbstract=null), Reference(id=1241069125619994993, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, doi=null, pmid=null, pmcid=null, year=2021, volume=25, issue=11, pageStart=1341, pageEnd=1346, url=null, language=null, rfNumber=[23], rfOrder=28, authorNames=Li WH, Zeng YX, Li XY, journalName=Chinese Journal of Disease Control & Prevention, refType=null, unstructuredReference=Li WH, Zeng YX, Li XY, et al. Application of SARIMA-GRNN combined model in forecasting the monthly incidence of typhoid fever and paratyphoid fever[J]. Chinese Journal of Disease Control & Prevention,2021, 25(11): 1341-1346.(In Chinese), articleTitle=Application of SARIMA-GRNN combined model in forecasting the monthly incidence of typhoid fever and paratyphoid fever, refAbstract=null), Reference(id=1241069125812932985, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, doi=null, pmid=null, pmcid=null, year=2021, volume=70, issue=null, pageStart=245, pageEnd=317, url=null, language=null, rfNumber=[24], rfOrder=29, authorNames=Burkart N, Huber MF, journalName=Journal of Artificial Intelligence Research, refType=null, unstructuredReference=Burkart N, Huber MF. A survey on the explainability of supervised machine learning[J]. Journal of Artificial Intelligence Research, 2021, 70: 245-317., articleTitle=A survey on the explainability of supervised machine learning, refAbstract=null), Reference(id=1241069125917790591, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, doi=null, pmid=null, pmcid=null, year=2021, volume=135, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[25], rfOrder=30, authorNames=Du XP, Xu HY, Zhu F, journalName=Computer Aided Design, refType=null, unstructuredReference=Du XP, Xu HY, Zhu F. Understanding the effect of hyperparameter optimization on machine learning models for structure design problems[J]. Computer Aided Design, 2021, 135: 103013., articleTitle=Understanding the effect of hyperparameter optimization on machine learning models for structure design problems, refAbstract=null), Reference(id=1241069126014259585, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, doi=null, pmid=null, pmcid=null, year=2021, volume=43, issue=1, pageStart=301, pageEnd=316, url=null, language=null, rfNumber=[26], rfOrder=31, authorNames=Yan D, Kong Y, Ye B, journalName=Environmental Geochemistry and Health, refType=null, unstructuredReference=Yan D, Kong Y, Ye B, et al. Spatio-temporal variation and daily prediction of PM2.5 concentration in world-class urban agglomerations of China[J]. Environmental Geochemistry and Health,2021, 43(1): 301-316., articleTitle=Spatio-temporal variation and daily prediction of PM2.5 concentration in world-class urban agglomerations of China, refAbstract=null), Reference(id=1241069126114922883, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=1, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[27], rfOrder=32, authorNames=Wang L, Xia Y, Lu YC, journalName=Computational Intelligence and Neuroscience, refType=null, unstructuredReference=Wang L, Xia Y, Lu YC. A novel forecasting approach by the GA-SVR-GRNN hybrid deep learning algorithm for oil future prices[J].Computational Intelligence and Neuroscience, 2022(1): 4952215., articleTitle=A novel forecasting approach by the GA-SVR-GRNN hybrid deep learning algorithm for oil future prices, refAbstract=null)], funds=[Fund(id=1241069120649744545, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, awardId=YWBF2023081, language=CN, fundingSource=重庆市公共卫生重点专科(学科)建设项目(YWBF2023081), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1241069115260064559, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, xref=1., ext=[AuthorCompanyExt(id=1241069115268453166, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, companyId=1241069115260064559, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=The Third People’s Hospital of Zhuhai, Zhuhai, Guangdong 519000, China), AuthorCompanyExt(id=1241069115276841775, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, companyId=1241069115260064559, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.珠海市第三人民医院,广东 珠海 519000)]), AuthorCompany(id=1241069115415253821, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, xref=2., ext=[AuthorCompanyExt(id=1241069115419448126, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, companyId=1241069115415253821, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.荆州市疾病预防控制中心)]), AuthorCompany(id=1241069115520111427, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, xref=3., ext=[AuthorCompanyExt(id=1241069115528500036, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, companyId=1241069115520111427, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.重庆市九龙坡区疾病预防控制中心,重庆 400050)])], figs=[ArticleFig(id=1241069119064297507, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, language=EN, label=Figure 1, caption=The time series of viral hepatitis incidence rates in China from 2004 to 2019, figureFileSmall=bcys+GEY3kekuGDdQOYJtw==, figureFileBig=TulQnCxUNJoANaD6ManIWw==, tableContent=null), ArticleFig(id=1241069119181738032, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, language=CN, label=图1, caption=2004—2019年全国病毒性肝炎发病率时间序列, figureFileSmall=bcys+GEY3kekuGDdQOYJtw==, figureFileBig=TulQnCxUNJoANaD6ManIWw==, tableContent=null), ArticleFig(id=1241069119290789944, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, language=EN, label=Figure 2, caption=Seasonal index of viral hepatitis incidence rates in China from 2004 to 2019, figureFileSmall=ZYeF4X0TZSlN/vELZyW2fw==, figureFileBig=gB8HVsN+Uh2uo5KFlZdO2g==, tableContent=null), ArticleFig(id=1241069119395647552, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, language=CN, label=图2, caption=2004—2019年全国病毒性肝炎季节指数, figureFileSmall=ZYeF4X0TZSlN/vELZyW2fw==, figureFileBig=gB8HVsN+Uh2uo5KFlZdO2g==, tableContent=null), ArticleFig(id=1241069119496310859, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, language=EN, label=Table 1, caption=

The annual incidence of viral hepatitis in China from 2004 to 2019

, figureFileSmall=null, figureFileBig=null, tableContent=
年份(年)病毒性肝炎甲肝乙肝丙肝戊肝未分型肝炎
发病数发病率 (1/10万)发病数发病率(1/10万)发病数发病率 (1/10万)发病数发病率 (1/10万)发病数发病率(1/10万)发病数发病率(1/10万)
20041 152 87488.6993 5877.20916 42670.5039 3813.0316 4441.2787 0366.70
20051 195 35591.9673 3495.64982 29775.5752 9274.0715 5411.2071 2415.48
20061 334 859102.0968 6675.251 109 13084.8270 6815.4119 0071.4567 3745.15
20071 425 428108.4477 1355.871 169 94689.0192 3787.0320 5771.5765 3924.97
20081 407 664106.5456 0524.241 169 56988.52108 4468.2118 5251.4055 0724.17
20091 425 020107.3043 8413.301 179 60788.82131 8499.9320 2751.5349 4483.72
20101 317 98298.7435 2772.641 060 58279.46153 03911.4723 6821.7745 4023.40
20111 372 344102.3431 4562.351 093 33581.54173 87212.9729 2022.1844 4793.32
20121 380 800102.4824 4531.811 087 08680.68201 62214.9627 2712.0240 3683.00
20131 251 87292.4622 2441.64962 97471.12203 15515.0027 9022.0635 5972.63
20141 223 02190.2525 9691.92935 70269.05202 80314.9726 9881.9931 5592.33
20151 218 94689.4722 6671.66934 21568.57207 89715.2627 1691.9926 9981.98
20161 221 47989.1121 2851.55942 26868.74206 83215.0927 9222.0422 7611.66
20171 283 52393.0218 8751.371 001 95272.61214 02315.5129 0142.1019 2841.40
20181 280 01592.1516 1961.17999 98571.99219 37515.7928 6032.0615 5001.12
20191 286 69192.1319 2711.381 002 29271.77223 66016.0228 1552.0212 9610.93
合计20 777 87396.63650 3243.0216 547 36676.962 501 94011.64386 2771.80690 4723.21
), ArticleFig(id=1241069119584391251, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, language=CN, label=表1, caption=

2004—2019年全国病毒性肝炎发病情况

, figureFileSmall=null, figureFileBig=null, tableContent=
年份(年)病毒性肝炎甲肝乙肝丙肝戊肝未分型肝炎
发病数发病率 (1/10万)发病数发病率(1/10万)发病数发病率 (1/10万)发病数发病率 (1/10万)发病数发病率(1/10万)发病数发病率(1/10万)
20041 152 87488.6993 5877.20916 42670.5039 3813.0316 4441.2787 0366.70
20051 195 35591.9673 3495.64982 29775.5752 9274.0715 5411.2071 2415.48
20061 334 859102.0968 6675.251 109 13084.8270 6815.4119 0071.4567 3745.15
20071 425 428108.4477 1355.871 169 94689.0192 3787.0320 5771.5765 3924.97
20081 407 664106.5456 0524.241 169 56988.52108 4468.2118 5251.4055 0724.17
20091 425 020107.3043 8413.301 179 60788.82131 8499.9320 2751.5349 4483.72
20101 317 98298.7435 2772.641 060 58279.46153 03911.4723 6821.7745 4023.40
20111 372 344102.3431 4562.351 093 33581.54173 87212.9729 2022.1844 4793.32
20121 380 800102.4824 4531.811 087 08680.68201 62214.9627 2712.0240 3683.00
20131 251 87292.4622 2441.64962 97471.12203 15515.0027 9022.0635 5972.63
20141 223 02190.2525 9691.92935 70269.05202 80314.9726 9881.9931 5592.33
20151 218 94689.4722 6671.66934 21568.57207 89715.2627 1691.9926 9981.98
20161 221 47989.1121 2851.55942 26868.74206 83215.0927 9222.0422 7611.66
20171 283 52393.0218 8751.371 001 95272.61214 02315.5129 0142.1019 2841.40
20181 280 01592.1516 1961.17999 98571.99219 37515.7928 6032.0615 5001.12
20191 286 69192.1319 2711.381 002 29271.77223 66016.0228 1552.0212 9610.93
合计20 777 87396.63650 3243.0216 547 36676.962 501 94011.64386 2771.80690 4723.21
), ArticleFig(id=1241069119693443161, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, language=EN, label=Table 2, caption=

Optimal GRNN models and their modeling accuracy for viral hepatitis incidence

, figureFileSmall=null, figureFileBig=null, tableContent=
肝炎类型sigmaMAPE(%)
病毒性肝炎0.781.80
甲肝0.0221.22
乙肝0.282.10
丙肝0.071.67
戊肝0.034.43
未分型肝炎0.0111.43
), ArticleFig(id=1241069119810883685, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, language=CN, label=表2, caption=

病毒性肝炎发病率GRNN最优模型及拟合效果

, figureFileSmall=null, figureFileBig=null, tableContent=
肝炎类型sigmaMAPE(%)
病毒性肝炎0.781.80
甲肝0.0221.22
乙肝0.282.10
丙肝0.071.67
戊肝0.034.43
未分型肝炎0.0111.43
), ArticleFig(id=1241069119915741292, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, language=EN, label=Table 3, caption=

The optimal SARIMA models and residual test results for viral hepatitis incidence

, figureFileSmall=null, figureFileBig=null, tableContent=
肝炎类型最优模型Q*P
病毒性肝炎SARIMA(2,1,0)(0,1,2)1210.1250.430
甲肝SARIMA(1,1,3)(2,1,1)1212.8740.231
乙肝SARIMA(2,1,0)(0,1,2)128.8090.550
丙肝SARIMA(2,1,1)(0,1,2)129.4850.487
戊肝SARIMA(1,0,2)(0,1,1)124.6750.912
未分型肝炎SARIMA(2,1,2)(2,1,1)1217.0050.074
), ArticleFig(id=1241069119995433073, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, language=CN, label=表3, caption=

病毒性肝炎发病率SARIMA最优模型及残差检验

, figureFileSmall=null, figureFileBig=null, tableContent=
肝炎类型最优模型Q*P
病毒性肝炎SARIMA(2,1,0)(0,1,2)1210.1250.430
甲肝SARIMA(1,1,3)(2,1,1)1212.8740.231
乙肝SARIMA(2,1,0)(0,1,2)128.8090.550
丙肝SARIMA(2,1,1)(0,1,2)129.4850.487
戊肝SARIMA(1,0,2)(0,1,1)124.6750.912
未分型肝炎SARIMA(2,1,2)(2,1,1)1217.0050.074
), ArticleFig(id=1241069120104484986, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, language=EN, label=Table 4, caption=

Comparison of modeling accuracy between GRNN and SARIMA models for viral hepatitis incidence

, figureFileSmall=null, figureFileBig=null, tableContent=
肝炎类型GRNNSARIMA
MAPE(%)MAERMSEMER(%)MAPE(%)MAERMSEMER(%)
病毒性肝炎1.800.150.211.843.840.310.463.86
甲肝21.220.030.0321.847.870.020.036.48
乙肝2.100.130.182.143.900.250.373.93
丙肝1.670.020.031.714.740.050.074.76
戊肝4.430.010.014.395.940.010.016.19
未分型肝炎11.430.010.0111.514.710.010.024.19
), ArticleFig(id=1241069120217731204, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, language=CN, label=表4, caption=

GRNN模型与SARIMA模型拟合效果比较

, figureFileSmall=null, figureFileBig=null, tableContent=
肝炎类型GRNNSARIMA
MAPE(%)MAERMSEMER(%)MAPE(%)MAERMSEMER(%)
病毒性肝炎1.800.150.211.843.840.310.463.86
甲肝21.220.030.0321.847.870.020.036.48
乙肝2.100.130.182.143.900.250.373.93
丙肝1.670.020.031.714.740.050.074.76
戊肝4.430.010.014.395.940.010.016.19
未分型肝炎11.430.010.0111.514.710.010.024.19
), ArticleFig(id=1241069120343560332, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, language=EN, label=Table 5, caption=

Comparison of the accuracy of viral hepatitis incidence forecasts using GRNN and SARIMA models

, figureFileSmall=null, figureFileBig=null, tableContent=
肝炎类型GRNNSARIMA
MAPE(%)MAERMSEMER(%)MAPE(%)MAERMSEMER(%)
病毒性肝炎2.910.210.232.942.540.190.212.58
甲肝17.170.020.0215.8748.890.050.0543.77
乙肝2.260.130.162.331.780.100.131.83
丙肝2.280.030.042.373.420.040.063.47
戊肝8.850.010.028.2411.880.020.0210.77
未分型肝炎8.410.010.018.263.270.000.003.19
), ArticleFig(id=1241069120456806545, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1241035820849746360, language=CN, label=表5, caption=

GRNN模型与SARIMA模型预测效果比较

, figureFileSmall=null, figureFileBig=null, tableContent=
肝炎类型GRNNSARIMA
MAPE(%)MAERMSEMER(%)MAPE(%)MAERMSEMER(%)
病毒性肝炎2.910.210.232.942.540.190.212.58
甲肝17.170.020.0215.8748.890.050.0543.77
乙肝2.260.130.162.331.780.100.131.83
丙肝2.280.030.042.373.420.040.063.47
戊肝8.850.010.028.2411.880.020.0210.77
未分型肝炎8.410.010.018.263.270.000.003.19
)], attaches=null, journal=Journal(id=1227664546253402114, delFlag=0, nameCn=现代预防医学, nameEn=Modern Preventive Medicine, nameHistory1=null, nameHistory2=null, issn=1003-8507, eissn=null, cn=51-1365/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=IeiuPXEZi6AA+k0VfvoiOQ==, journalPrice=null, startedYear=null, abbrevIsoEn=Modern Preventive Medicine, journalRemark=null, publicationField=null, createdTime=1770627636734, updatedTime=1770628902248, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=M, firstLetterEn=M, subjectCode=Life Sciences, subjectName=null, subjectCodeEn=Life Sciences, subjectNameEn=null, picCn=IeiuPXEZi6AA+k0VfvoiOQ==, picEn=/9iTl8/ndms4tBz1fL28Pg==, jcr=null, cjcr=null, exts=[JournalExt(id=1227669854342280188, language=CN, name=现代预防医学, 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=1770628902278, updatedTime=1770628902278, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://xdyfyxzz.paperopen.com/#/regist, submissionEditorUrl=http://xdyfyxzz.paperopen.com/#/Login, submissionReviewUrl=http://xdyfyxzz.paperopen.com/#/Login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1227669854396806141, language=EN, name=Modern Preventive Medicine, 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=1770628902291, updatedTime=1770628902291, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://xdyfyxzz.paperopen.com/#/regist, submissionEditorUrl=http://xdyfyxzz.paperopen.com/#/Login, submissionReviewUrl=http://xdyfyxzz.paperopen.com/#/Login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1227665162245664772, websiteList=[Website(id=1227687234141352800, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1227665162245664772, 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/xdyfyx/CN, language=CN, createTime=1770633045945, createBy=18614031015, updateTime=1770633090526, updateBy=18614031015, name=现代预防医学-中文, tplId=1146099689490845704, title=现代预防医学, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1227687735088051072, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=articleTextType, value=kx, createTime=1770633165380, updateTime=1770633165380, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735071273853, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=banner, value=null, createTime=1770633165376, updateTime=1770633165376, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735113216899, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=grayFlag, value=0, createTime=1770633165386, updateTime=1770633165386, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735062885244, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=logo, value=https://castjournals.cast.org.cn/joweb/xdyfyx/CN/file/pic?fileId=/XB5plC0xuykmQnycvtyrw==, createTime=1770633165374, updateTime=1770633165374, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735125799813, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=minRunFlag, value=0, createTime=1770633165389, updateTime=1770633165389, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735083856767, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/xdyfyx/CN/file/pic, createTime=1770633165379, updateTime=1770633165379, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735121605508, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=silenceFlag, value=0, createTime=1770633165388, updateTime=1770633165388, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735079662462, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1770633165378, updateTime=1770633165378, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735096439681, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=themeColor, value=null, createTime=1770633165382, updateTime=1770633165382, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735104828290, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=themeStyle, value=null, createTime=1770633165384, updateTime=1770633165384, creator=18614031015, updator=18614031015)]), Website(id=1227687234338485094, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1227665162245664772, 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/xdyfyx/EN, language=EN, createTime=1770633045992, createBy=18614031015, updateTime=1770633115374, updateBy=18614031015, name=现代预防医学-英文, tplId=1146101810881728533, title=Modern Preventive Medicine, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1227687709129507332, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=articleTextType, value=kx, createTime=1770633159191, updateTime=1770633159191, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709108535809, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=banner, value=null, createTime=1770633159186, updateTime=1770633159186, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709167256071, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=grayFlag, value=0, createTime=1770633159200, updateTime=1770633159200, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709095952896, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=logo, value=https://castjournals.cast.org.cn/joweb/xdyfyx/EN/file/pic?fileId=/XB5plC0xuykmQnycvtyrw==, createTime=1770633159183, updateTime=1770633159183, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709179838985, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=minRunFlag, value=0, createTime=1770633159203, updateTime=1770633159203, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709121118723, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/xdyfyx/EN/file/pic, createTime=1770633159189, updateTime=1770633159189, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709171450376, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=silenceFlag, value=0, createTime=1770633159201, updateTime=1770633159201, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709112730114, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1770633159187, updateTime=1770633159187, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709133701637, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=themeColor, value=null, createTime=1770633159192, updateTime=1770633159192, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709154673158, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=themeStyle, value=null, createTime=1770633159197, updateTime=1770633159197, creator=18614031015, updator=18614031015)])], journalTitle=现代预防医学, weixinUrl=null, journalUrl=http://xdyfyxzz.paperopen.com/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Modern Preventive Medicine, journalPhotoCn=IeiuPXEZi6AA+k0VfvoiOQ==, journalPhotoEn=/9iTl8/ndms4tBz1fL28Pg==, journalFirstLetter=M, 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), detailUrlCn=https://castjournals.cast.org.cn/joweb/xdyfyx/CN/10.20043/j.cnki.MPM.202406385, detailUrlEn=https://castjournals.cast.org.cn/joweb/xdyfyx/EN/10.20043/j.cnki.MPM.202406385, pdfUrlCn=https://castjournals.cast.org.cn/joweb/xdyfyx/CN/PDF/10.20043/j.cnki.MPM.202406385, pdfUrlEn=https://castjournals.cast.org.cn/joweb/xdyfyx/EN/PDF/10.20043/j.cnki.MPM.202406385, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
时间序列广义回归神经网络模型在病毒性肝炎发病率预测中的应用
收藏切换
PDF下载
孙亚军 1, 3 , 刘天 2 , 姚远 3
现代预防医学 | 流行病与统计方法 2024,51(23): 4260-4265
收起
收藏切换
现代预防医学 | 流行病与统计方法 2024, 51(23): 4260-4265
时间序列广义回归神经网络模型在病毒性肝炎发病率预测中的应用
全屏
孙亚军1, 3, 刘天2, 姚远3
作者信息
  • 1.珠海市第三人民医院,广东 珠海 519000
  • 2.荆州市疾病预防控制中心
  • 3.重庆市九龙坡区疾病预防控制中心,重庆 400050
  • 孙亚军(1978—),男,硕士,主任医师,研究方向:疾病监测与数据分析

通讯作者:

姚远,E-mail:
Application of time series generalized regression neural network model in predicting the incidence of viral hepatitis
Ya-jun SUN1, 3, Tian LIU2, Yuan YAO3
Affiliations
  • The Third People’s Hospital of Zhuhai, Zhuhai, Guangdong 519000, China
出版时间: 2024-12-10 doi: 10.20043/j.cnki.MPM.202406385
文章导航
收藏切换
目的

本研究旨在介绍基于时间序列广义回归神经网络(generalized regression neural network, GRNN)模型在中国病毒性肝炎发病率预测中的应用,评估其拟合及预测精度。

方法

收集全国2004—2019年病毒性肝炎逐月发病率数据构建时间序列,以2004年1月—2019年6月数据为训练数据,2019年7—12月数据为测试数据,分别建立GRNN和SARIMA模型,预测2019年7—12月发病率并与测试数据比较。采用平均绝对百分比误差(MAPE)评价模型拟合及预测效果。

结果

GRNN模型对各类肝炎的拟合MAPE在1.67%~21.22%之间,预测MAPE在2.26%~17.17%之间。与之相比,SARIMA模型对各类肝炎的拟合MAPE在3.84%~7.87%之间,预测MAPE在2.54%~48.89%之间,其中甲肝的预测MAPE为48.89%,显示出较大的预测误差。

结论

GRNN模型在我国病毒性肝炎月发病率预测中表现优于SARIMA模型,适合推广应用。

GRNN  /  SARIMA  /  预测  /  病毒性肝炎  /  时间序列
Objective

To introduce the application of the time series generalized regression neural network (GRNN) model in predicting the incidence of viral hepatitis in China and to evaluate its fitting and predictive accuracy.

Methods

Monthly incidence data of viral hepatitis from 2004 to 2019 were collected to construct time series. Data from January 2004 to June 2019 were used as training data, while data from July to December 2019 served as testing data. Both GRNN and SARIMA models were established to predict the incidence from July to December 2019, and the predictions were compared with the testing data. The mean absolute percentage error (MAPE) was employed to assess the model’s fitting and predictive performance.

Results

The fitting MAPE for the GRNN model across various types of hepatitis ranged from 1.67% to 21.22%, while the predictive MAPE ranged from 2.26% to 17.17%. In comparison, the SARIMA model’s fitting MAPE for various types of hepatitis ranged from 3.84% to 7.87%, with a predictive MAPE ranging from 2.54% to 48.89%. Notably, the predictive MAPE for hepatitis A was 48.89%, indicating a significant prediction error.

Conclusion

The GRNN model outperformed the SARIMA model in predicting the monthly incidence of viral hepatitis in China, suggesting its suitability for broader application.

GRNN  /  SARIMA  /  Prediction  /  Viral hepatitis  /  Time series
孙亚军, 刘天, 姚远. 时间序列广义回归神经网络模型在病毒性肝炎发病率预测中的应用. 现代预防医学, 2024 , 51 (23) : 4260 -4265 . DOI: 10.20043/j.cnki.MPM.202406385
Ya-jun SUN, Tian LIU, Yuan YAO. Application of time series generalized regression neural network model in predicting the incidence of viral hepatitis[J]. Modern Preventive Medicine, 2024 , 51 (23) : 4260 -4265 . DOI: 10.20043/j.cnki.MPM.202406385
病毒性肝炎(hepatitis virus)是我国法定报告乙类传染病的一组疾病的统称,包括甲型病毒性肝炎(简称甲肝),乙型病毒性肝炎(简称乙肝)、丙型病毒性肝炎(简称丙肝)、戊型病毒性肝炎(简称戊肝)和未分型病毒性肝炎(简称未分型肝炎)5种亚型[1]。病毒性肝炎是全球数百万慢性感染和死亡的罪魁祸首,对公共卫生仍构成重大威胁,其流行病学变化对社会和卫生服务提供有重要影响[2]。因此,准确预测肝炎发病率对于识别其流行趋势、早期预防和更好地制定政府战略规划至关重要[3]。目前,季节性自回归积分滑动平均模型(seasonal autoregressive integrated moving average, SARIMA)和神经网络模型被广泛应用于疾病发病率预测[3-7]。作为基于径向基函数网络的神经网络模型,广义回归神经网络(generalized regression neural network, GRNN)模型相比SARIMA模型,在处理复杂非线性关系、数据适应性方面具有显著优势,且预测精度高、训练快速、易于实现[5,8-9]。2019年,Francisco等人[10]基于R语言和GRNN神经网络,开发了用于时间序列预测的tsfgrnn包。目前,国内基于单一GRNN模型预测我国传染病发病率的报道较少[11]。本文利用2004—2019年全国逐月病毒性肝炎发病率数据,探讨基于R语言GRNN模型在病毒性肝炎发病率预测中的应用,并与SARIMA模型(R语言自动化建模)比较,以评估两种模型的拟合和预测效果,为GRNN模型在传染病日常监测预测预警中的应用和推广提供参考。
2004—2019年全国病毒性肝炎数据来源于公共卫生科学数据中心(http://www.phsciencedata.cn/),获取病毒性肝炎及各亚型逐月发病率数据。以2004年1月—2019年6月数据拟合模型,并预测2019年7—12月发病率。
GRNN作为径向基(radial basis function, RBF)神经网络的一种变体,具有快速、单遍学习的特点[10]。GRNN具有3层,包括输入层、隐含层和输出层[12]。隐含层是径向基层,基函数通常采用高斯函数:,其中x为输入向量,xi为训练样本,σ为平滑参数。GRNN模型先通过隐含层产生一组权重wi(总和为1,代表每个训练样本对最终结果的贡献),再通过输出层计算训练样本目标值yi的加权平均值,作为GRNN输出向量。在GRNN模型中,平滑参数σ是一个关键参数,它控制着在计算时各个训练样本目标值的重要性。当σ较大时,所有训练样本目标值权重相似,导致模型结果趋于所有训练样本目标值的平均值;当σ较小时,最接近输入向量的训练样本目标值有显著的权重,使模型结果更倾向于这些样本的目标值[10,13]
R语言中通过tsfgrnn包grnn_forecasting函数对时间序列数据建立GRNN模型,自回归滞后期(lags)、平滑参数(sigma)、多步向前预测策略(msas)、训练样本转换(transform)等是建模的关键设置[10]。(1)自回归滞后期。该参数用于创建训练样本的输入向量,可手动设置,也可使用自动选择功能。自动选择基于以下标准进行。滞后期为1∶f,其中f为时间序列的周期数。例如,季度数据的滞后期为1∶4,月度数据的滞后期为1∶12。对于周期数为1的时间序列(如年度数据),选择偏自相关函数(partial autocorrelation function, PACF)中具有显著自相关性的滞后期。如果没有滞后期具有显著的自相关性,则选择滞后期为1:5。(2)平滑参数sigma选取。如前所述,GRNN对平滑参数非常敏感,因此为它选择合适的值至关重要。为了做出更好的选择,Francisco[12]开发了滚动原点技术(rolling origin technique)探寻最优参数sigma。该方法将历史数据分为训练数据和验证数据,逐步滚动进行预测,通过最小化平均绝对百分比误差(mean absolute percentage error,MAPE)来选择sigma,从而使预测值与验证数据的误差最小。(3)多步向前预测策略。GRNN预测策略包括多输入多输出策略(multiple-input multiple-output, MIMO)和递归策略(recursive),Francisco等[12]证实递归策略效果更好且速度更快,故参数默认设置为recursive。(4)训练样本变换。如果时间序列数据具有趋势,则建议使用。该参数默认设置为加性变换(additive),适用于线性趋势的数据,对于指数性趋势的数据应设为乘法变换(multiplicative),对于没有明显趋势的数据,则设为不变换(none)。
SARIMA模型是ARIMA模型的扩展,是经典的时间序列模型之一,专门用于处理具有季节性波动的时间序列数据,SARIMA模型结合了ARIMA模型和季节性成分,能够更好地捕捉和预测数据中的季节性模式,在疾病预测领域得到了广泛应用。SARIMA原理见参考文献[14]。在本研究中,利用R语言“forecast”包中auto.arima( )函数建立SARIMA模型[15]。该函数能够自动选择最优的模型参数,包括自回归阶数(p)、差分次数(d)、滑动平均阶数(q)以及对应的季节性参数(P、D、Q)。其模型选择步骤如下:首先,选择差分次数d和D。通过差分使序列平稳,再通过单位根检验(默认为KPSS检验,也可指定使用ADF 或 PP 检验)选择合适的d和D ;其次,选择AR和MA阶数。通过评估不同的p、q、P、Q组合,基于最小化信息准则(默认为修正的赤池信息准则AICc,也可指定使用AIC或BIC)选择最优组合;最后,对模型残差进行白噪声检验(Ljung-Box检验)以确保模型的适用性。
基于R语言“tidyverse”“forecast”“tsfgrnn”扩展包进行数据预处理、模型建立和模型预测。利用ts( )函数将原始数据转化为时间序列格式,采用decompose( )函数分解时间序列,并提取季节指数,该函数首先使用移动平均方法提取时间序列的趋势(trend)成分,再通过计算实际数据和趋势成分之间的差异,来识别和提取季节性成分(seasonal),最后通过将原始数据减去趋势和季节性成分,得到不规则成分(irregular);采用auto.arima( )函数自动识别并建立SARIMA模型,使用forecast( )函数对未来的数据进行预测;通过grnn_forecasting( )函数建立GRNN模型并进行预测。应用checkresiduals( )函数进行Ljung-Box检验,以评估模型残差的自相关性,确保模型的适用性。模型拟合及预测效果评价采用平均绝对百分比误差 (MAPE)、平均绝对误差(mean absolute error, MAE)、均方根误差(root mean squared error, RMSE)和平均误差率(mean error rate, MER)4个指标。使用平均年度变化百分比(average annual percent change,AAPC)描述全国病毒性肝炎及各亚型发病率变化,采用joinpoint回归模型分析发病率时间趋势。所有检验均为双侧检验,检验水准为0.05。
2004—2019年全国累积报告病毒性肝炎20 777 873例,年均发病率为96.63/10万。其中乙肝报告发病率最高,为76.96/10万,戊肝发病率最低,为1.80/10万。2004—2019年全国病毒性肝炎和乙肝的发病率总体上无显著变化,AAPC分别为0.4%(95%CI: -0.9%~1.7%)和0.3%(95%CI: -1.1%~1.7%)。其中,2004—2007年两者发病率均显著上升,AAPC分别为8.0%(95%CI: 2.6%~13.6%)和9.4%(95%CI: 3.6%~15.6%);而在2007—2015年,两者发病率均显著下降,AAPC分别为-2.5%(95%CI: -3.8%~-1.2%)和-3.6%(95%CI: -5.0%~-2.2%)。丙肝和戊肝的发病率总体呈上升趋势,AAPC分别为11.6%(95%CI: 10.9%~12.3%)和3.6%(95%CI: 1.9%~5.3%);其中,2004—2012年两种肝炎的发病率快速增长,2012年后增长速度放缓。甲肝和未分型肝炎的发病率总体呈下降趋势,AAPC分别为-11.4%(95%CI: -13.7%~-9.0%)和-12.0%(95%CI: -12.8%~-11.1%);其中,2012—2019年甲肝的下降趋势减缓;而未分型肝炎在2014—2019年呈加速下降趋势。分季节来看,病毒性肝炎、乙肝有明显的季节性;甲肝、丙肝、戊肝和未分型肝炎季节性不明显。见表1图12
病毒性肝炎发病率数据为月度数据,根据GRNN模型输入向量数据选取规则,选取滞后期1:12作为输入,sigma参数设为"ROLLING",多步预测法选择递归法(“recursive”),控制趋势选择加性变换(“additive”),预测2019年7—12月发病率。通过滚动原点(“rolling origin”)评估方法来评估模型拟合的准确性。拟合的最优模型参数及拟合的平均绝对百分比误差MAPE,见表2
利用“forecast”包中的auto.arima( )函数自动建模,建模结果及残差自相关检验结果见表3。病毒性肝炎、甲肝、乙肝、丙肝、戊肝的最优模型残差均为白噪声,序列信息提取完全,模型可以用于预测;未分类肝炎的最优模型残差可能存在轻微的自相关性,模型可以用于短期预测,但需关注预测误差。
MAPE、MAE、RMSE、MER分别介于1.67%~21.22%、0.01~0.15、0.01~0.21、1.71%~21.84%,而SARIMA模型分别介于3.84~7.87、0.01~0.31、0.01~0.46、3.86%~6.48%,GRNN模型拟合误差波动幅度总体高于SARIMA模型,见表4。GRNN模型的预测MAPE、MAE、RMSE、MER分别介于2.26~17.17、0.01~0.21、0.01~0.23、2.33%~15.87%,而SARIMA模型分别介于1.78%~48.89%、0~0.19、0~0.21、1.83%~43.77%,GRNN模型的预测误差波动幅度总体小于SARIMA模型,见表5。一般而言,模型的预测MAPE在0~10%之间表示高预测精度,10%~20%之间表示良好预测精度[16]。GRNN模型对于病毒性肝炎及各亚型预测的MAPE均在20%以内,显示出良好的预测精度。
本文基于R语言tsfgrnn包介绍GRNN模型在病毒性肝炎及其亚型发病率预测中的应用。研究结果表明,GRNN模型具有较高的预测精度;与SARIMA模型相比,GRNN模型预测病毒性肝炎及其亚型发病率更为稳健,这与既往同类研究结果相似[9,17-18]。Francisco等曾比较GRNN模型与指数平滑模型、自动化SARIMA模型、K近邻时间序列预测模型、神经网络自回归模型和多层感知器模型的预测效果,结果显示GRNN模型优于K近邻时间序列预测模型、神经网络自回归模型、多层感知器模型,但略逊于指数平滑模型、自动化SARIMA模型[10]。然而,中国学者研究显示,在肾综合征出血热和新型冠状病毒肺炎发病率预测中,GRNN模型预测误差远高于SARIMA模型[19-20]
本研究中,就预测误差MAPE而言,GRNN模型预测病毒性肝炎、乙肝、未分型肝炎发病率误差均高于SARIMA模型,但对于其他三种亚型的肝炎,情况刚好相反。这种以SARIMA模型相比较的GRNN模型发病率预测误差高低不一的原因,可能与GRNN模型过拟合、不同的疾病特征、地区与监测方法差异、数据自身特性及模型适用性有关[18,20]。研究表明,GRNN模型在捕捉非线性关系时表现优越,而SARIMA模型在处理线性和季节性数据时更为有效[17,21]。有学者利用两者优势,发展出SARIMA-GRNN组合模型,其发病率预测效果优于单一的SARIMA模型[22-23]。基于R语言的SARIMA-GRNN组合自动化模型对病毒性肝炎及其亚型发病率的预测效果如何,尚有待于后续进一步研究。
作为人工神经网络家族的一员,GRNN模型本质上也是一种“黑箱”技术,因此,该模型依然存在专业解释性差的问题[24]。然而,与既往研究中神经网络预测涉及大量参数,缺乏系统化建模流程和策略不同[25],基于R语言tsfgrnn包的GRNN模型已经以自动化方式整合了最佳建模方法和训练样本转换策略[12]。因此,相比SARIMA模型,本文介绍的GRNN模型具有以下优点[5,8,12]:(1)非线性关系的捕捉:GRNN模型能更好地捕捉时间序列中的非线性关系。(2)建模快速与易用性:GRNN 模型通过单次训练并仅需调整一个平滑参数来实现快速建模,并且不需要传统的统计建模经验。此外,tsfgrnn包提供了自动选择最优参数的功能,使其在快速自动化预测中更加便捷。尽管forecast包提供了自动选择SARIMA模型参数的功能,但这些参数仍需通过统计检验才能最终确定,因此SARIMA模型的自动化流程通常仍需专家指导。(3)稳健性与适应性:GRNN模型通过平滑参数调整和训练样本转换来适应不同的数据模式,从而在变化的数据环境中保持较高的预测精度和灵活性。
综上所述,GRNN为一种无需统计建模经验、操作简单、功能强大的时间序列预测模型,对传染病发病率时间序列的预测效果较好,值得进一步推广应用。本研究也存在一定的局限性[17,20,26-27]:一是,未能对更密集的日、周数据及不同流行季节数据进行预测效果分析;二是,模型仅考虑时间因素, 属于单因素模型,无法加入其它疾病影响因素,如气候、重大事件等,与复杂的病毒性肝炎流行可能不相适应。
  • 重庆市公共卫生重点专科(学科)建设项目(YWBF2023081)
参考文献 引证文献
排序方式:
[1]
Usuda D, Kaneoka Y, Ono R, et al. Current perspectives of viral hepatitis[J]. World Journal of Gastroenterology, 2024, 30(18): 2402-2417.
[2]
Black AP, Wallace J, Binka M, et al. Correction: the challenges of viral hepatitis elimination: a global response to a global problem[J].BMC Public Health, 2023, 23(1): 1229.
[3]
Xia ZH, Qin L, Ning Z, et al. Deep learning time series prediction models in surveillance data of hepatitis incidence in China[J]. PLOS One, 2022, 17(4): e0265660.
[4]
Zhai MM, Li WH, Tie P, et al. Research on the predictive effect of a combined model of ARIMA and neural networks on human brucellosis in Shanxi Province, China: a time series predictive analysis[J]. BMC Infectious Diseases, 2021, 21(1): 280.
[5]
Li ZQ, Wang ZZ, Song H, et al. Application of a hybrid model in predicting the incidence of tuberculosis in a Chinese population[J].Infection and Drug Resistance, 2019, 12: 1011-1020.
[6]
Feng Y, Cui X, Lv J, et al. Deep learning models for hepatitis E incidence prediction leveraging meteorological factors[J]. PLOS One,2023, 18(3): e0282928.
[7]
Mollalo A, Rivera KM, Vahedi B. Artificial neural network modeling of novel coronavirus (COVID-19) incidence rates across the continental United States[J]. International Journal of Environmental Research and Public Health, 2020, 17(12): 4204.
[8]
Zhu XX, Zheng YM, Zheng YL, et al. Application of generalized regression neural network and sarima model in prediction of AIDS[EB/OL]. [2024-10-20]. https://ieeexplore.ieee.org/document/9988161.
[9]
冯佳宁,肖宇飞,王晓璇,等.ARIMA乘积季节模型与GRNN模型在猩红热发病预测中的比较[J].中国卫生统计202037(6):851-854.
Feng JN, Xiao YF, Wang XX, et al. A comparative study of multiplicative seasonal ARIMA model and GRNN for scarlet fever incidence forecasting[J]. Chinese Journal of Health Statistics, 2020, 37(6): 851-854.(In Chinese)
[10]
Martínez F, Charte F, Rivera AJ, et al. Automatic time series forecasting with GRNN: A comparison with other models[EB/OL].[2024-10-20]. https://link.springer.com/chapter/10.1007/978-3-030-20521-8_17.
[11]
李于于,曾令城,柳巍.遗传优化的广义回归神经网络在肺结核发病预测中的应用[J].现代预防医学202047(21):3863-3866, 3923.
Li YY, Zeng LC, Liu W. Application of genetic-optimized generalized regression neural network in the prediction of tuberculosis[J]. Modern Preventive Medicine, 2020, 47(21): 3863-3866, 3923.(In Chinese)
[12]
Martínez F, Charte F, Frías MP, et al. Strategies for time series forecasting with generalized regression neural networks[J].Neurocomputing, 2022, 491: 509-521.
[13]
汪宗正.基于广义回归神经网络的动态光散射粒度反演研究[D].淄博:山东理工大学,2023.
Wang ZZ. Study on particle size distribution inversion of dynamic light scattering based on generalized regression neural network[D]. Zibo:Shandong University of Technology, 2023.(In Chinese)
[14]
Box G, Jenkins GM, Reinsel GC, et al. Time series analysis: forecasting and control(5th ed.)[M]. New Jersey: John Wiley&Sons, 2015.
[15]
Hyndman R, Athanasopoulos G, Bergmeir C, et al. 2024. Forecast: forecasting functions for time series and linear models[EB/OL]. [2024-10-20]. https://pkg.robjhyndman.com/forecast/.
[16]
Dun M, Xu ZC, Chen Y, et al.Short-term air quality prediction based on fractional grey linear regression and support vector machine[J]. Mathematical Problems in Engineering, 2020, 249: 1-13.
[17]
Wei WD, Jiang JJ, Liang H, et al. Application of a combined model with autoregressive integrated moving average (ARIMA) and generalized regression neural network (GRNN) in forecasting hepatitis incidence in Heng county, China[J]. PLOS One, 2016, 11(6):e0156768.
[18]
Wang YW, Shen ZZ, Jiang Y.Comparison of autoregressive integrated moving average model and generalised regression neural network model for prediction of haemorrhagic fever with renal syndrome in China: a time-series study[J]. BMJ Open, 2019, 9(6):e025773.
[19]
刘天,姚梦雷,侯清波,等.7种时间序列模型对全国肾综合征出血热发病率预测效果比较[J].中国媒介生物学及控制杂志202233(4):548-554.
Liu T, Yao ML, Hou QB, et al. Comparison of seven time series models in fitting and predicting the incidence of hemorrhagic fever with renal syndrome in China[J]. Chinese Journal of Vector Biology and Control,2022, 33(4): 548-554.(In Chinese)
[20]
Wang G, Wu T, Wei W, et al. Comparison of ARIMA, ES, GRNN and ARIMA-GRNN hybrid models to forecast the second wave of COVID-19 in India and the United States[J]. Epidemiology and Infection, 2021, 149: e240.
[21]
Guo YH, Feng Y, Qu FL, et al. Prediction of hepatitis E using machine learning models[J]. PLOS One, 2020, 15(9): e0237750.
[22]
李峰,陈国清,徐士林,等.三种时间序列模型在盐城市肾综合征出血热发病预测应用中的比较研究[J].中国卫生统计202037(2):249-252.
Li F, Chen GQ, Xu SL, et al. Comparative analysis of three time series models for predicting hemorrhagic fever with renal syndrome incidence in Yancheng City[J]. Chinese Journal of Health Statistics, 2020, 37(2): 249-252.(In Chinese)
[23]
李文豪,曾昱兴,李笑颜,等.SARIMA-GRNN组合模型在伤寒与副伤寒逐月发病数预测中的应用[J].中华疾病控制杂志202125(11):1341-1346.
Li WH, Zeng YX, Li XY, et al. Application of SARIMA-GRNN combined model in forecasting the monthly incidence of typhoid fever and paratyphoid fever[J]. Chinese Journal of Disease Control & Prevention,2021, 25(11): 1341-1346.(In Chinese)
[24]
Burkart N, Huber MF. A survey on the explainability of supervised machine learning[J]. Journal of Artificial Intelligence Research, 2021, 70: 245-317.
[25]
Du XP, Xu HY, Zhu F. Understanding the effect of hyperparameter optimization on machine learning models for structure design problems[J]. Computer Aided Design, 2021, 135: 103013.
[26]
Yan D, Kong Y, Ye B, et al. Spatio-temporal variation and daily prediction of PM2.5 concentration in world-class urban agglomerations of China[J]. Environmental Geochemistry and Health,2021, 43(1): 301-316.
[27]
Wang L, Xia Y, Lu YC. A novel forecasting approach by the GA-SVR-GRNN hybrid deep learning algorithm for oil future prices[J].Computational Intelligence and Neuroscience, 2022(1): 4952215.
2024年第51卷第23期
PDF下载
71
31
引用本文
BibTeX
文章信息
doi: 10.20043/j.cnki.MPM.202406385
  • 接收时间:2024-06-22
  • 首发时间:2026-03-18
  • 出版时间:2024-12-10
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-06-22
基金
重庆市公共卫生重点专科(学科)建设项目(YWBF2023081)
作者信息
    1.珠海市第三人民医院,广东 珠海 519000
    2.荆州市疾病预防控制中心
    3.重庆市九龙坡区疾病预防控制中心,重庆 400050

通讯作者:

姚远,E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/xdyfyx/CN/10.20043/j.cnki.MPM.202406385
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