Article(id=1149780470608655200, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149780466032669506, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2403340, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1715011200000, receivedDateStr=2024-05-07, revisedDate=1735747200000, revisedDateStr=2025-01-02, acceptedDate=null, acceptedDateStr=null, onlineDate=1752058626080, onlineDateStr=2025-07-09, pubDate=1744041600000, pubDateStr=2025-04-08, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1752058626080, onlineIssueDateStr=2025-07-09, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1752058626080, creator=13701087609, updateTime=1752058626080, updator=13701087609, issue=Issue{id=1149780466032669506, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='10', pageStart='3969', pageEnd='4395', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1752058624990, creator=13701087609, updateTime=1768456644259, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1218558743898411553, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149780466032669506, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1218558743898411554, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149780466032669506, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=4355, endPage=4360, ext={EN=ArticleExt(id=1149780470860313443, articleId=1149780470608655200, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Prediction of Traffic Accident Severity Based on Integrated Models, columnId=1156262728772735295, journalTitle=Science Technology and Engineering, columnName=Papers·Traffics and Transportations, runingTitle=null, highlight=null, articleAbstract=

Traffic accidents pose significant risks to public safety and represent a critical issue in transportation systems. The accurate prediction of accident severity is essential for implementing effective prevention and intervention measures. An ensemble learning approach, combining the advanced algorithms XGBoost and MLP, was proposed to enhance the accuracy of traffic accident severity predictions. A stacked classifier was established and its performance in traffic accident prediction was thoroughly evaluated. The experimental results demonstrate that the integrated model significantly improves prediction accuracy compared to the traditional XGBoost model, with a notable 20.41% increase in the macro-average F1 score. The advantages and innovations of the model, including model integration and network transformation, were highlighted. Additionally, the key features affecting the prediction results were analyzed, and the model's potential value in practical applications was explored. This study provides more scientific and efficient decision support for traffic safety management and is expected to play a crucial role in fields such as traffic management and intelligent driving.

, correspAuthors=Yan-min ZHANG, 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=Han-kun YANG, Shuai LU, Wen-jie QIN, Yan-min ZHANG), CN=ArticleExt(id=1149780498475610324, articleId=1149780470608655200, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=基于集成模型的交通事故严重程度预测, columnId=1156262730664366426, journalTitle=科学技术与工程, columnName=论文·交通运输, runingTitle=null, highlight=null, articleAbstract=

交通事故对公共安全构成重大风险,是交通运输系统中的重要问题。准确预测事故严重程度对于采取有效的预防和干预措施至关重要。提出了一种基于集成学习的方法,将XGBoost和MLP两种先进算法相结合,以更精准地预测交通事故的严重程度。建立了一个堆叠分类器,并详细评估了其在交通事故预测中的性能。实验结果表明,该集成模型相较于传统XGBoost模型,在预测准确性上有明显提升,在宏平均F1分数上显著提高了20.41%。展示了模型优势与创新性,包括模型集成与网络改造。此外,还分析了影响预测结果的关键特征,并探讨了模型在实际应用中的潜在价值。该研究为交通安全管理提供了更科学、更高效的决策支持,有望在交通管理、智能驾驶等领域发挥重要作用。

, correspAuthors=张彦敏, authorNote=null, correspAuthorsNote=
* 张彦敏(1980—),男,汉族,山东泰安人,博士,高级工程师。研究方向:水声工程。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=ogeMDpwGe1VKzrZCzGwU7w==, magXml=ZQ942NKHniB0p5gfx1seUg==, pdfUrl=null, pdf=VWiyZZKJBPbqYINMTt6vFg==, pdfFileSize=5990464, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=g8X3547m7g9OcAFylpR4+Q==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=CR2I4YatfaLYEwch8VnqNA==, mapNumber=null, authorCompany=null, fund=null, authors=

杨翰琨(2001—),男,汉族,安徽滁州人,硕士研究生。研究方向:深度学习。E-mail:

, authorsList=杨翰琨, 鲁帅, 秦文杰, 张彦敏)}, authors=[Author(id=1218525107404849566, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=yanghankun@hrbeu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1218525107505512881, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, authorId=1218525107404849566, language=EN, stringName=Han-kun YANG, firstName=Han-kun, middleName=null, lastName=YANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Harbin Engineering University, Yantai Graduate School, Yantai 265500, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1218525107681673663, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, authorId=1218525107404849566, language=CN, stringName=杨翰琨, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 哈尔滨工程大学烟台研究生院, 烟台 265500, bio={"content":"

杨翰琨(2001—),男,汉族,安徽滁州人,硕士研究生。研究方向:深度学习。E-mail:

"}, bioImg=null, bioContent=

杨翰琨(2001—),男,汉族,安徽滁州人,硕士研究生。研究方向:深度学习。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1218525107098665337, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, xref=1, ext=[AuthorCompanyExt(id=1218525107111248251, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, companyId=1218525107098665337, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Harbin Engineering University, Yantai Graduate School, Yantai 265500, China), AuthorCompanyExt(id=1218525107161579903, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, companyId=1218525107098665337, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 哈尔滨工程大学烟台研究生院, 烟台 265500)])]), Author(id=1218525107790725578, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, 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=1218525107920749015, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, authorId=1218525107790725578, language=EN, stringName=Shuai LU, firstName=Shuai, middleName=null, lastName=LU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Harbin Engineering University, Yantai Graduate School, Yantai 265500, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1218525108033995238, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, authorId=1218525107790725578, language=CN, stringName=鲁帅, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 哈尔滨工程大学烟台研究生院, 烟台 265500, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1218525107098665337, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, xref=1, ext=[AuthorCompanyExt(id=1218525107111248251, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, companyId=1218525107098665337, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Harbin Engineering University, Yantai Graduate School, Yantai 265500, China), AuthorCompanyExt(id=1218525107161579903, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, companyId=1218525107098665337, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 哈尔滨工程大学烟台研究生院, 烟台 265500)])]), Author(id=1218525108184990198, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, orderNo=2, 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=1218525108323402243, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, authorId=1218525108184990198, language=EN, stringName=Wen-jie QIN, firstName=Wen-jie, middleName=null, lastName=QIN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Harbin Engineering University, Yantai Graduate School, Yantai 265500, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1218525108428259855, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, authorId=1218525108184990198, language=CN, stringName=秦文杰, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 哈尔滨工程大学烟台研究生院, 烟台 265500, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1218525107098665337, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, xref=1, ext=[AuthorCompanyExt(id=1218525107111248251, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, companyId=1218525107098665337, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Harbin Engineering University, Yantai Graduate School, Yantai 265500, China), AuthorCompanyExt(id=1218525107161579903, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, companyId=1218525107098665337, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 哈尔滨工程大学烟台研究生院, 烟台 265500)])]), Author(id=1218525108562477596, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wangenda@163.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1218525108671529517, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, authorId=1218525108562477596, language=EN, stringName=Yan-min ZHANG, firstName=Yan-min, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, *, address=2 Hubei Key Laboratory of Marine Electromagnetic Detection and Control, Wuhan Second Ship Design and Research Institute, Wuhan 430064, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1218525108814135863, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, authorId=1218525108562477596, language=CN, stringName=张彦敏, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, *, address=2 武汉第二船舶设计研究所海洋电磁探测与控制湖北省重点实验室, 武汉 430064, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1218525107274826125, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, xref=2, ext=[AuthorCompanyExt(id=1218525107279020430, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, companyId=1218525107274826125, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Hubei Key Laboratory of Marine Electromagnetic Detection and Control, Wuhan Second Ship Design and Research Institute, Wuhan 430064, China), AuthorCompanyExt(id=1218525107287409041, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, companyId=1218525107274826125, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 武汉第二船舶设计研究所海洋电磁探测与控制湖北省重点实验室, 武汉 430064)])])], keywords=[Keyword(id=1218525109078377040, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, language=EN, orderNo=1, keyword=traffic accidents), Keyword(id=1218525109187428959, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, language=EN, orderNo=2, keyword=severity prediction), Keyword(id=1218525109309063787, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, language=EN, orderNo=3, keyword=XGBoost), Keyword(id=1218525109418115702, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, language=EN, orderNo=4, keyword=MLP), Keyword(id=1218525109560722051, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, language=EN, orderNo=5, keyword=feature analysis), Keyword(id=1218525109648802443, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, language=EN, orderNo=6, keyword=ensemble learning), Keyword(id=1218525109741077143, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, language=EN, orderNo=7, keyword=deep learning), Keyword(id=1218525109850129062, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, language=CN, orderNo=1, keyword=交通事故), Keyword(id=1218525109963375278, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, language=CN, orderNo=2, keyword=严重程度预测), Keyword(id=1218525110097593022, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, language=CN, orderNo=3, keyword=XGBoost), Keyword(id=1218525110236005065, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, language=CN, orderNo=4, keyword=MLP), Keyword(id=1218525110374417114, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, language=CN, orderNo=5, keyword=特征分析), Keyword(id=1218525110487663327, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, language=CN, orderNo=6, keyword=集成学习), Keyword(id=1218525110630269675, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, language=CN, orderNo=7, keyword=深度学习)], refs=[Reference(id=1218525113461425081, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, doi=null, pmid=null, pmcid=null, year=2024, volume=10, issue=2, pageStart=153, pageEnd=155, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=Wu R, journalName=Academic Journal of Science and Technology, refType=null, unstructuredReference=Wu R. Development status of intelligent traffic management system[J]. Academic Journal of Science and Technology, 2024, 10(2): 153-155., articleTitle=Development status of intelligent traffic management system, refAbstract=null), Reference(id=1218525113574671298, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=36, pageEnd=40, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=Sharma A, Madan V, Bhargav V, journalName=14th International Conference on Cloud Computing, Data Science & Engineering(Confluence), refType=null, unstructuredReference=Sharma A, Madan V, Bhargav V, et al. Smart city traffic control system: a literature review[C]// 14th International Conference on Cloud Computing, Data Science & Engineering(Confluence). New York: IEEE, 2024: 36-40., articleTitle=Smart city traffic control system: a literature review, refAbstract=null), Reference(id=1218525113687917515, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, doi=null, pmid=null, pmcid=null, year=2024, volume=2, issue=1, pageStart=18, pageEnd=27, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=Zheng X, Yuan J Q, Yu L Q, journalName=International Journal of Computer Science and Information Technology, refType=null, unstructuredReference=Zheng X, Yuan J Q, Yu L Q, et al. Machine learning-based traffic flow prediction and intelligent traffic management[J]. International Journal of Computer Science and Information Technology, 2024, 2(1): 18-27., articleTitle=Machine learning-based traffic flow prediction and intelligent traffic management, refAbstract=null), Reference(id=1218525113885049809, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, doi=null, pmid=null, pmcid=null, year=2023, volume=14, issue=11, pageStart=429, pageEnd=437, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=Vinu S, Sherimon P C, Ismaeel A, journalName=International Journal of Advanced Computer Science and Applications, refType=null, unstructuredReference=Vinu S, Sherimon P C, Ismaeel A, et al. An overview of different deep learning techniques used in road accident detection[J]. International Journal of Advanced Computer Science and Applications, 2023, 14(11): 429-437., articleTitle=An overview of different deep learning techniques used in road accident detection, refAbstract=null), Reference(id=1218525113981518806, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, doi=null, pmid=null, pmcid=null, year=2024, volume=67, issue=3, pageStart=1041, pageEnd=1059, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=Yue L, Qi J F, Jin H B, journalName=Computer Journal, refType=null, unstructuredReference=Yue L, Qi J F, Jin H B, et al. An improved genetic-XGBoost classifier for customer consumption behavior prediction[J]. Computer Journal, 2024, 67(3): 1041-1059., articleTitle=An improved genetic-XGBoost classifier for customer consumption behavior prediction, refAbstract=null), Reference(id=1218525114103153630, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=6, pageStart=187, pageEnd=189, url=null, language=null, rfNumber=[6], rfOrder=5, authorNames=朱小平, 张丽英, 刘静, journalName=时代汽车, refType=null, unstructuredReference=朱小平, 张丽英, 刘静, 等. 基于XGBoost的自动驾驶汽车事故风险预测研究[J]. 时代汽车, 2024(6): 187-189., articleTitle=基于XGBoost的自动驾驶汽车事故风险预测研究, refAbstract=null), Reference(id=1218525114233177062, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=6, pageStart=187, pageEnd=189, url=null, language=null, rfNumber=[6], rfOrder=6, authorNames=Zhu Xiaoping, Zhang Liying, Liu Jing, journalName=Times Automotive, refType=null, unstructuredReference=Zhu Xiaoping, Zhang Liying, Liu Jing, et al. Research on accident risk prediction of self-driving cars based on XGBoost[J]. Times Automotive, 2024(6): 187-189., articleTitle=Research on accident risk prediction of self-driving cars based on XGBoost, refAbstract=null), Reference(id=1218525114321257453, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, doi=null, pmid=null, pmcid=null, year=2024, volume=48, issue=1, pageStart=25, pageEnd=30, url=null, language=null, rfNumber=[7], rfOrder=7, authorNames=蒋源, 陈小鸿, 胡松华, journalName=武汉理工大学学报(交通科学与工程版), refType=null, unstructuredReference=蒋源, 陈小鸿, 胡松华. 基于XGBoost模型的路段交通流量短时预测[J]. 武汉理工大学学报(交通科学与工程版), 2024, 48(1): 25-30., articleTitle=基于XGBoost模型的路段交通流量短时预测, refAbstract=null), Reference(id=1218525114480641013, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, doi=null, pmid=null, pmcid=null, year=2024, volume=48, issue=1, pageStart=25, pageEnd=30, url=null, language=null, rfNumber=[7], rfOrder=8, authorNames=Jiang Yuan, Chen Xiaohong, Hu Songhua, journalName=Journal of Wuhan University of Technology(Transportation Science and Engineering Edition), refType=null, unstructuredReference=Jiang Yuan, Chen Xiaohong, Hu Songhua. Short-time prediction of roadway traffic flow based on XGBoost model[J]. Journal of Wuhan University of Technology(Transportation Science and Engineering Edition), 2024, 48(1): 25-30., articleTitle=Short-time prediction of roadway traffic flow based on XGBoost model, refAbstract=null), Reference(id=1218525114589692925, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, doi=null, pmid=null, pmcid=null, year=2024, volume=50, issue=2, pageStart=33, pageEnd=42, url=null, language=null, rfNumber=[8], rfOrder=9, authorNames=单永航, 张希, 胡川, journalName=计算机工程, refType=null, unstructuredReference=单永航, 张希, 胡川, 等. 基于集成学习的交通事故严重程度预测研究与应用[J]. 计算机工程, 2024, 50(2): 33-42., articleTitle=基于集成学习的交通事故严重程度预测研究与应用, refAbstract=null), Reference(id=1218525114723909636, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, doi=null, pmid=null, pmcid=null, year=2024, volume=50, issue=2, pageStart=33, pageEnd=42, url=null, language=null, rfNumber=[8], rfOrder=10, authorNames=Shan Yonghang, Zhang Xi, Hu Chuan, journalName=Computer Engineering, refType=null, unstructuredReference=Shan Yonghang, Zhang Xi, Hu Chuan, et al. Research and application of traffic accident severity prediction based on integrated learning[J]. Computer Engineering, 2024, 50(2): 33-42., articleTitle=Research and application of traffic accident severity prediction based on integrated learning, refAbstract=null), Reference(id=1218525114849738764, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, doi=null, pmid=null, pmcid=null, year=2023, volume=35, issue=2, pageStart=757, pageEnd=774, url=null, language=null, rfNumber=[9], rfOrder=11, authorNames=Mohammed A, Rania K, journalName=Journal of King Saud University-Computer and Information Sciences, refType=null, unstructuredReference=Mohammed A, Rania K. A comprehensive review on ensemble deep learning: opportunities and challenges[J]. Journal of King Saud University-Computer and Information Sciences, 2023, 35(2): 757-774., articleTitle=A comprehensive review on ensemble deep learning: opportunities and challenges, refAbstract=null), Reference(id=1218525114988150806, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, doi=null, pmid=null, pmcid=null, year=2023, volume=14, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=12, authorNames=Ehteram M, Ali-Najah A, Zohreh-Sheikh K, journalName=Atmospheric Pollution Research, refType=null, unstructuredReference=Ehteram M, Ali-Najah A, Zohreh-Sheikh K, et al. Graph convolutional network-long short term memory neural network- multi layer perceptron- Gaussian progress regression model: a new deep learning model for predicting ozone concertation[J]. Atmospheric Pollution Research, 2023, 14. DOI: 10.1016/j.apr.2023.101766., articleTitle=Graph convolutional network-long short term memory neural network- multi layer perceptron- Gaussian progress regression model: a new deep learning model for predicting ozone concertation, refAbstract=null), Reference(id=1218525115101397020, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, doi=null, pmid=null, pmcid=null, year=2023, volume=72, issue=10, pageStart=12602, pageEnd=12614, url=null, language=null, rfNumber=[11], rfOrder=13, authorNames=Yao X D, Wang Y D, Wu Y L, journalName=IEEE Transactions on Vehicular Technology, refType=null, unstructuredReference=Yao X D, Wang Y D, Wu Y L, et al. MLP-based efficient convolutional neural network for lane detection[J]. IEEE Transactions on Vehicular Technology, 2023, 72(10): 12602-12614., articleTitle=MLP-based efficient convolutional neural network for lane detection, refAbstract=null), Reference(id=1218525115214643235, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, doi=null, pmid=null, pmcid=null, year=2024, volume=14, issue=8, pageStart=28, pageEnd=35, url=null, language=null, rfNumber=[12], rfOrder=14, authorNames=柳一航, 沈航先, journalName=科技创新与应用, refType=null, unstructuredReference=柳一航, 沈航先. 基于集成学习模型的交通事故严重程度时空预测[J]. 科技创新与应用, 2024, 14(8): 28-35., articleTitle=基于集成学习模型的交通事故严重程度时空预测, refAbstract=null), Reference(id=1218525115327889447, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, doi=null, pmid=null, pmcid=null, year=2024, volume=14, issue=8, pageStart=28, pageEnd=35, url=null, language=null, rfNumber=[12], rfOrder=15, authorNames=Liu Yihang, Shen Hangxian, journalName=Science and Technology Innovation and Application, refType=null, unstructuredReference=Liu Yihang, Shen Hangxian. Spatio-temporal prediction of traffic accident severity based on integrated learning model[J]. Science and Technology Innovation and Application, 2024, 14(8): 28-35., articleTitle=Spatio-temporal prediction of traffic accident severity based on integrated learning model, refAbstract=null), Reference(id=1218525115436941362, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=15, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=16, authorNames=Ahmed S, journalName=Sustainability, refType=null, unstructuredReference=Ahmed S. A software framework for predicting the maize yield using modified multi-layer perceptron[J]. Sustainability, 2023, 15. DOI: 10.3390/su15043017., articleTitle=A software framework for predicting the maize yield using modified multi-layer perceptron, refAbstract=null), Reference(id=1218525115516633143, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, doi=null, pmid=null, pmcid=null, year=2022, volume=37, issue=3, pageStart=41, pageEnd=45, url=null, language=null, rfNumber=[14], rfOrder=17, authorNames=张铭梁, 侯霞, journalName=北京信息科技大学学报(自然科学版), refType=null, unstructuredReference=张铭梁, 侯霞. 基于XGBoost-MLP集成方法的离港航班延误预测[J]. 北京信息科技大学学报(自然科学版), 2022, 37(3): 41-45., articleTitle=基于XGBoost-MLP集成方法的离港航班延误预测, refAbstract=null), Reference(id=1218525115608907837, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, doi=null, pmid=null, pmcid=null, year=2022, volume=37, issue=3, pageStart=41, pageEnd=45, url=null, language=null, rfNumber=[14], rfOrder=18, authorNames=Zhang Mingliang, Hou Xia, journalName=Journal of Beijing University of Information Science and Technology(Natural Science Edition), refType=null, unstructuredReference=Zhang Mingliang, Hou Xia. Delay prediction of departing flights based on XGBoost-MLP integration method[J]. Journal of Beijing University of Information Science and Technology(Natural Science Edition), 2022, 37(3): 41-45., articleTitle=Delay prediction of departing flights based on XGBoost-MLP integration method, refAbstract=null), Reference(id=1218525115738931270, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, doi=null, pmid=null, pmcid=null, year=2023, volume=31, issue=6, pageStart=3360, pageEnd=3379, url=null, language=null, rfNumber=[15], rfOrder=19, authorNames=Asselman A, Mohamed K, Souhaib A, journalName=Interactive Learning Environments, refType=null, unstructuredReference=Asselman A, Mohamed K, Souhaib A. Enhancing the prediction of student performance based on the machine learning XGBoost algorithm[J]. Interactive Learning Environments, 2023, 31(6): 3360-3379., articleTitle=Enhancing the prediction of student performance based on the machine learning XGBoost algorithm, refAbstract=null), Reference(id=1218525115810234442, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=2, pageStart=831, pageEnd=837, url=null, language=null, rfNumber=[16], rfOrder=20, authorNames=王博文, 王景升, 吴恩重, journalName=科学技术与工程, refType=null, unstructuredReference=王博文, 王景升, 吴恩重. 面向不平衡数据集的SMOTENC-XGBoost驾驶人交通安全评估模型[J]. 科学技术与工程, 2023, 23(2): 831-837., articleTitle=面向不平衡数据集的SMOTENC-XGBoost驾驶人交通安全评估模型, refAbstract=null), Reference(id=1218525115898314831, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=2, pageStart=831, pageEnd=837, url=null, language=null, rfNumber=[16], rfOrder=21, authorNames=Wang Bowen, Wang Jingsheng, Wu Enzhong, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Wang Bowen, Wang Jingsheng, Wu Enzhong. SMOTENC-XGBoost driver traffic safety assessment model for unbalanced datasets[J]. Science Technology and Engineering, 2023, 23(2): 831-837., articleTitle=SMOTENC-XGBoost driver traffic safety assessment model for unbalanced datasets, refAbstract=null), Reference(id=1218525116057698390, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, doi=null, pmid=null, pmcid=null, year=2023, volume=382, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=22, authorNames=Li Q F, Song Z M, journalName=Journal of Cleaner Production, refType=null, unstructuredReference=Li Q F, Song Z M. Prediction of compressive strength of rice husk ash concrete based on stacking ensemble learning model[J]. Journal of Cleaner Production, 2023, 382.DOI: 10.1016/j.jclepro.2022.135279., articleTitle=Prediction of compressive strength of rice husk ash concrete based on stacking ensemble learning model, refAbstract=null), Reference(id=1218525116133195870, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, doi=null, pmid=null, pmcid=null, year=2023, volume=15, issue=7, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=23, authorNames=Xin L, Chen C, Gao R D, journalName=Symmetry-Basel, refType=null, unstructuredReference=Xin L, Chen C, Gao R D, et al. Prediction of high-speed traffic flow around city based on BO-XGBoost model[J]. Symmetry-Basel, 2023, 15(7). DOI: 10.3390/sym15071453., articleTitle=Prediction of high-speed traffic flow around city based on BO-XGBoost model, refAbstract=null), Reference(id=1218525116250636388, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, doi=null, pmid=null, pmcid=null, year=2023, volume=5, issue=4, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=24, authorNames=Yue L L, Liu L Y, Li M Q, journalName=Transportation Safety and Environment, refType=null, unstructuredReference=Yue L L, Liu L Y, Li M Q, et al. Research on text fault recognition for on-board equipment of a C3 train control system based on an integrated XGBoost algorithm[J]. Transportation Safety and Environment, 2023, 5(4). DOI: 10.1093/tse/tdac066., articleTitle=Research on text fault recognition for on-board equipment of a C3 train control system based on an integrated XGBoost algorithm, refAbstract=null), Reference(id=1218525116368076905, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, doi=null, pmid=null, pmcid=null, year=2023, volume=165, issue=4, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[20], rfOrder=25, authorNames=Movahedi F, Padman R, Antaki J F, journalName=The Journal of Thoracic and Cardiovascular Surgery, refType=null, unstructuredReference=Movahedi F, Padman R, Antaki J F. Limitations of receiver operating characteristic curve on imbalanced data: assist device morta-lity risk scores[J]. The Journal of Thoracic and Cardiovascular Surgery, 2023, 165(4). DOI: 10.1016/j.jtcvs.2021.07.041., articleTitle=Limitations of receiver operating characteristic curve on imbalanced data: assist device morta-lity risk scores, refAbstract=null), Reference(id=1218525116485517425, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, doi=null, pmid=null, pmcid=null, year=2023, volume=48, issue=13, pageStart=5197, pageEnd=5228, url=null, language=null, rfNumber=[21], rfOrder=26, authorNames=Ming W Y, Sun P Y, Zhang Z, journalName=International Journal of Hydrogen Energy, refType=null, unstructuredReference=Ming W Y, Sun P Y, Zhang Z, et al. A systematic review of machine learning methods applied to fuel cells in performance evaluation, durability prediction, and application monitoring[J]. International Journal of Hydrogen Energy, 2023, 48(13): 5197-5228., articleTitle=A systematic review of machine learning methods applied to fuel cells in performance evaluation, durability prediction, and application monitoring, refAbstract=null)], funds=[Fund(id=1218525113192989609, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, awardId=52101383, language=CN, fundingSource=国家自然科学基金(52101383), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1218525107098665337, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, xref=1, ext=[AuthorCompanyExt(id=1218525107111248251, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, companyId=1218525107098665337, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Harbin Engineering University, Yantai Graduate School, Yantai 265500, China), AuthorCompanyExt(id=1218525107161579903, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, companyId=1218525107098665337, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 哈尔滨工程大学烟台研究生院, 烟台 265500)]), AuthorCompany(id=1218525107274826125, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, xref=2, ext=[AuthorCompanyExt(id=1218525107279020430, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, companyId=1218525107274826125, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Hubei Key Laboratory of Marine Electromagnetic Detection and Control, Wuhan Second Ship Design and Research Institute, Wuhan 430064, China), AuthorCompanyExt(id=1218525107287409041, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, companyId=1218525107274826125, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 武汉第二船舶设计研究所海洋电磁探测与控制湖北省重点实验室, 武汉 430064)])], figs=[ArticleFig(id=1218525110890316544, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, language=EN, label=Fig.1, caption=XGBoost algorithm flowchart, figureFileSmall=BAXj74KmLkSbYvZ4bi0D/Q==, figureFileBig=GEzJTy0P+qjBZOCBWO9g0g==, tableContent=null), ArticleFig(id=1218525111095837448, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, language=CN, label=图1, caption=XGBoost算法流程图, figureFileSmall=BAXj74KmLkSbYvZ4bi0D/Q==, figureFileBig=GEzJTy0P+qjBZOCBWO9g0g==, tableContent=null), ArticleFig(id=1218525111246832407, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, language=EN, label=Fig.2, caption=MLP network architecture diagram, figureFileSmall=JnB+orx5TAOnsnCnk4Ru7g==, figureFileBig=h5wzb5cYudncqg/oWDGH+Q==, tableContent=null), ArticleFig(id=1218525111402021665, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, language=CN, label=图2, caption=MLP网络构架图, figureFileSmall=JnB+orx5TAOnsnCnk4Ru7g==, figureFileBig=h5wzb5cYudncqg/oWDGH+Q==, tableContent=null), ArticleFig(id=1218525111506879273, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, language=EN, label=Fig.3, caption=Design concept flowchart, figureFileSmall=l5MVcSzw+p86dfl4TSvF5g==, figureFileBig=yJxtZL9PJHy1m77UJyyFqA==, tableContent=null), ArticleFig(id=1218525111674651440, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, language=CN, label=图3, caption=设计思路流程图, figureFileSmall=l5MVcSzw+p86dfl4TSvF5g==, figureFileBig=yJxtZL9PJHy1m77UJyyFqA==, tableContent=null), ArticleFig(id=1218525111796286264, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, language=EN, label=Fig.4, caption=Comparison between predicted and actual distribution, figureFileSmall=brEdKHpy9hv4ueAqQ6VIvQ==, figureFileBig=qigNWlPAw7gpkZyj4gUqJA==, tableContent=null), ArticleFig(id=1218525111964058433, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, language=CN, label=图4, caption=预测与实际分布对比, figureFileSmall=brEdKHpy9hv4ueAqQ6VIvQ==, figureFileBig=qigNWlPAw7gpkZyj4gUqJA==, tableContent=null), ArticleFig(id=1218525112060527430, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, language=EN, label=Fig.5, caption=Feature importance ranking, figureFileSmall=VuWs4j5+TnveARNdNOCNOw==, figureFileBig=WCXbbqse4RNBBudSs4Zv5g==, tableContent=null), ArticleFig(id=1218525112177967956, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, language=CN, label=图5, caption=特征重要性排序, figureFileSmall=VuWs4j5+TnveARNdNOCNOw==, figureFileBig=WCXbbqse4RNBBudSs4Zv5g==, tableContent=null), ArticleFig(id=1218525112266048346, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, language=EN, label=Fig.6, caption=The confusion matrix of predictive models, figureFileSmall=fU6bLM4szzrIcB+wMt/RFw==, figureFileBig=Uffh69GB0rn5/h/m7LUOrQ==, tableContent=null), ArticleFig(id=1218525112366711651, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, language=CN, label=图6, caption=不同事故程度的ROC曲线, figureFileSmall=fU6bLM4szzrIcB+wMt/RFw==, figureFileBig=Uffh69GB0rn5/h/m7LUOrQ==, tableContent=null), ArticleFig(id=1218525112463180653, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, language=EN, label=Fig.7, caption=The confusion matrix of predictive models, figureFileSmall=9XgRX51Sakx5yiY+zCMWIg==, figureFileBig=Ci5kbaq/QTw0ugoaZZQrWQ==, tableContent=null), ArticleFig(id=1218525112551261047, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, language=CN, label=图7, caption=预测模型的混淆矩阵

方格中的数值表示每个预测和实际类别组合的样本数量

, figureFileSmall=9XgRX51Sakx5yiY+zCMWIg==, figureFileBig=Ci5kbaq/QTw0ugoaZZQrWQ==, tableContent=null), ArticleFig(id=1218525112651924350, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, language=EN, label=Table 1, caption=

Model performance evaluation form

, figureFileSmall=null, figureFileBig=null, tableContent=
程度 精确度 召回率 F1分数 支持度
程度1 0.70 0.40 0.51 12 356
程度2 0.91 0.96 0.93 754 603
程度3 0.72 0.57 0.64 116 693
程度4 0.51 0.18 0.27 21 440
), ArticleFig(id=1218525112731616132, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, language=CN, label=表1, caption=

模型性能评估表

, figureFileSmall=null, figureFileBig=null, tableContent=
程度 精确度 召回率 F1分数 支持度
程度1 0.70 0.40 0.51 12 356
程度2 0.91 0.96 0.93 754 603
程度3 0.72 0.57 0.64 116 693
程度4 0.51 0.18 0.27 21 440
), ArticleFig(id=1218525112823890830, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, language=EN, label=Table 2, caption=

Model performance comparison form

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 宏平均 加权平均
传统XGBoost模型 0.49 0.86
集成XGBoost-MLP模型 0.59 0.87
), ArticleFig(id=1218525112945525658, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780470608655200, language=CN, label=表2, caption=

模型性能对比表

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 宏平均 加权平均
传统XGBoost模型 0.49 0.86
集成XGBoost-MLP模型 0.59 0.87
)], attaches=null, journal=Journal(id=1146119176004939786, delFlag=0, nameCn=科学技术与工程, nameEn=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, issn=1671-1815, eissn=, cn=11-4688/T, coden=null, periodic=4, language=CN, oaType=是, 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=UKU/O7GSka5polgCTkbIIw==, journalPrice=null, startedYear=null, abbrevIsoEn=Sci Technol Eng, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1754445529766, createdBy=null, updatedBy=13701087609, firstLetterCn=S, firstLetterEn=S, subjectCode=Natural Sciences, subjectName=自然科学, subjectCodeEn=Natural Sciences, subjectNameEn=null, picCn=UKU/O7GSka5polgCTkbIIw==, picEn=5hwlULoNwcbj3xUmVi9MAQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1159791870395564357, language=CN, name=科学技术与工程, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529793, updatedTime=1754445529793, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.stae.com.cn/jsygc/site/menus/20090429150146001, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1159791870441701702, language=EN, name=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529804, updatedTime=1754445529804, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1146123166801305609, websiteList=[Website(id=1148243202391400884, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, 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/kxjsygc/CN, language=CN, createTime=1751692112777, createBy=18614031015, updateTime=1753520965431, updateBy=18614031015, name=科学技术与工程-中文站点, tplId=1146099689490845704, title=科学技术与工程, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148622798802673703, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=articleTextType, value=kx, createTime=1751782615614, updateTime=1751782615614, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798781702180, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=banner, value=null, createTime=1751782615609, updateTime=1751782615609, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798769119267, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1751782615606, updateTime=1751782615606, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798794285094, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751782615612, updateTime=1751782615612, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798790090789, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751782615611, updateTime=1751782615611, creator=18614031015, updator=18614031015)]), Website(id=1155914124811976731, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, 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/kxjsygc/EN, language=EN, createTime=1753521003206, createBy=18614031015, updateTime=1753521003206, updateBy=18614031015, name=科学技术与工程-英文站点, tplId=1146101810881728533, title=Science Technology and Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155914371227308235, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=articleTextType, value=kx, createTime=1753521061952, updateTime=1753521061952, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371210531016, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=banner, value=null, createTime=1753521061947, updateTime=1753521061947, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371202142407, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1753521061945, updateTime=1753521061945, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371223113930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753521061950, updateTime=1753521061950, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371218919625, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753521061949, updateTime=1753521061949, creator=18614031015, updator=18614031015)])], journalTitle=科学技术与工程, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=Science Technology and Engineering, journalPhotoCn=UKU/O7GSka5polgCTkbIIw==, journalPhotoEn=5hwlULoNwcbj3xUmVi9MAQ==, journalFirstLetter=S, 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=null, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2403340, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2403340, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2403340, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2403340, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于集成模型的交通事故严重程度预测
收藏切换
PDF下载
杨翰琨 1 , 鲁帅 1 , 秦文杰 1 , 张彦敏 2, *
科学技术与工程 | 论文·交通运输 2025,25(10): 4355-4360
收起
收藏切换
科学技术与工程 | 论文·交通运输 2025, 25(10): 4355-4360
基于集成模型的交通事故严重程度预测
全屏
杨翰琨1 , 鲁帅1, 秦文杰1, 张彦敏2, *
作者信息
  • 1 哈尔滨工程大学烟台研究生院, 烟台 265500
  • 2 武汉第二船舶设计研究所海洋电磁探测与控制湖北省重点实验室, 武汉 430064
  • 杨翰琨(2001—),男,汉族,安徽滁州人,硕士研究生。研究方向:深度学习。E-mail:

通讯作者:

* 张彦敏(1980—),男,汉族,山东泰安人,博士,高级工程师。研究方向:水声工程。E-mail:
Prediction of Traffic Accident Severity Based on Integrated Models
Han-kun YANG1 , Shuai LU1, Wen-jie QIN1, Yan-min ZHANG2, *
Affiliations
  • 1 Harbin Engineering University, Yantai Graduate School, Yantai 265500, China
  • 2 Hubei Key Laboratory of Marine Electromagnetic Detection and Control, Wuhan Second Ship Design and Research Institute, Wuhan 430064, China
出版时间: 2025-04-08 doi: 10.12404/j.issn.1671-1815.2403340
文章导航
收藏切换

交通事故对公共安全构成重大风险,是交通运输系统中的重要问题。准确预测事故严重程度对于采取有效的预防和干预措施至关重要。提出了一种基于集成学习的方法,将XGBoost和MLP两种先进算法相结合,以更精准地预测交通事故的严重程度。建立了一个堆叠分类器,并详细评估了其在交通事故预测中的性能。实验结果表明,该集成模型相较于传统XGBoost模型,在预测准确性上有明显提升,在宏平均F1分数上显著提高了20.41%。展示了模型优势与创新性,包括模型集成与网络改造。此外,还分析了影响预测结果的关键特征,并探讨了模型在实际应用中的潜在价值。该研究为交通安全管理提供了更科学、更高效的决策支持,有望在交通管理、智能驾驶等领域发挥重要作用。

交通事故  /  严重程度预测  /  XGBoost  /  MLP  /  特征分析  /  集成学习  /  深度学习

Traffic accidents pose significant risks to public safety and represent a critical issue in transportation systems. The accurate prediction of accident severity is essential for implementing effective prevention and intervention measures. An ensemble learning approach, combining the advanced algorithms XGBoost and MLP, was proposed to enhance the accuracy of traffic accident severity predictions. A stacked classifier was established and its performance in traffic accident prediction was thoroughly evaluated. The experimental results demonstrate that the integrated model significantly improves prediction accuracy compared to the traditional XGBoost model, with a notable 20.41% increase in the macro-average F1 score. The advantages and innovations of the model, including model integration and network transformation, were highlighted. Additionally, the key features affecting the prediction results were analyzed, and the model's potential value in practical applications was explored. This study provides more scientific and efficient decision support for traffic safety management and is expected to play a crucial role in fields such as traffic management and intelligent driving.

traffic accidents  /  severity prediction  /  XGBoost  /  MLP  /  feature analysis  /  ensemble learning  /  deep learning
杨翰琨, 鲁帅, 秦文杰, 张彦敏. 基于集成模型的交通事故严重程度预测. 科学技术与工程, 2025 , 25 (10) : 4355 -4360 . DOI: 10.12404/j.issn.1671-1815.2403340
Han-kun YANG, Shuai LU, Wen-jie QIN, Yan-min ZHANG. Prediction of Traffic Accident Severity Based on Integrated Models[J]. Science Technology and Engineering, 2025 , 25 (10) : 4355 -4360 . DOI: 10.12404/j.issn.1671-1815.2403340
城市交通管理系统是现代城市基础设施的重要组成部分[1]。随着城市化的快速推进和车辆数量的激增,交通事故频发已成为全球多数城市的一个严峻问题。这些事故不仅造成严重的人员伤亡,还对城市交通流动和公共安全构成重大威胁。因此,准确预测和有效管理交通事故的严重程度是城市交通管理系统的一个核心挑战[2]
在传统的交通事故管理中,预测事故的严重程度通常依赖于事故现场的初步报告和历史事故数据[1]。然而,这种方法往往反应迟缓,且准确性有限。为了提高预测的准确性和实时性,越来越多的研究开始集中于利用先进的数据分析技术和算法来预测交通事故的严重程度[3-4]。以极端梯度提升(eXtreme gradient boosting,XGBoost)模型为例,Li等[5]运用该模型预测客户消费行为;朱小平等[6]用该模型预测自动驾驶汽车事故风险;蒋源等[7]用该模型对路段交通流量进行短时预测,均取得了显著效果。
然而,尽管XGBoost在处理复杂的非线性关系时表现卓越,但面对如交通预测这样的高复杂度问题时,该模型仍显示出一定的局限性。为此,单永航等[8]提出了一种集成学习方法来预测交通事故的程度,这开辟了改进预测模型的新途径。集成学习是一种通过组合多个模型来提升预测性能的方法,主要包括Bagging、Boosting和Stacking等类型。其中,Bagging,也称做自助聚集方法,通过并行训练多个独立模型并综合它们的预测结果,有效地降低了模型的方差,增强了预测的稳定性。而Boosting方法则侧重于按顺序训练一系列模型,旨在通过减少偏差提高准确率,并通过迭代优化提升整体预测效果。Stacking则通过将不同模型的预测结果作为输入,利用一个新的模型(称为元模型)进行整合,借助各基模型独特的数据处理方式,实现比任何单一模型更精准的预测结果[9]
多层感知器(multi-layer perceptron,MLP)是一种前馈神经网络[10],它包含一个或多个隐藏层。每个节点与下一层的每个节点通过权重连接,每个连接的权重表示了该连接的重要性。输入层接收输入数据,经过隐藏层的处理后,输出层产生最终结果。每个神经元应用激活函数来决定是否将信号传递给下一层,这使得MLP能够学习和模拟非线性复杂函数[11-12]。Ahmed[13]利用多层感知器模型进行作物产量预测,相较于其他算法,该模型显示出了更低的均方根误差,表明其预测精度较高。张铭梁等[14]使用XGBoost和MLP集成方法预测离港航班延误问题,达到了提高预测精度的效果。
在这一背景下,现采用Stacking集成XGBoost和MLP的先进算法,旨在更准确地分析城市交通数据,及时发现交通安全隐患。相对于传统方法,本文算法不依赖于人工经验和简单的统计分析,而是结合两种模型的学习策略和假设空间,获得更多样化的模型集成。这种方法为交通安全管理提供更科学、更高效的决策支持,有助于降低事故发生率、优化交通流量,实现城市交通安全的可持续发展目标。
XGBoost是一种强大的集成学习方法,利用梯度提升技术构建多棵决策树,并将它们整合成一个强大的模型[15]。其核心思想是通过迭代训练决策树,每棵树纠正前一棵树的错误,最小化损失函数,逐步提升模型性能[16]
相较于传统决策树,XGBoost引入正则化项和特征选择机制,有效控制模型复杂度和过拟合风险。正则化项惩罚模型参数,使其更倾向于简单配置,提高泛化能力。特征选择机制评估特征重要性,排除不重要特征,减小模型维度,提高训练速度、稳定性和解释性。XGBoost模型通过迭代计算梯度、拟合决策树、更新模型,不断优化损失函数,构建决策树模型序列,最终组合形成预测模型,保持了模型的泛化能力和性能。
XGBoost模型在梯度提升算法的框架基础上进行了改进和优化,以提高模型的性能和泛化能力,其原理流程如图1所示。
XGBoost目标函数是由两部分组成的总体函数。第一部分是损失函数,用于衡量模型预测值与真实值之间的偏差。第二部分是正则项Ω,用于惩罚模型的复杂度,以避免过拟合。整体目标函数Obj是这两部分的求和。
Obj= i = 1 nl(yi, y ^ i)+ k = 1 kΩ(fk)
式(1)中:l(yi, y ^ i)为损失函数;fk为第k个数模型预测结果。
在每次迭代k时,XGBoost通过最小化目标函数Objk来调整模型。
Objk= i = 1 nl[yi, y ^ i k - 1+fk(xi)]+Ω(fk)
式(2)中: y ^ i k - 1为第k-1次迭代中第i个样本的预测值。
通过迭代更新,模型逐渐提高预测准确度,优化过程中求得的权重和偏置项(w*,q*)。
(w*,q*)=argminw,q i = 1 nl[yi, y ^ i k - 1+wq(xi)+Ω(fk)]
MLP是一种前馈神经网络,常用于模式识别、分类和回归等任务。它由输入层、隐藏层和输出层构成[9],如图2所示。输入层接收数据特征作为输入,隐藏层和输出层对数据进行进一步处理。隐藏层的节点数和层数可根据实际情况调整。MLP的基本单元是神经元,每个神经元接收来自其他神经元的信息,并按权重进行加权求和。若刺激强度超过阈值,则经过激活函数进行非线性变换得到输出。
在训练阶段,MLP通过学习调整参数权重来建立输入和输出的映射关系。训练过程包括多轮前向传播和反向传播。前向传播将输入信号逐层传递至输出层,计算预测结果。损失函数评估预测值与真实值之间的差异,常用的有交叉熵和均方差损失函数。反向传播将误差传回网络各层,通过梯度下降更新权重参数,直至误差达到预定标准。
网络集成技术是一种先进的方法,通过将多个单独的模型融合在一起,增强整体的预测性能。在进行模型集成之前,重要的一步是考虑各个模型在架构上的差异,以确保它们能够有效地整合。本文研究中采用了Stacking方法来实现模型集成。该方法特别有效,因为它利用了多个基模型的预测结果作为新的输入特征,这些特征随后用于训练一个更高层次的元模型,以进行最终的预测[17-19]
具体地,首先将各个基模型的预测结果整合成一个新的特征矩阵,然后将这个新的特征矩阵与原始数据的特征矩阵合并。
Xstacked=[X Xnew]
式(4)中:Xstacked为经过堆叠的特征矩阵,用于输入到新的模型中。Xnew为新的训练特征数据集,这些数据集经过不同模型的预测结果合成,作为下一阶段的输入。
这个合并后的特征矩阵将被用作元模型的训练数据,从而进一步优化预测结果。
Meta(Xstacked)=y
在实施过程中,输入层首先需要加载并预处理数据,这是确保数据质量和后续模型表现的关键步骤。在隐藏层的设计中,将多层感知器的隐藏层输出与XGBoost的输出进行结合,形成一个混合的网络结构。这种结构不仅增强了模型的表达能力,还提高了处理复杂数据的能力。最终,在设计输出层时,根据具体的任务需求进行了优化,使用元模型进行最终决策。通过这种方式,能够有效地整合各种模型,最大化预测精度和可靠性。
本次实验的主要目标是通过建立一个堆叠分类器来提高分类任务的预测准确率,在XGBoost基础上集成MLP深度学习,选取并预处理充分的交通事故数据,对模型进行训练。整个预处理和模型训练过程被封装在一个流水线中,确保数据的一致处理和简化模型的使用流程。流水线中包含了数据预处理步骤和堆叠模型的训练步骤。最终在独立的验证集上测试模型的性能,以评估模型的泛化能力。预测结果将调整回原始的标签范围,用于性能评估。整体设计思路如图3所示。通过这一系列步骤,本次实验旨在验证通过不同类型模型的集成是否能有效提升交通事故验证程度的预测准确率,并探索不同模型特征提取能力的互补性,最终达到优化分类性能的目的。
本次研究收集了大量公开交通事故数据,并处理了缺失值和异常值。筛选了关于时间特征、气候特征和道路特征方面的特征。基于所有特征的性质,将特征在类型上分为数值型特征和类别型特征。对于数值型特征,采用均值填补缺失值并进行标准化处理,以消除不同特征之间的规模差异;对于类别型特征,则使用常量填补缺失值,并应用目标编码技术,以提高模型对这些特征的理解和使用效率。
本次研究的数据集包含7 728 394个样本,其目标变量交通事故严重程度被划分为轻微事故、一般事故、重大事故、特大事故4个等级。轻微事故通常仅造成车辆轻微损伤,一般事故会导致车辆明显损坏和人员轻伤,重大事故会造成严重车辆损坏和人员重伤,特大事故通常导致车辆报废以及人员死亡或重伤。为了进行模型训练和验证,本文研究将数据集按照80%训练集和20%验证集进行划分,分别用于训练和验证。
本文研究详细配置了每个模型组件的参数,确保了模型的优化性能和结果的可靠性。MLP模型设定了3个关键层:输入层根据特征数量定为30维,接下来的两个隐藏层分别配置128个和64个神经元,并使用ReLU激活函数来引入非线性处理能力,最终的输出层包含4个神经元,使用softmax函数输出类别概率。设置了4个严重程度级别的类别数量。为了确保结果的可重复性,选择了随机种子42。为了提高训练速度,利用 GPU 加速。最后,使用训练好的模型对验证集数据进行预测,并对模型的性能进行评估,以确保模型在实际应用中的有效性和准确性。
本文研究旨在探讨基MLP和XGBoost的堆叠集成模型在预测交通事故严重程度上的有效性。通过详细的实验分析,不仅考察了模型的预测准确性,还探究了影响预测结果的关键特征。
本文研究将轻微事故、一般事故、重大事故、特大事故4个等级分别对应为1~4级。图4中的核密度估计图展示了预测交通事故严重程度和实际程度的分布情况,基础数据来源于验证集。通过对比观察,可以直观地发现预测和实际的交通事故严重程度具有相似的分布趋势,这表明对于不同样本数的各严重程度等级,模型的预测分布和实际分布在各个等级上都表现出很高的一致性。
对不同特征在预测交通事故严重程度中的重要性进行了排序,如图5所示。这些排序是通过算法在训练过程中自动学习和调整权重后得到的。
每个条形代表一个特征,其长度表示该特征的重要性。“日出/日落”二分类特征具有最高的权重,表明其在预测交通事故严重程度时起着关键作用,可能与光照条件与驾驶员视线直接相关。紧随其后的是“是否在转弯环”“距离”和“是否需要礼让行人”,这些特征的重要性指示了道路环境和交通行为对事故严重程度的预测价值。
本文研究细致评估了模型对于预测交通事故严重程度的分类性能。总体上,模型的准确率达到了0.88。此外,还分析了分类结果的精确度、召回率、F1分数以及支持度,结果如表1所示。
进一步地,采用接收者操作特性(receiver operating characteristic,ROC)曲线来描述模型性能。曲线下面积(area under the curve, AUC)越接近1,模型的诊断能力越强[20]图6中展示了针对4个不同严重程度类别的分类器性能的ROC曲线。各条曲线以不同颜色区分,其中红色曲线代表对严重事故程度1的预测,其AUC值高达0.97,表明该分类器在区分该事故严重程度与其他事故方面表现卓越。
为了直观地了解模型在各个分类类别中的预测准确度及其误判情况,本文研究还采用混淆矩阵来展示模型在不同严重程度事故预测中的详细性能,如图7所示。图7揭示了在其他类别上的一些误分类情况,这对于进一步调整和优化模型参数,以及提高模型整体预测性能具有重要指导意义。
为了进一步展现本文研究提出的集成模型在预测交通事故严重程度上的优势,进行了与传统XGBoost模型的对比分析。特别关注了模型预测结果的综合性能指标F1分数,它平衡了精确度和召回率的影响,提供了对模型性能的全面评价[21]。如表2所显示的性能对比数据清晰地揭示了集成模型在预测准确性上的提升。宏平均F1分数反映了模型在所有类别上的平均性能,而加权平均F1分数则考虑了不同类别的样本量对整体性能的影响。
研究表明集成XGBoost-MLP模型相对于传统XGBoost模型在在加权平均F1分数上,提升了约1.16%,在宏平均F1分数上从0.49提升到0.59,提升了约20.41%。这样的增幅不仅统计上是显著的,也在实际应用中可能意味着对于事故严重性预测的显著改进,特别是在预测较不频繁发生的事故类别时。这一提升展现了集成模型在综合不同模型的特点和优势,提高整体预测能力方面的潜力。
提出了基于XGBoost和MLP的集成模型在预测交通事故严重程度上表现出显著的优势。XGBoost和MLP具有不同的学习策略和假设空间。XGBoost擅长处理结构化数据,而MLP更适合处理非结构化数据,可以学习到更复杂的非线性关系。通过结合两者的优势,可以更好地处理原始数据中的复杂特征,提供更丰富的特征表示,从而获得更多样化的模型集成。
基于集成XGBoost和MLP的交通事故严重程度预测模型具有广泛的应用前景。在实用性上,该模型不仅可用于交通安全管理系统,提供实时的交通事故严重程度预测,还可以集成到智能驾驶辅助系统,为驾驶员提供交通事故风险预警,减少事故发生的频率、减轻事故造成的损失。此外,本文模型还可以应用于保险业务、城市规划与交通设计、智慧城市建设等领域。
总之,基于集成XGBoost和MLP的交通事故严重程度预测模型可以为提高交通安全水平和城市交通运行效率发挥积极的作用。
  • 国家自然科学基金(52101383)
参考文献 引证文献
排序方式:
[1]
Wu R. Development status of intelligent traffic management system[J]. Academic Journal of Science and Technology, 2024, 10(2): 153-155.
[2]
Sharma A, Madan V, Bhargav V, et al. Smart city traffic control system: a literature review[C]// 14th International Conference on Cloud Computing, Data Science & Engineering(Confluence). New York: IEEE, 2024: 36-40.
[3]
Zheng X, Yuan J Q, Yu L Q, et al. Machine learning-based traffic flow prediction and intelligent traffic management[J]. International Journal of Computer Science and Information Technology, 2024, 2(1): 18-27.
[4]
Vinu S, Sherimon P C, Ismaeel A, et al. An overview of different deep learning techniques used in road accident detection[J]. International Journal of Advanced Computer Science and Applications, 2023, 14(11): 429-437.
[5]
Yue L, Qi J F, Jin H B, et al. An improved genetic-XGBoost classifier for customer consumption behavior prediction[J]. Computer Journal, 2024, 67(3): 1041-1059.
[6]
朱小平, 张丽英, 刘静, 等. 基于XGBoost的自动驾驶汽车事故风险预测研究[J]. 时代汽车, 2024(6): 187-189.
Zhu Xiaoping, Zhang Liying, Liu Jing, et al. Research on accident risk prediction of self-driving cars based on XGBoost[J]. Times Automotive, 2024(6): 187-189.
[7]
蒋源, 陈小鸿, 胡松华. 基于XGBoost模型的路段交通流量短时预测[J]. 武汉理工大学学报(交通科学与工程版), 2024, 48(1): 25-30.
Jiang Yuan, Chen Xiaohong, Hu Songhua. Short-time prediction of roadway traffic flow based on XGBoost model[J]. Journal of Wuhan University of Technology(Transportation Science and Engineering Edition), 2024, 48(1): 25-30.
[8]
单永航, 张希, 胡川, 等. 基于集成学习的交通事故严重程度预测研究与应用[J]. 计算机工程, 2024, 50(2): 33-42.
Shan Yonghang, Zhang Xi, Hu Chuan, et al. Research and application of traffic accident severity prediction based on integrated learning[J]. Computer Engineering, 2024, 50(2): 33-42.
[9]
Mohammed A, Rania K. A comprehensive review on ensemble deep learning: opportunities and challenges[J]. Journal of King Saud University-Computer and Information Sciences, 2023, 35(2): 757-774.
[10]
Ehteram M, Ali-Najah A, Zohreh-Sheikh K, et al. Graph convolutional network-long short term memory neural network- multi layer perceptron- Gaussian progress regression model: a new deep learning model for predicting ozone concertation[J]. Atmospheric Pollution Research, 2023, 14. DOI: 10.1016/j.apr.2023.101766.
[11]
Yao X D, Wang Y D, Wu Y L, et al. MLP-based efficient convolutional neural network for lane detection[J]. IEEE Transactions on Vehicular Technology, 2023, 72(10): 12602-12614.
[12]
柳一航, 沈航先. 基于集成学习模型的交通事故严重程度时空预测[J]. 科技创新与应用, 2024, 14(8): 28-35.
Liu Yihang, Shen Hangxian. Spatio-temporal prediction of traffic accident severity based on integrated learning model[J]. Science and Technology Innovation and Application, 2024, 14(8): 28-35.
[13]
Ahmed S. A software framework for predicting the maize yield using modified multi-layer perceptron[J]. Sustainability, 2023, 15. DOI: 10.3390/su15043017.
[14]
张铭梁, 侯霞. 基于XGBoost-MLP集成方法的离港航班延误预测[J]. 北京信息科技大学学报(自然科学版), 2022, 37(3): 41-45.
Zhang Mingliang, Hou Xia. Delay prediction of departing flights based on XGBoost-MLP integration method[J]. Journal of Beijing University of Information Science and Technology(Natural Science Edition), 2022, 37(3): 41-45.
[15]
Asselman A, Mohamed K, Souhaib A. Enhancing the prediction of student performance based on the machine learning XGBoost algorithm[J]. Interactive Learning Environments, 2023, 31(6): 3360-3379.
[16]
王博文, 王景升, 吴恩重. 面向不平衡数据集的SMOTENC-XGBoost驾驶人交通安全评估模型[J]. 科学技术与工程, 2023, 23(2): 831-837.
Wang Bowen, Wang Jingsheng, Wu Enzhong. SMOTENC-XGBoost driver traffic safety assessment model for unbalanced datasets[J]. Science Technology and Engineering, 2023, 23(2): 831-837.
[17]
Li Q F, Song Z M. Prediction of compressive strength of rice husk ash concrete based on stacking ensemble learning model[J]. Journal of Cleaner Production, 2023, 382.DOI: 10.1016/j.jclepro.2022.135279.
[18]
Xin L, Chen C, Gao R D, et al. Prediction of high-speed traffic flow around city based on BO-XGBoost model[J]. Symmetry-Basel, 2023, 15(7). DOI: 10.3390/sym15071453.
[19]
Yue L L, Liu L Y, Li M Q, et al. Research on text fault recognition for on-board equipment of a C3 train control system based on an integrated XGBoost algorithm[J]. Transportation Safety and Environment, 2023, 5(4). DOI: 10.1093/tse/tdac066.
[20]
Movahedi F, Padman R, Antaki J F. Limitations of receiver operating characteristic curve on imbalanced data: assist device morta-lity risk scores[J]. The Journal of Thoracic and Cardiovascular Surgery, 2023, 165(4). DOI: 10.1016/j.jtcvs.2021.07.041.
[21]
Ming W Y, Sun P Y, Zhang Z, et al. A systematic review of machine learning methods applied to fuel cells in performance evaluation, durability prediction, and application monitoring[J]. International Journal of Hydrogen Energy, 2023, 48(13): 5197-5228.
2025年第25卷第10期
PDF下载
333
134
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2403340
  • 接收时间:2024-05-07
  • 首发时间:2025-07-09
  • 出版时间:2025-04-08
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-05-07
  • 修回日期:2025-01-02
基金
国家自然科学基金(52101383)
作者信息
    1 哈尔滨工程大学烟台研究生院, 烟台 265500
    2 武汉第二船舶设计研究所海洋电磁探测与控制湖北省重点实验室, 武汉 430064

通讯作者:

* 张彦敏(1980—),男,汉族,山东泰安人,博士,高级工程师。研究方向:水声工程。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2403340
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