Article(id=1156983787000258786, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1156983783787421903, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2400859, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1706544000000, receivedDateStr=2024-01-30, revisedDate=1731600000000, revisedDateStr=2024-11-15, acceptedDate=null, acceptedDateStr=null, onlineDate=1753776030540, onlineDateStr=2025-07-29, pubDate=1739808000000, pubDateStr=2025-02-18, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1753776030540, onlineIssueDateStr=2025-07-29, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1753776030540, creator=13701087609, updateTime=1753776030540, updator=13701087609, issue=Issue{id=1156983783787421903, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='5', pageStart='1753', pageEnd='2192', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1753776029774, creator=13701087609, updateTime=1769691857141, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1223739602251436918, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1156983783787421903, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1223739602251436919, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1156983783787421903, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=1774, endPage=1882, ext={EN=ArticleExt(id=1156983790338924786, articleId=1156983787000258786, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Intelligent Rock Recognition Based on Lightweight Network and Transfer Learning, columnId=1156262729351549255, journalTitle=Science Technology and Engineering, columnName=Papers·Astronomy and Geosciences, runingTitle=null, highlight=null, articleAbstract=

In rock image recognition, achieving rapid and accurate identification of rocks is crucial for the digitalization of rocks. Among the challenges faced in intelligent rock recognition is the issue of image blurring caused by environmental factors such as lighting and humidity. In light of this, a novel deep learning approach (MobileNetV3-small-RegNetX) was proposed for rock image recognition, which is suitable for scenarios with limited resources such as mobile devices. Building upon the RegNet network, transfer learning methods, combining the advantages of the MobileNetV3 residual structure with squeeze-and-excitation (SE)modules was employed to effectively optimize feature extraction and network structure, leading to a significant improvement in detection speed. To validate the accuracy of this approach, comparative experiments were conducted between the new model and current mainstream lightweight models (DenseNet and ShuffleNet). The results demonstrate that the new model proposed exhibits high precision (82.15%) and fast processing (0.06 GFLOPs). Additionally, the model demonstrates good adaptability to environmental factors such as lighting and humidity-induced image blurring.

, 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=Shun-yong LI, Qing-hui LI, Yu-man XING), CN=ArticleExt(id=1156983954088747800, articleId=1156983787000258786, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=基于轻量化网络和迁移学习的岩石智能识别, columnId=1156262730077163858, journalTitle=科学技术与工程, columnName=论文·天文学、地球科学, runingTitle=null, highlight=null, articleAbstract=在岩石图像识别中,实现岩石快速准确的识别是岩石数字化发展的关键。其中,光照、湿度等环境因素引起的图像模糊问题成为岩石智能识别的最大挑战之一。基于此,提出了一种新的深度学习方法(MbileNetV3-small-RegNetX)来识别岩石图像,其适用于移动设备等资源有限的场景。在RegNet网络的基础上采用迁移学习方法,结合MobileNetV3残差结构与通道注意力(squeeze-and-excitation,SE)模块的优势,有效地优化了特征提取与网络结构,并显著提升了检测速度。为验证该方法的准确性,将新模型与当下主流的轻量化模型(DenseNet和ShuffleNet)进行消融对比实验。结果显示,所提模型表现出高精度(82.15%)、快速(0.06 GFLOPs)的特点。此外,该模型对于光照、湿度等环境因素引起的图像模糊具有良好的适应性。, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=dw8ddZ4lYRC2fxYKYWTrkg==, magXml=4y91wd+ZCexxy8FEZUHTzQ==, pdfUrl=null, pdf=6n35b1i3Q/msnhD8MSNKPw==, pdfFileSize=13428761, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=UeE4oIXm5P9L8Kv+ze1UpA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=7bPDYpnWPPUvK2YxbEFysw==, mapNumber=null, authorCompany=null, fund=null, authors=

李顺勇(1975—),男,汉族,山西大同人,博士,教授。研究方向:统计机器学习与数据挖掘。E-mail:

, authorsList=李顺勇, 李青辉, 邢煜曼)}, authors=[Author(id=1225467168909865858, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=lisy75@sxu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1225467168997946251, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, authorId=1225467168909865858, language=EN, stringName=Shun-yong LI, firstName=Shun-yong, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Mathematical Sciences, Shanxi University, Taiyuan 030006, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1225467169123775378, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, authorId=1225467168909865858, language=CN, stringName=李顺勇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=山西大学数学科学学院, 太原 030006, bio={"content":"

李顺勇(1975—),男,汉族,山西大同人,博士,教授。研究方向:统计机器学习与数据挖掘。E-mail:

"}, bioImg=null, bioContent=

李顺勇(1975—),男,汉族,山西大同人,博士,教授。研究方向:统计机器学习与数据挖掘。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1225467167567688565, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, xref=null, ext=[AuthorCompanyExt(id=1225467167571882870, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, companyId=1225467167567688565, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mathematical Sciences, Shanxi University, Taiyuan 030006, China), AuthorCompanyExt(id=1225467167580271479, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, companyId=1225467167567688565, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=山西大学数学科学学院, 太原 030006)])]), Author(id=1225467169224438686, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, 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=1225467169316713379, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, authorId=1225467169224438686, language=EN, stringName=Qing-hui LI, firstName=Qing-hui, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Mathematical Sciences, Shanxi University, Taiyuan 030006, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1225467169404793774, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, authorId=1225467169224438686, language=CN, stringName=李青辉, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=山西大学数学科学学院, 太原 030006, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1225467167567688565, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, xref=null, ext=[AuthorCompanyExt(id=1225467167571882870, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, companyId=1225467167567688565, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mathematical Sciences, Shanxi University, Taiyuan 030006, China), AuthorCompanyExt(id=1225467167580271479, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, companyId=1225467167567688565, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=山西大学数学科学学院, 太原 030006)])]), Author(id=1225467169530622905, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, 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=1225467169706783687, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, authorId=1225467169530622905, language=EN, stringName=Yu-man XING, firstName=Yu-man, middleName=null, lastName=XING, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Mathematical Sciences, Shanxi University, Taiyuan 030006, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1225467169790669774, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, authorId=1225467169530622905, language=CN, stringName=邢煜曼, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=山西大学数学科学学院, 太原 030006, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1225467167567688565, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, xref=null, ext=[AuthorCompanyExt(id=1225467167571882870, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, companyId=1225467167567688565, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mathematical Sciences, Shanxi University, Taiyuan 030006, China), AuthorCompanyExt(id=1225467167580271479, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, companyId=1225467167567688565, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=山西大学数学科学学院, 太原 030006)])])], keywords=[Keyword(id=1225467170038133731, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=EN, orderNo=1, keyword=rock recognition), Keyword(id=1225467170226877424, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=EN, orderNo=2, keyword=deep learning), Keyword(id=1225467170331735036, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=EN, orderNo=3, keyword=image classification), Keyword(id=1225467170478534663, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=EN, orderNo=4, keyword=transfer learning), Keyword(id=1225467170562420754, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=EN, orderNo=5, keyword=MobileNet network), Keyword(id=1225467170906353701, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=CN, orderNo=1, keyword=岩石识别), Keyword(id=1225467171069931572, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=CN, orderNo=2, keyword=深度学习), Keyword(id=1225467171204149310, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=CN, orderNo=3, keyword=图像分类), Keyword(id=1225467171359338567, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=CN, orderNo=4, keyword=迁移学习), Keyword(id=1225467171464196175, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=CN, orderNo=5, keyword=MobileNet网络)], refs=[Reference(id=1225467182944006943, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2022, volume=68, issue=6, pageStart=2290, pageEnd=2304, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=许振浩, 马文, 李术才, journalName=地质论评, refType=null, unstructuredReference=许振浩, 马文, 李术才, 等. 岩性识别: 方法、现状及智能化发展趋势[J]. 地质论评, 2022, 68(6): 2290-2304., articleTitle=岩性识别: 方法、现状及智能化发展趋势, refAbstract=null), Reference(id=1225467183107584809, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2022, volume=68, issue=6, pageStart=2290, pageEnd=2304, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Xu Zhenhao, Ma Wen, Li Shucai, journalName=Geological Review, refType=null, unstructuredReference=Xu Zhenhao, Ma Wen, Li Shucai, et al. Lithological identification: methods, current situation, and intelligent development trend[J]. Geological Review, 2022, 68(6): 2290-2304., articleTitle=Lithological identification: methods, current situation, and intelligent development trend, refAbstract=null), Reference(id=1225467183262774069, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2023, volume=58, issue=3, pageStart=495, pageEnd=506, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=夏文鹤, 谢万洋, 唐印东, journalName=石油地球物理勘探, refType=null, unstructuredReference=夏文鹤, 谢万洋, 唐印东, 等. 砂样岩屑图像特征的岩性智能高效识别[J]. 石油地球物理勘探, 2023, 58(3): 495-506., articleTitle=砂样岩屑图像特征的岩性智能高效识别, refAbstract=null), Reference(id=1225467183371825980, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2023, volume=58, issue=3, pageStart=495, pageEnd=506, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=Xia Wenhe, Xie Wanyang, Tang Yindong, journalName=Petroleum Geophysical Exploration, refType=null, unstructuredReference=Xia Wenhe, Xie Wanyang, Tang Yindong, et al. Intelligent and efficient identification of lithology based on image features of sand samples and rock debris[J]. Petroleum Geophysical Exploration, 2023, 58(3): 495-506., articleTitle=Intelligent and efficient identification of lithology based on image features of sand samples and rock debris, refAbstract=null), Reference(id=1225467183497655111, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2022, volume=51, issue=8, pageStart=43, pageEnd=47, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=仝容超, journalName=化工矿物与加工, refType=null, unstructuredReference=仝容超. 机器学习在岩性智能识别中的应用研究进展[J]. 化工矿物与加工, 2022, 51(8): 43-47, 54., articleTitle=机器学习在岩性智能识别中的应用研究进展, refAbstract=null), Reference(id=1225467183623484243, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2022, volume=51, issue=8, pageStart=43, pageEnd=47, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=Tong Rongchao, journalName=Chemical Minerals and Processing, refType=null, unstructuredReference=Tong Rongchao. Research progress on the application of machine learning in intelligent lithology recognition[J]. Chemical Minerals and Processing, 2022, 51(8): 43-47, 54., articleTitle=Research progress on the application of machine learning in intelligent lithology recognition, refAbstract=null), Reference(id=1225467183761896284, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2020, volume=40, issue=20, pageStart=98, pageEnd=100, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=高婷, 杨洋, 何江, journalName=中国石油和化工标准与质量, refType=null, unstructuredReference=高婷, 杨洋, 何江. 人工智能在岩石图像上的应用综述[J]. 中国石油和化工标准与质量, 2020, 40(20): 98-100., articleTitle=人工智能在岩石图像上的应用综述, refAbstract=null), Reference(id=1225467183887725418, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2020, volume=40, issue=20, pageStart=98, pageEnd=100, url=null, language=null, rfNumber=[4], rfOrder=7, authorNames=Gao Ting, Yang Yang, He Jiang, journalName=Chinese Petroleum and Chemical Standards and Quality, refType=null, unstructuredReference=Gao Ting, Yang Yang, He Jiang. Overview of the application of artificial intelligence in rock images[J]. Chinese Petroleum and Chemical Standards and Quality, 2020, 40(20): 98-100., articleTitle=Overview of the application of artificial intelligence in rock images, refAbstract=null), Reference(id=1225467184017748853, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2022, volume=14, issue=4, pageStart=1140, pageEnd=1152, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=Xu Z H, Ma W, Lin P, journalName=Journal of Rock Mechanics and Geotechnical Engineering, refType=null, unstructuredReference=Xu Z H, Ma W, Lin P, et al. Deep learning of rock microscopic images for intelligent lithology identification: neural network comparison and selection[J]. Journal of Rock Mechanics and Geotechnical Engineering, 2022, 14(4): 1140-1152., articleTitle=Deep learning of rock microscopic images for intelligent lithology identification: neural network comparison and selection, refAbstract=null), Reference(id=1225467184147772291, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2023, volume=32, issue=6, pageStart=2965, pageEnd=2980, url=null, language=null, rfNumber=[6], rfOrder=9, authorNames=Hou Z, Wei J, Shen J, journalName=Natural Resources Research, refType=null, unstructuredReference=Hou Z, Wei J, Shen J, et al. Intelligent lithology identification methods for rock images based on object detection[J]. Natural Resources Research, 2023, 32(6): 2965-2980., articleTitle=Intelligent lithology identification methods for rock images based on object detection, refAbstract=null), Reference(id=1225467184240046990, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2020, volume=30, issue=5, pageStart=1192, pageEnd=1201, url=null, language=null, rfNumber=[7], rfOrder=10, authorNames=王李管, 陈斯佳, 贾明滔, journalName=中国有色金属学报, refType=null, unstructuredReference=王李管, 陈斯佳, 贾明滔, 等. 基于深度学习的黑钨矿图像识别选矿方法[J]. 中国有色金属学报, 2020, 30(5): 1192-1201., articleTitle=基于深度学习的黑钨矿图像识别选矿方法, refAbstract=null), Reference(id=1225467184374264725, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2020, volume=30, issue=5, pageStart=1192, pageEnd=1201, url=null, language=null, rfNumber=[7], rfOrder=11, authorNames=Wang Liguan, Chen Sijia, Jia Mingtao, journalName=Chinese Journal of Nonferrous Metals, refType=null, unstructuredReference=Wang Liguan, Chen Sijia, Jia Mingtao, et al. Deep learning based image recognition and beneficiation method for tungsten ore[J]. Chinese Journal of Nonferrous Metals, 2020, 30(5): 1192-1201., articleTitle=Deep learning based image recognition and beneficiation method for tungsten ore, refAbstract=null), Reference(id=1225467184466539425, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2021, volume=29, issue=5, pageStart=1075, pageEnd=1092, url=null, language=null, rfNumber=[8], rfOrder=12, authorNames=许振浩, 马文, 林鹏, journalName=应用基础与工程科学学报, refType=null, unstructuredReference=许振浩, 马文, 林鹏, 等. 基于岩石图像迁移学习的岩性智能识别[J]. 应用基础与工程科学学报, 2021, 29(5): 1075-1092., articleTitle=基于岩石图像迁移学习的岩性智能识别, refAbstract=null), Reference(id=1225467184579785641, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2021, volume=29, issue=5, pageStart=1075, pageEnd=1092, url=null, language=null, rfNumber=[8], rfOrder=13, authorNames=Xu Zhenhao, Ma Wen, Lin Peng, journalName=Journal of Applied Fundamentals and Engineering Science, refType=null, unstructuredReference=Xu Zhenhao, Ma Wen, Lin Peng, et al. Intelligent lithology recognition based on rock image transfer learning[J]. Journal of Applied Fundamentals and Engineering Science, 2021, 29(5): 1075-1092., articleTitle=Intelligent lithology recognition based on rock image transfer learning, refAbstract=null), Reference(id=1225467184651088820, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2022, volume=38, issue=3, pageStart=17, pageEnd=22, url=null, language=null, rfNumber=[9], rfOrder=14, authorNames=谭永健, 田苗, 徐德馨, journalName=地理与地理信息科学, refType=null, unstructuredReference=谭永健, 田苗, 徐德馨, 等. 基于Xception网络的岩石图像分类识别研究[J]. 地理与地理信息科学, 2022, 38(3): 17-22., articleTitle=基于Xception网络的岩石图像分类识别研究, refAbstract=null), Reference(id=1225467184776917948, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2022, volume=38, issue=3, pageStart=17, pageEnd=22, url=null, language=null, rfNumber=[9], rfOrder=15, authorNames=Tan Yongjian, Tian Miao, Xu Dexin, journalName=Geography and Geographic Information Science, refType=null, unstructuredReference=Tan Yongjian, Tian Miao, Xu Dexin, et al. Research on rock image classification and recognition based on Xception network[J]. Geography and Geographic Information Science, 2022, 38(3): 17-22., articleTitle=Research on rock image classification and recognition based on Xception network, refAbstract=null), Reference(id=1225467184902747081, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2023, volume=42, issue=5, pageStart=1003, pageEnd=1010, url=null, language=null, rfNumber=[10], rfOrder=16, authorNames=赵兴东, 王宏宇, 白夜, journalName=矿床地质, refType=null, unstructuredReference=赵兴东, 王宏宇, 白夜. 基于卷积神经网络迁移学习模型的矿岩智能识别方法[J]. 矿床地质, 2023, 42(5): 1003-1010., articleTitle=基于卷积神经网络迁移学习模型的矿岩智能识别方法, refAbstract=null), Reference(id=1225467185057936343, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2023, volume=42, issue=5, pageStart=1003, pageEnd=1010, url=null, language=null, rfNumber=[10], rfOrder=17, authorNames=Zhao Xingdong, Wang Hongyu, Bai Ye, journalName=Deposit Geology, refType=null, unstructuredReference=Zhao Xingdong, Wang Hongyu, Bai Ye. A mining and rock intelligent recognition method based on convolutional neural network transfer learning model[J]. Deposit Geology, 2023, 42(5): 1003-1010., articleTitle=A mining and rock intelligent recognition method based on convolutional neural network transfer learning model, refAbstract=null), Reference(id=1225467185242485737, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2023, volume=41, issue=3, pageStart=450, pageEnd=458, url=null, language=null, rfNumber=[11], rfOrder=18, authorNames=袁硕, 刘玉敏, 安志伟, journalName=吉林大学学报(信息科学版), refType=null, unstructuredReference=袁硕, 刘玉敏, 安志伟, 等. 基于改进ShuffleNetV2网络的岩石图像识别[J]. 吉林大学学报(信息科学版), 2023, 41(3): 450-458., articleTitle=基于改进ShuffleNetV2网络的岩石图像识别, refAbstract=null), Reference(id=1225467185364120569, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2023, volume=41, issue=3, pageStart=450, pageEnd=458, url=null, language=null, rfNumber=[11], rfOrder=19, authorNames=Yuan Shuo, Liu Yumin, An Zhiwei, journalName=Journal of Jilin University (Information Science Edition), refType=null, unstructuredReference=Yuan Shuo, Liu Yumin, An Zhiwei, et al. Rock image recognition based on improved ShuffleNetV2 network[J]. Journal of Jilin University (Information Science Edition), 2023, 41(3): 450-458., articleTitle=Rock image recognition based on improved ShuffleNetV2 network, refAbstract=null), Reference(id=1225467185477366784, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2023, volume=30, issue=4, pageStart=26, pageEnd=34, url=null, language=null, rfNumber=[12], rfOrder=20, authorNames=熊峰, 廖一凡, 曹伟腾, journalName=安全与环境工程, refType=null, unstructuredReference=熊峰, 廖一凡, 曹伟腾, 等. 基于卷积神经网络-深度迁移学习的岩性自动识别研究[J]. 安全与环境工程, 2023, 30(4): 26-34., articleTitle=基于卷积神经网络-深度迁移学习的岩性自动识别研究, refAbstract=null), Reference(id=1225467186861486094, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2023, volume=30, issue=4, pageStart=26, pageEnd=34, url=null, language=null, rfNumber=[12], rfOrder=21, authorNames=Xiong Feng, Liao Yifan, Cao Weiteng, journalName=Safety and Environmental Engineering, refType=null, unstructuredReference=Xiong Feng, Liao Yifan, Cao Weiteng, et al. Research on automatic lithology recognition based on convolutional neural network deep transfer learning[J]. Safety and Environmental Engineering, 2023, 30(4): 26-34., articleTitle=Research on automatic lithology recognition based on convolutional neural network deep transfer learning, refAbstract=null), Reference(id=1225467187062812697, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2021, volume=15, issue=4, pageStart=743, pageEnd=753, url=null, language=null, rfNumber=[13], rfOrder=22, authorNames=肖振久, 杨晓迪, 魏宪, journalName=计算机科学与探索, refType=null, unstructuredReference=肖振久, 杨晓迪, 魏宪, 等. 改进的轻量型网络在图像识别上的应用[J]. 计算机科学与探索, 2021, 15(4): 743-753., articleTitle=改进的轻量型网络在图像识别上的应用, refAbstract=null), Reference(id=1225467187264139299, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2021, volume=15, issue=4, pageStart=743, pageEnd=753, url=null, language=null, rfNumber=[13], rfOrder=23, authorNames=Xiao Zhenjiu, Yang Xiaodi, Wei Xian, journalName=Computer Science and Exploration, refType=null, unstructuredReference=Xiao Zhenjiu, Yang Xiaodi, Wei Xian, et al. The application of improved lightweight networks in image recognition[J]. Computer Science and Exploration, 2021, 15(4): 743-753., articleTitle=The application of improved lightweight networks in image recognition, refAbstract=null), Reference(id=1225467187402551345, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2023, volume=33, issue=10, pageStart=128, pageEnd=134, url=null, language=null, rfNumber=[14], rfOrder=24, authorNames=杜睿山, 宋健辉, 孟令东, journalName=计算机技术与发展, refType=null, unstructuredReference=杜睿山, 宋健辉, 孟令东. 基于注意力机制的岩石铸体薄片轻量化分割[J]. 计算机技术与发展, 2023, 33(10): 128-134., articleTitle=基于注意力机制的岩石铸体薄片轻量化分割, refAbstract=null), Reference(id=1225467187549351996, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2023, volume=33, issue=10, pageStart=128, pageEnd=134, url=null, language=null, rfNumber=[14], rfOrder=25, authorNames=Du Ruishan, Song Jianhui, Meng Lingdong, journalName=Computer Technology and Development, refType=null, unstructuredReference=Du Ruishan, Song Jianhui, Meng Lingdong. Lightweight segmentation of rock casting thin sections based on attention mechanism[J]. Computer Technology and Development, 2023, 33(10): 128-134., articleTitle=Lightweight segmentation of rock casting thin sections based on attention mechanism, refAbstract=null), Reference(id=1225467187721318473, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=2, pageStart=674, pageEnd=680, url=null, language=null, rfNumber=[15], rfOrder=26, authorNames=陈开峰, 俞伟聪, 唐雁文, journalName=科学技术与工程, refType=null, unstructuredReference=陈开峰, 俞伟聪, 唐雁文, 等. 基于轻量化深度学习网络的数字仪表识别[J]. 科学技术与工程, 2023, 23(2): 674-680., articleTitle=基于轻量化深度学习网络的数字仪表识别, refAbstract=null), Reference(id=1225467187838758992, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=2, pageStart=674, pageEnd=680, url=null, language=null, rfNumber=[15], rfOrder=27, authorNames=Chen Kaifeng, Yu Weicong, Tang Yanwen, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Chen Kaifeng, Yu Weicong, Tang Yanwen, et al. Digital instrument recognition based on lightweight deep learning networks[J]. Science Technology and Engineering, 2023, 23(2): 674-680., articleTitle=Digital instrument recognition based on lightweight deep learning networks, refAbstract=null), Reference(id=1225467188010725471, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=29, pageStart=12628, pageEnd=12637, url=null, language=null, rfNumber=[16], rfOrder=28, authorNames=刘今子, 杜文颖, 董驰, journalName=科学技术与工程, refType=null, unstructuredReference=刘今子, 杜文颖, 董驰, 等. 基于色彩空间和深度残差网络ResNet-50的复杂岩性油气藏岩石样本智能分类及识别[J]. 科学技术与工程, 2023, 23(29): 12628-12637., articleTitle=基于色彩空间和深度残差网络ResNet-50的复杂岩性油气藏岩石样本智能分类及识别, refAbstract=null), Reference(id=1225467188115583078, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=29, pageStart=12628, pageEnd=12637, url=null, language=null, rfNumber=[16], rfOrder=29, authorNames=Liu Jinzi, Du Wenying, Dong Chi, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Liu Jinzi, Du Wenying, Dong Chi, et al. Intelligent classification and recognition of complex lithology oil and gas reservoir rock samples based on color space and depth residual network ResNet-50[J]. Science Technology and Engineering, 2023, 23(29): 12628-12637., articleTitle=Intelligent classification and recognition of complex lithology oil and gas reservoir rock samples based on color space and depth residual network ResNet-50, refAbstract=null), Reference(id=1225467188321103988, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=9, pageStart=3779, pageEnd=3786, url=null, language=null, rfNumber=[17], rfOrder=30, authorNames=王明明, 孙寅静, 孙晓云, journalName=科学技术与工程, refType=null, unstructuredReference=王明明, 孙寅静, 孙晓云, 等. 基于深度残差网络与迁移学习的地形识别方法[J]. 科学技术与工程, 2023, 23(9): 3779-3786., articleTitle=基于深度残差网络与迁移学习的地形识别方法, refAbstract=null), Reference(id=1225467188463710335, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=9, pageStart=3779, pageEnd=3786, url=null, language=null, rfNumber=[17], rfOrder=31, authorNames=Wang Mingming, Sun Yinjing, Sun Xiaoyun, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Wang Mingming, Sun Yinjing, Sun Xiaoyun, et al. A terrain recognition method based on deep residual networks and transfer learning[J]. Science Technology and Engineering, 2023, 23(9): 3779-3786., articleTitle=A terrain recognition method based on deep residual networks and transfer learning, refAbstract=null), Reference(id=1225467188648259721, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2022, volume=39, issue=12, pageStart=6323, pageEnd=6344, url=null, language=null, rfNumber=[18], rfOrder=32, authorNames=Marriam N, Ali J, Aun I, journalName=The Visual Computer, refType=null, unstructuredReference=Marriam N, Ali J, Aun I. ResNet-Swish-Dense54: a deep learning approach for deepfakes detection[J]. The Visual Computer, 2022, 39(12): 6323-6344., articleTitle=ResNet-Swish-Dense54: a deep learning approach for deepfakes detection, refAbstract=null), Reference(id=1225467188782477463, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2023, volume=58, issue=5, pageStart=1031, pageEnd=1041, url=null, language=null, rfNumber=[19], rfOrder=33, authorNames=翟晓岩, 高刚, 李勇根, journalName=石油地球物理勘探, refType=null, unstructuredReference=翟晓岩, 高刚, 李勇根, 等. 融合注意力机制的二维卷积神经网络测井曲线重构方法[J]. 石油地球物理勘探, 2023, 58(5): 1031-1041., articleTitle=融合注意力机制的二维卷积神经网络测井曲线重构方法, refAbstract=null), Reference(id=1225467188904112287, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2023, volume=58, issue=5, pageStart=1031, pageEnd=1041, url=null, language=null, rfNumber=[19], rfOrder=34, authorNames=Zhai Xiaoyan, Gao Gang, Li Yonggen, journalName=Petroleum Geophysical Exploration, refType=null, unstructuredReference=Zhai Xiaoyan, Gao Gang, Li Yonggen, et al. A two-dimensional convolutional neural network well logging curve reconstruction method integrating attention mechanism[J]. Petroleum Geophysical Exploration, 2023, 58(5): 1031-1041., articleTitle=A two-dimensional convolutional neural network well logging curve reconstruction method integrating attention mechanism, refAbstract=null), Reference(id=1225467189050912935, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2023, volume=20, issue=9, pageStart=3604, pageEnd=3615, url=null, language=null, rfNumber=[20], rfOrder=35, authorNames=凌同华, 陈梓浓, 张胜, journalName=铁道科学与工程学报, refType=null, unstructuredReference=凌同华, 陈梓浓, 张胜, 等. 岩石岩性轻量化网络识别方法及其隧道工程应[J]. 铁道科学与工程学报, 2023, 20(9): 3604-3615., articleTitle=岩石岩性轻量化网络识别方法及其隧道工程应, refAbstract=null), Reference(id=1225467189176742067, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2023, volume=20, issue=9, pageStart=3604, pageEnd=3615, url=null, language=null, rfNumber=[20], rfOrder=36, authorNames=Ling Tonghua, Chen Zinong, Zhang Sheng, journalName=Journal of Railway Science and Engineering, refType=null, unstructuredReference=Ling Tonghua, Chen Zinong, Zhang Sheng, et al. A lightweight network recognition method for rock lithology and its application in tunnel engineering[J]. Journal of Railway Science and Engineering, 2023, 20(9): 3604-3615., articleTitle=A lightweight network recognition method for rock lithology and its application in tunnel engineering, refAbstract=null), Reference(id=1225467189285793983, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=4, pageStart=1953, pageEnd=1953, url=null, language=null, rfNumber=[21], rfOrder=37, authorNames=Jin G, Liu Y L, Qin P L, journalName=Sensors, refType=null, unstructuredReference=Jin G, Liu Y L, Qin P L, et al. An end-to-end steel surface classification approach based on EDCGAN and MobileNet V2[J]. Sensors, 2023, 23(4): 1953-1953., articleTitle=An end-to-end steel surface classification approach based on EDCGAN and MobileNet V2, refAbstract=null), Reference(id=1225467189365485766, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2023, volume=15, issue=6, pageStart=3229, pageEnd=3243, url=null, language=null, rfNumber=[22], rfOrder=38, authorNames=Rajendra B S P, Sai B C, journalName=International Journal of Information Technology, refType=null, unstructuredReference=Rajendra B S P, Sai B C. Mobilenetv3: a deep learning technique for human face expressions identification[J]. International Journal of Information Technology, 2023, 15(6): 3229-3243., articleTitle=Mobilenetv3: a deep learning technique for human face expressions identification, refAbstract=null), Reference(id=1225467189461954767, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2023, volume=17, issue=5, pageStart=4305, pageEnd=4317, url=null, language=null, rfNumber=[23], rfOrder=39, authorNames=Zhang R C, Yuan Y C, Meng X, journalName=Journal of Food Measurement and Characterization, refType=null, unstructuredReference=Zhang R C, Yuan Y C, Meng X, et al. A multitask model based on MobileNetV3 for fine-grained classification of jujube varieties[J]. Journal of Food Measurement and Characterization, 2023, 17(5): 4305-4317., articleTitle=A multitask model based on MobileNetV3 for fine-grained classification of jujube varieties, refAbstract=null), Reference(id=1225467189558423764, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2022, volume=82, issue=12, pageStart=18709, pageEnd=18725, url=null, language=null, rfNumber=[24], rfOrder=40, authorNames=Yang Y, Han J, journalName=Multimedia Tools and Applications, refType=null, unstructuredReference=Yang Y, Han J. Real-time object detector based MobileNetV3 for UAV applications[J]. Multimedia Tools and Applications, 2022, 82(12): 18709-18725., articleTitle=Real-time object detector based MobileNetV3 for UAV applications, refAbstract=null), Reference(id=1225467189654892763, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2023, volume=49, issue=4, pageStart=62, pageEnd=69, url=null, language=null, rfNumber=[25], rfOrder=41, authorNames=孔二伟, 张亚邦, 李佳悦, journalName=工矿自动化, refType=null, unstructuredReference=孔二伟, 张亚邦, 李佳悦, 等. 面向煤矿井下低光照图像的增强方[J]. 工矿自动化, 2023, 49(4): 62-69, 85., articleTitle=面向煤矿井下低光照图像的增强方, refAbstract=null), Reference(id=1225467189772333283, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, doi=null, pmid=null, pmcid=null, year=2023, volume=49, issue=4, pageStart=62, pageEnd=69, url=null, language=null, rfNumber=[25], rfOrder=42, authorNames=Kong Erwei, Zhang Yabang, Li Jiayue, journalName=Industrial and Mining Automation, refType=null, unstructuredReference=Kong Erwei, Zhang Yabang, Li Jiayue, et al. An enhancement method for low light images in coal mine underground[J]. Industrial and Mining Automation, 2023, 49(4): 62-69, 85., articleTitle=An enhancement method for low light images in coal mine underground, refAbstract=null)], funds=[Fund(id=1225467180926546631, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, awardId=61976128, language=CN, fundingSource=国家自然科学基金(61976128), fundOrder=null, country=null), Fund(id=1225467181052375766, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, awardId=62072293, language=CN, fundingSource=国家自然科学基金(62072293), fundOrder=null, country=null), Fund(id=1225467182440690406, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, awardId=202303021221054, language=CN, fundingSource=山西省基础研究计划(202303021221054), fundOrder=null, country=null), Fund(id=1225467182587491058, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, awardId=2024-002, language=CN, fundingSource=山西省回国留学人员科研教研资助项目(2024-002), fundOrder=null, country=null), Fund(id=1225467182717514502, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, awardId=2022YJJG010, language=CN, fundingSource=山西省研究生教育教学改革课题(2022YJJG010), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1225467167567688565, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, xref=null, ext=[AuthorCompanyExt(id=1225467167571882870, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, companyId=1225467167567688565, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mathematical Sciences, Shanxi University, Taiyuan 030006, China), AuthorCompanyExt(id=1225467167580271479, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, companyId=1225467167567688565, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=山西大学数学科学学院, 太原 030006)])], figs=[ArticleFig(id=1225467171741020267, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=EN, label=Fig.1, caption=Deep convolution, figureFileSmall=xj2gLt5ExFg6fF6SgIcm/Q==, figureFileBig=7xipEBzu+Z/vT3vGUJ5o5A==, tableContent=null), ArticleFig(id=1225467171829100659, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=CN, label=图1, caption=深度卷积, figureFileSmall=xj2gLt5ExFg6fF6SgIcm/Q==, figureFileBig=7xipEBzu+Z/vT3vGUJ5o5A==, tableContent=null), ArticleFig(id=1225467171971707010, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=EN, label=Fig.2, caption=Point by point convolution, figureFileSmall=X4nzrWXj0K3rWbIBpkT6fw==, figureFileBig=n+3Mr0rIZmLnV1PRndiu5w==, tableContent=null), ArticleFig(id=1225467173401964686, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=CN, label=图2, caption=逐点卷积, figureFileSmall=X4nzrWXj0K3rWbIBpkT6fw==, figureFileBig=n+3Mr0rIZmLnV1PRndiu5w==, tableContent=null), ArticleFig(id=1225467173611679903, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=EN, label=Fig.3, caption=Inverted residual structure, figureFileSmall=eA/knKh6LEaIo65RAk5+bQ==, figureFileBig=j2sbpakWU9kJlJKOcwfrSw==, tableContent=null), ArticleFig(id=1225467173821395121, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=CN, label=图3, caption=倒残差结构, figureFileSmall=eA/knKh6LEaIo65RAk5+bQ==, figureFileBig=j2sbpakWU9kJlJKOcwfrSw==, tableContent=null), ArticleFig(id=1225467173997555905, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=EN, label=Fig.4, caption=SE module, figureFileSmall=vG3vBro/P0+bGotah4O1aQ==, figureFileBig=rWySIaKe/gWzumqhxcbnog==, tableContent=null), ArticleFig(id=1225467174299545810, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=CN, label=图4, caption=SE模块, figureFileSmall=vG3vBro/P0+bGotah4O1aQ==, figureFileBig=rWySIaKe/gWzumqhxcbnog==, tableContent=null), ArticleFig(id=1225467174530232542, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=EN, label=Fig.5, caption=H-Swish function, figureFileSmall=kN3CTt28Ol/4uWJ09rsD1Q==, figureFileBig=R7yogCZeELHelW6QdRE5Ww==, tableContent=null), ArticleFig(id=1225467174748336362, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=CN, label=图5, caption=H-Swish函数, figureFileSmall=kN3CTt28Ol/4uWJ09rsD1Q==, figureFileBig=R7yogCZeELHelW6QdRE5Ww==, tableContent=null), ArticleFig(id=1225467174878359802, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=EN, label=Fig.6, caption=Core module, figureFileSmall=Zm/PY1CsDGzFgLkILGAwVQ==, figureFileBig=1EWN2tkcN8sp9+osaSafhQ==, tableContent=null), ArticleFig(id=1225467175079686409, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=CN, label=图6, caption=核心模块, figureFileSmall=Zm/PY1CsDGzFgLkILGAwVQ==, figureFileBig=1EWN2tkcN8sp9+osaSafhQ==, tableContent=null), ArticleFig(id=1225467175197126937, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=EN, label=Fig.7, caption=Experimental technology route, figureFileSmall=HVUt3g9DkmfT0+A9EV8Y/g==, figureFileBig=i6pBbfR5TjMPalEeVVtinQ==, tableContent=null), ArticleFig(id=1225467175306178849, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=CN, label=图7, caption=实验技术路线, figureFileSmall=HVUt3g9DkmfT0+A9EV8Y/g==, figureFileBig=i6pBbfR5TjMPalEeVVtinQ==, tableContent=null), ArticleFig(id=1225467175440396591, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=EN, label=Fig.8, caption=Example of rock image, figureFileSmall=dukApc0vRzJZlrUidAEntg==, figureFileBig=l/kIpgZYbQRbxLHqATx93g==, tableContent=null), ArticleFig(id=1225467175566225726, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=CN, label=图8, caption=岩石图像示例, figureFileSmall=dukApc0vRzJZlrUidAEntg==, figureFileBig=l/kIpgZYbQRbxLHqATx93g==, tableContent=null), ArticleFig(id=1225467175708832075, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=EN, label=Fig.9, caption=Example of data enhancement effect, figureFileSmall=wHUxr0RaQQdIVhpCko0dvg==, figureFileBig=YlUps/407qVR4aQnYNFdUg==, tableContent=null), ArticleFig(id=1225467175876604254, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=CN, label=图9, caption=数据增强效果示例, figureFileSmall=wHUxr0RaQQdIVhpCko0dvg==, figureFileBig=YlUps/407qVR4aQnYNFdUg==, tableContent=null), ArticleFig(id=1225467176069542254, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=EN, label=Fig.10, caption=Accuracy and loss value convergence curve, figureFileSmall=1RFhyZCDenNeOdC9RrV5eQ==, figureFileBig=yK377zIECNBNIevCESo0+w==, tableContent=null), ArticleFig(id=1225467176254091651, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=CN, label=图10, caption=准确率与损失值收敛曲线, figureFileSmall=1RFhyZCDenNeOdC9RrV5eQ==, figureFileBig=yK377zIECNBNIevCESo0+w==, tableContent=null), ArticleFig(id=1225467176396698002, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=EN, label=Fig.11, caption=Confusion matrix on test set, figureFileSmall=Bp9uhB8vFBdXpJvBsjvmqg==, figureFileBig=3yqcEfTiJrrs2sk4A8A4ow==, tableContent=null), ArticleFig(id=1225467176518332831, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=CN, label=图11, caption=测试集上的混淆矩阵, figureFileSmall=Bp9uhB8vFBdXpJvBsjvmqg==, figureFileBig=3yqcEfTiJrrs2sk4A8A4ow==, tableContent=null), ArticleFig(id=1225467177936007604, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=EN, label=Table 1, caption=

MbileNetV3-Small network structure

, figureFileSmall=null, figureFileBig=null, tableContent=
输入尺寸 操作 扩展因子 输出维度 是否使用注意力机制 激活函数类型 步长
2242×3 conv2d,3×3 16 HS 2
1122×1 bneck,3×3 16 16 RE 2
562×16 bneck,3×3 72 24 RE 2
282×24 bneck,3×3 88 24 RE 1
282×24 bneck,5×5 96 40 HS 2
142×40 bneck,5×5 240 40 HS 1
142×40 bneck,5×5 240 40 HS 1
142×40 bneck,5×5 120 48 HS 1
142×48 bneck,5×5 144 48 HS 1
142×48 bneck,5×5 288 96 HS 2
72×96 bneck,5×5 576 96 HS 1
72×96 bneck,5×5 576 96 HS 1
72×96 conv2d,1×1 576 HS 1
72×576 pool,7×7 1
12×576 conv2d,1×1,NBN 1 024 HS 1
12×1 024 conv2d,1×1,NBN 7 1
), ArticleFig(id=1225467178464489935, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=CN, label=表1, caption=

MbileNetV3-Small网络结构

, figureFileSmall=null, figureFileBig=null, tableContent=
输入尺寸 操作 扩展因子 输出维度 是否使用注意力机制 激活函数类型 步长
2242×3 conv2d,3×3 16 HS 2
1122×1 bneck,3×3 16 16 RE 2
562×16 bneck,3×3 72 24 RE 2
282×24 bneck,3×3 88 24 RE 1
282×24 bneck,5×5 96 40 HS 2
142×40 bneck,5×5 240 40 HS 1
142×40 bneck,5×5 240 40 HS 1
142×40 bneck,5×5 120 48 HS 1
142×48 bneck,5×5 144 48 HS 1
142×48 bneck,5×5 288 96 HS 2
72×96 bneck,5×5 576 96 HS 1
72×96 bneck,5×5 576 96 HS 1
72×96 conv2d,1×1 576 HS 1
72×576 pool,7×7 1
12×576 conv2d,1×1,NBN 1 024 HS 1
12×1 024 conv2d,1×1,NBN 7 1
), ArticleFig(id=1225467178628067801, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=EN, label=Table 2, caption=

Distribution of rock image data

, figureFileSmall=null, figureFileBig=null, tableContent=
岩石种类 样本数量 岩石种类 样本数量
黑色煤 18 灰色泥质粉砂岩 45
深灰色泥岩 62 灰黑色泥岩 29
深灰色粉砂质泥岩 39 浅灰色细砂岩 73
灰色细砂岩 17
), ArticleFig(id=1225467178846171637, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=CN, label=表2, caption=

岩石图像数据分布

, figureFileSmall=null, figureFileBig=null, tableContent=
岩石种类 样本数量 岩石种类 样本数量
黑色煤 18 灰色泥质粉砂岩 45
深灰色泥岩 62 灰黑色泥岩 29
深灰色粉砂质泥岩 39 浅灰色细砂岩 73
灰色细砂岩 17
), ArticleFig(id=1225467179039109638, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=EN, label=Table 3, caption=

Various rock image grid clipping specifications

, figureFileSmall=null, figureFileBig=null, tableContent=
岩石种类 网格规格 岩石种类 网格规格
黑色煤 4×4 灰色泥质粉砂岩 3×2
深灰色泥岩 2×2 灰黑色泥岩 5×2
深灰色粉砂质泥岩 2×4 浅灰色细砂岩 2×2
灰色细砂岩 4×4
), ArticleFig(id=1225467179164938769, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=CN, label=表3, caption=

各类岩石图像网格裁剪规格

, figureFileSmall=null, figureFileBig=null, tableContent=
岩石种类 网格规格 岩石种类 网格规格
黑色煤 4×4 灰色泥质粉砂岩 3×2
深灰色泥岩 2×2 灰黑色泥岩 5×2
深灰色粉砂质泥岩 2×4 浅灰色细砂岩 2×2
灰色细砂岩 4×4
), ArticleFig(id=1225467179370459682, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=EN, label=Table 4, caption=

Data enhancement details

, figureFileSmall=null, figureFileBig=null, tableContent=
增强方式 参数设置
随机调整图像的亮度和对比度 [-1.5,1.5]、[-1.5,1.5]
高斯模糊处理 [7,15]
平移、缩放和旋转 [0.3]、[-90,90]
色调、饱和度 [20,20]、[-30,30]
对比度限制自适应直方图均衡化
水平、垂直翻转
), ArticleFig(id=1225467179487900210, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=CN, label=表4, caption=

数据增强详情

, figureFileSmall=null, figureFileBig=null, tableContent=
增强方式 参数设置
随机调整图像的亮度和对比度 [-1.5,1.5]、[-1.5,1.5]
高斯模糊处理 [7,15]
平移、缩放和旋转 [0.3]、[-90,90]
色调、饱和度 [20,20]、[-30,30]
对比度限制自适应直方图均衡化
水平、垂直翻转
), ArticleFig(id=1225467179617923653, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=EN, label=Table 5, caption=

Data enhancement effect (quantity)

, figureFileSmall=null, figureFileBig=null, tableContent=
岩石类别 数据增强前数量 数据增强后数量
黑色煤 18 2 304
深灰色泥岩 62 1 984
深灰色粉砂质泥岩 39 2 496
灰色细砂岩 17 2 176
灰色泥质粉砂岩 45 2 160
灰黑色泥岩 29 2 320
浅灰色细砂岩 73 2 336
), ArticleFig(id=1225467179764724312, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=CN, label=表5, caption=

数据增强效果(数量)

, figureFileSmall=null, figureFileBig=null, tableContent=
岩石类别 数据增强前数量 数据增强后数量
黑色煤 18 2 304
深灰色泥岩 62 1 984
深灰色粉砂质泥岩 39 2 496
灰色细砂岩 17 2 176
灰色泥质粉砂岩 45 2 160
灰黑色泥岩 29 2 320
浅灰色细砂岩 73 2 336
), ArticleFig(id=1225467179932496490, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=EN, label=Table 6, caption=

Data distribution

, figureFileSmall=null, figureFileBig=null, tableContent=
岩石类别 样本数量 训练集 测试集
黑色煤 2 304 1 844 460
深灰色泥岩 1 984 1 588 396
深灰色粉砂质泥岩 2 496 1 997 499
灰色细砂岩 2 176 1 741 435
灰色泥质粉砂岩 2 160 1 728 432
灰黑色泥岩 2 320 1 856 464
浅灰色细砂岩 2 336 1 869 467
汇总 15 776 12 623 3 153
), ArticleFig(id=1225467180117045886, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=CN, label=表6, caption=

数据分布

, figureFileSmall=null, figureFileBig=null, tableContent=
岩石类别 样本数量 训练集 测试集
黑色煤 2 304 1 844 460
深灰色泥岩 1 984 1 588 396
深灰色粉砂质泥岩 2 496 1 997 499
灰色细砂岩 2 176 1 741 435
灰色泥质粉砂岩 2 160 1 728 432
灰黑色泥岩 2 320 1 856 464
浅灰色细砂岩 2 336 1 869 467
汇总 15 776 12 623 3 153
), ArticleFig(id=1225467180276429458, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=EN, label=Table 7, caption=

Model comparison experiment results

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 类别 精确率/% 召回率/% F1/% 平均精确率/% 平均召回率/% 平均F1/%
DenseNet 0 94.48 96.74 95.60 75.72 76.35 75.83
1 69.61 63.64 66.49
2 71.19 68.34 69.73
3 86.16 95.86 90.75
4 59.01 46.99 52.32
5 75.62 84.91 80.01
6 73.98 77.94 75.91
ShuffleNet 0 95.10 96.96 96.02 75.49 76.19 75.34
1 65.35 66.67 66.02
2 69.23 68.54 68.88
3 86.22 94.94 90.37
4 62.45 38.89 47.93
5 75.66 87.07 80.96
6 74.40 80.30 77.24
MbileNetV3 0 95.97 98.26 97.10 82.15 82.41 82.21
1 74.86 68.43 71.50
2 78.32 76.75 77.53
3 88.54 97.71 92.90
4 69.68 65.97 67.78
5 84.44 90.09 87.17
6 83.22 79.66 81.40
), ArticleFig(id=1225467180494533283, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983787000258786, language=CN, label=表7, caption=

模型对比实验结果

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 类别 精确率/% 召回率/% F1/% 平均精确率/% 平均召回率/% 平均F1/%
DenseNet 0 94.48 96.74 95.60 75.72 76.35 75.83
1 69.61 63.64 66.49
2 71.19 68.34 69.73
3 86.16 95.86 90.75
4 59.01 46.99 52.32
5 75.62 84.91 80.01
6 73.98 77.94 75.91
ShuffleNet 0 95.10 96.96 96.02 75.49 76.19 75.34
1 65.35 66.67 66.02
2 69.23 68.54 68.88
3 86.22 94.94 90.37
4 62.45 38.89 47.93
5 75.66 87.07 80.96
6 74.40 80.30 77.24
MbileNetV3 0 95.97 98.26 97.10 82.15 82.41 82.21
1 74.86 68.43 71.50
2 78.32 76.75 77.53
3 88.54 97.71 92.90
4 69.68 65.97 67.78
5 84.44 90.09 87.17
6 83.22 79.66 81.40
)], 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.1671-1815.2400859, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2400859, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2400859, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2400859, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于轻量化网络和迁移学习的岩石智能识别
收藏切换
PDF下载
李顺勇 , 李青辉 , 邢煜曼
科学技术与工程 | 论文·天文学、地球科学 2025,25(5): 1774-1882
收起
收藏切换
科学技术与工程 | 论文·天文学、地球科学 2025, 25(5): 1774-1882
基于轻量化网络和迁移学习的岩石智能识别
全屏
李顺勇 , 李青辉, 邢煜曼
作者信息
  • 山西大学数学科学学院, 太原 030006
  • 李顺勇(1975—),男,汉族,山西大同人,博士,教授。研究方向:统计机器学习与数据挖掘。E-mail:

Intelligent Rock Recognition Based on Lightweight Network and Transfer Learning
Shun-yong LI , Qing-hui LI, Yu-man XING
Affiliations
  • School of Mathematical Sciences, Shanxi University, Taiyuan 030006, China
出版时间: 2025-02-18 doi: 10.12404/j.issn.1671-1815.2400859
文章导航
收藏切换
在岩石图像识别中,实现岩石快速准确的识别是岩石数字化发展的关键。其中,光照、湿度等环境因素引起的图像模糊问题成为岩石智能识别的最大挑战之一。基于此,提出了一种新的深度学习方法(MbileNetV3-small-RegNetX)来识别岩石图像,其适用于移动设备等资源有限的场景。在RegNet网络的基础上采用迁移学习方法,结合MobileNetV3残差结构与通道注意力(squeeze-and-excitation,SE)模块的优势,有效地优化了特征提取与网络结构,并显著提升了检测速度。为验证该方法的准确性,将新模型与当下主流的轻量化模型(DenseNet和ShuffleNet)进行消融对比实验。结果显示,所提模型表现出高精度(82.15%)、快速(0.06 GFLOPs)的特点。此外,该模型对于光照、湿度等环境因素引起的图像模糊具有良好的适应性。
岩石识别  /  深度学习  /  图像分类  /  迁移学习  /  MobileNet网络

In rock image recognition, achieving rapid and accurate identification of rocks is crucial for the digitalization of rocks. Among the challenges faced in intelligent rock recognition is the issue of image blurring caused by environmental factors such as lighting and humidity. In light of this, a novel deep learning approach (MobileNetV3-small-RegNetX) was proposed for rock image recognition, which is suitable for scenarios with limited resources such as mobile devices. Building upon the RegNet network, transfer learning methods, combining the advantages of the MobileNetV3 residual structure with squeeze-and-excitation (SE)modules was employed to effectively optimize feature extraction and network structure, leading to a significant improvement in detection speed. To validate the accuracy of this approach, comparative experiments were conducted between the new model and current mainstream lightweight models (DenseNet and ShuffleNet). The results demonstrate that the new model proposed exhibits high precision (82.15%) and fast processing (0.06 GFLOPs). Additionally, the model demonstrates good adaptability to environmental factors such as lighting and humidity-induced image blurring.

rock recognition  /  deep learning  /  image classification  /  transfer learning  /  MobileNet network
李顺勇, 李青辉, 邢煜曼. 基于轻量化网络和迁移学习的岩石智能识别. 科学技术与工程, 2025 , 25 (5) : 1774 -1882 . DOI: 10.12404/j.issn.1671-1815.2400859
Shun-yong LI, Qing-hui LI, Yu-man XING. Intelligent Rock Recognition Based on Lightweight Network and Transfer Learning[J]. Science Technology and Engineering, 2025 , 25 (5) : 1774 -1882 . DOI: 10.12404/j.issn.1671-1815.2400859
近年来,深度学习算法已广泛应用于岩石领域,其中岩石图像识别技术在地质勘探、矿产资源开发和环境监测等领域展示出巨大潜力[1-2]。为了实现自动化、高效率、低成本和低风险的岩石图像识别,学者们积极探索并提出了多种基于机器学习算法的岩石图像识别技术[3]。这些技术主要涵盖卷积神经网络(convolutional neural network,CNN)、深度信念网络(deep belief network,dBN)、稀疏表示分类器(sparse representation classifier,SRC)3个方面。值得注意的是,CNN作为一种经典而高效的技术,已成为岩石图像识别领域广泛关注的焦点所在[4-6]
王李管等[7]以VGG19为骨干网络,提出了一种选矿的岩石图像识别模型,这一模型具有收敛速度快、分类精度高等优势,其预测准确率达97.51%。但是以VGG19作为主干网络,会增大模型的运算开销,其在资源有限的应用场景中常难以为继;许振浩等[8]提出了一种基于ResNet-101的岩性智能识别算法,这一算法具有识别稳定性好、泛化能力强等优点,其模型最高F1可达90.7%。但是,这一成果受限于数据集图像较为简单,故并未对不同自然环境条件下的岩石图像加以研究。谭永健等[9]基于Xception网络,提出了一种针对10类岩石的智能图像识别方法,该方法结合通道可分离卷积、残差连接、迁移学习等技术,最终预测精度达86%。但是,Xception网络大量训练数据的需求以及较高的模型复杂度,使其难以在实际中得到较好应用;赵兴东等[10]基于InceptionV3网络,提出了一种针对8种岩石的迁移学习岩石分类模型,其模型的平均准确率超过了80%,并且具有良好的鲁棒性。袁硕等[11]以ShuffleNetV2网络为源模型,插入ECA模块,使用Mish激活函数代替ReLu激活函数,并引入深度可分离卷积进行模型构建。该实验结果表明,改进后的算法结构简单,同时具有轻量化的特点。但是,这一研究的实验数据为正常光照条件下的岩石图像,并未考虑不同湿度和不同光照下岩石表面的纹理和粒径等问题。
基于此,现提出一种新的深度学习岩石智能识别方法(MbileNetV3-small-RegNetX),该方法结合深度可变性、批归一化、瓶颈结构(bottleneck structure,bneck)和通道注意力(channel attention)等技术,同时以迁移学习[12]来加快模型训练速度,构建岩石岩性的智能识别与分类模型。期望新方法能够高效地、快速地识别岩样,并且可以部署在小型移动设备上[13-15]
通道可分离卷积通过将标准卷积分解为逐通道卷积(depthwise convolution,DW)和逐点卷积(pointwise convolution,PW)两个步骤,以提高模型的效率和性能。具体而言,对于具有C个输入通道和K个卷积核的输入特征图,其进行深度可分离卷积的实现步骤如下。
步骤1 针对每个输入通道执行单独的卷积操作。该卷积操作采用一个深度为1的卷积核,它能生成C个单通道的卷积特征图,如图1所示。这一步等效于逐个对每个通道进行标准卷积操作。
步骤2 对之前生成的C个单通道卷积特征图进行PW卷积(核为1×1)操作,如图2所示。这个操作可以看作是在通道维度上的线性变换,以产生最终的输出特征图。
通道可分离卷积通过分解原有的大型卷积操作为两个小型卷积,极大地改善了模型运算量的问题。这不仅使模型具有更少的计算需求,还可以加速模型的训练和推理过程。
与传统残差结构[16-17]不同。倒残差结构首先对通道进行升维(核为1×1),接着通过通道可分离卷积来抽取特征(核为3×3),最后再进行通道降维(核为1×1)。呈两头小、中间大的梭形结构,如图3所示。倒残差结构不仅可以保持准确率和泛化性能,而且具有更低的计算和存储资源需求。
SE(squeeze-and-excitation)模块由一个全局平均池化层和两个全连接(fully connected,FC)层组成,如图4所示。首先,通过一个全局平均池化操作,将输入特征图的空间尺寸压缩为一个特征向量。在这个过程中,每个特征通道的信息被整合成一个通道的统计特征。这个压缩操作能够捕捉到特征通道的全局相关性。
接下来,引入两个FC层,其中,FC1的节点个数为输入通道的1/4,激活函数是ReLu。FC2的节点个数等于输出通道数,激活函数是H-Sigmoid。这样,增加了重要特征通道的权重,有助于提高网络的表示能力和分类准确性。
Swish的计算如式(1)所示。
Swish(x)=xsigmoid(x)
Swish图像如图5所示,其具有无上界、有下界、平滑、非单调等特点,可使神经网络层具有更丰富的表现能力。但Swish还存在一定的不足,其计算、求导复杂,对量化过程不友好,即计算量比较大。
H-Swish函数[18]优于Swish函数,可显著降低网络中的计算量,其计算如式(2)所示。
$\operatorname{H-Swish}(x)=x \frac{\operatorname{ReLu6}(x+3)}{6}$
选择H-Swish函数有助于解决计算量大的问题,同时其近似线性性质好、扩展性强。实践证明,相比传统的Swish激活函数,H-Swish的简化计算形式不仅提高了模型的计算速度,还使梯度传播更容易。因此,在模型设计的部分模块中选择该函数作为激活函数。
主要从两个角度调整核心模块,一方面在bneck单元中引入SE通道注意力机制[19-20]来提升模型的性能;另一方面采用H-Swish作为SE模块中FC2的激活函数,以提高模型的计算速度。具体结构如图6所示,在bottleneck模块中增加了通道重要性的学习和调整模块,即所提的SE模块,使得模型能够自适应地学习通道权重,从而更好地聚焦于重要的通道特征,以提高特征的表达能力和区分性。
常用的MbileNetV3[21-24]网络模型有Mbile-NetV3-Large和MbileNetV3-Small,综合考量模型的参数量以及训练效果,提出了MbileNetV3-Small-RegNetX网络,其网络结构如表1所示。
采用MbileNetV3-Small进行特征提取后引入了RegNet的head网络,即head网络由全局平均池化层和一个全连接层组成。相较于传统的网络结构,该结构更为简明,突出了高效计算与低资源消耗的特点,使得模型在计算资源有限环境下仍表现出色。
实施的技术路线如图7所示。首先,针对公开数据进行数据清洗,得到283张bpm格式的图片。其次,采用图像裁剪、数据增强等方法来丰富样本,共获得15 776张jpg格式的图片,并以9∶1的比例划分数据集。最后,固定RegNetX为主网络,分别以DenseNet-121、MobileNetV3-small、ShuffleNet-v1为骨干网络进行模型训练。
实验使用公开的岩石图像数据集——第九届“泰迪杯”数据挖掘挑战赛B题数据集,该数据集包含不同环境条件下的7类岩石,如图8所示,共315张岩石图片,在数据增强之前,进行数据清洗,剩余283张岩石图片,图像大小均为4 096像素×3 000像素,具体数据分布如表2所示。
受限于岩石图像数据集中样本数量较少,并且各类岩石图像存在样本类别不均衡的问题,因此,通过数据裁剪、数据增强[25]等方法扩充岩石数据集。一方面,采用不同尺寸的网格对岩石图像进行网格裁剪,如表3所示,初步扩充数据集,另外,针对裁剪后的图片,采用多种方式(如表4所示)进行数据增强,具体增强效果如图9所示。最终,使得数据集中各岩石种类的图像占比大致相等,数据增强前后效果对比如表5所示。
通过数据增强,获得了丰富的样本数据。随后,实验以9∶1的比例划分数据集,获得训练集与测试集,具体数据分布如表6所示。
使用配置有Intel E5 CPU处理器和NVIDIA GeForce RTX 3090显卡的计算机进行实验。该计算机运行在Windows 10企业版操作系统下,并配备有14 GB的内存。此外,选用了Pytorch 1.7.1框架和Python 3.7.16版本作为实验工具,所有实验代码均是在该环境下进行开发和运行。
在有效性实验中,使用了公开的岩石图像数据集进行实验。实验数据包含12 623张训练图像和3 153张测试图像。将模型训练的批量大小设置为32,使用SGD优化器进行参数更新,学习率设置为0.001,并进行了50个epoch的训练。
实验结果如图10所示,与DenseNet-121和ShuffleNet-v1相比,提出的MbileNetV3-small-RegNetX新模型分类效果显著。如图10(a)所示,该模型相较于其他两个模型具有更快的损失收敛速度,同时具备更高的预测精度,如图10(b)所示。由此可见,本文模型能够在简化网络的前提下,精准地捕获到岩石图像的纹理特征和粒径细节。
混淆矩阵是用于评估分类模型性能的一种常见指标,也称为误差矩阵。混淆矩阵如图11所示,可以看出,相比于DenseNet-121[图11(a)]和ShuffleNet-v1[图11(b)]为骨干网络训练的模型,所提MbileNetV3-small-RegNetX模型[图11(c)]具备更强的分类性能,并且各类的预测准确度均优于前两个模型。此外,通过观察对角线识别正确数量发现,3种模型对于黑色煤(0)、深灰色粉砂质泥岩(2)、灰色细砂岩(3)、灰黑色泥岩(5)、浅灰色细砂岩(6)的识别能力均显著,而ShuffleNet-V1-RegNetX和DenseNet-121-RegNetX对于深灰色泥岩(1)、灰色泥质粉砂岩(4)的识别能力不足,值得庆幸的是,MbileNetV3-small-RegNetX很好地弥补了这两类岩石识别的缺陷,其在训练集上的识别精度高达83.41%。
在分类问题中,通常需要对样本进行预测并将其分类为正类或负类。在进行预测时,可能会出现4种情况:真正类(TP),假正类(FP),真负类(TN),假负类(FN)。根据上述情况,可以计算出准确率(P)、精确率(A)、召回率(R)、F1等评价指标。其计算公式如下。
$P=\frac{\mathrm{TP}}{\mathrm{TP}+\mathrm{FP}} \times 100 \%$
$R=\frac{\mathrm{TP}}{\mathrm{TP}+\mathrm{FN}} \times 100 \%$
$A=\frac{\mathrm{TP}+\mathrm{TN}}{\mathrm{TP}+\mathrm{FP}+\mathrm{TN}+\mathrm{FN}} \times 100 \%$
$F_{1}=\frac{2 P R}{P+R} \times 100 \%$
为更合理地评估本文模型的泛化能力,比较不同岩石岩性智能识别模型的性能差异,基于上述评价指标在测试集上进行模型验证,具体各模型对比验证的指标值如表7所示。
表7中,DenseNet、ShuffleNet和MobileNet作为Backbone的网络分别获得了75.83%、75.34%和82.21%的Mean F1。其中所提的MobileNetV3-small-RegNetX表现最佳,该模型通过引入SE注意力机制和倒残差结构的轻量化模块,实现了在降低计算量和参数量的同时,保持更高的精度。
具体而言,MbileNetV3-small-RegNetX在类别0(黑色煤)方面,精确率、召回率和F1各方面均表现出色。它的精确率达到了95.97%,召回率为98.26%,F1达到了97.10%。这表明类别0的分类结果非常准确,模型能够很好地捕捉到此类岩石的纹理特征。然而,类别1(深灰色泥岩)和4(灰色泥质粉砂岩)的评估结果相对较低,F1分别为71.50%和67.78%,其中类别1的精确率为74.86%,召回率为68.43%,而类别4的精确率和召回率相对低一些,分别为69.68%和65.97%,这是由于灰色泥质粉砂岩类内(同一岩石类别)与类间(不同岩石类别)差异均比较大,使得模型对这类岩石的纹理特征学习困难,进而导致模型无法出色的识别这类岩石。此外,类别2(深灰色粉砂质泥岩)和6(浅灰色细砂岩)在精确率、召回率和F1方面呈现出相似的结果。它们的精确率分别为78.32%和83.22%,召回率分别为76.75%和79.66%,F1分别为77.53%和81.40%。这表明对于类别2和类别6的分类结果相对较好,并且分类器对这些类别的特征进行捕获时有良好的性能表现。同时,类别3(灰色细砂岩)和类别5(灰黑色泥岩)也获得了相对较高的F1。类别3的精确率为88.54%,召回率为97.71%,F1达到92.90%。类别5的精确率为84.44%,召回率为90.09%,F1为87.17%。这说明在分类任务中,对于类别3和类别5的分类准确性更显著。
将深度学习算法应用于岩石图像识别中,通过所提出的MobileNetV3-small-RegNetX模型,实现了对岩石样品快速准确的识别。该模型以轻量化特征提取与简化网络结构为核心,显著提高了岩石图像识别的速度和精度。实验结果如下。
(1)本文模型在岩石图像识别中表现出优异的性能。其网络精度高,在测试集上,精确率达到了82.15%,同时运算速度快,计算量仅需0.06GFLOPs,其中GFLOPs(giga floating-point operations per second)是指每秒10亿次的浮点运算数,是衡量计算机计算能力的一个重要指标。
(2)该模型还展现出对光照、湿度等环境条件变化的良好适应性,能够有效应对环境因素引起的图像模糊等问题。将来的研究将从高效的特征提取方法入手,以进一步提高分类的速度和准确性。
  • 国家自然科学基金(61976128)
  • 国家自然科学基金(62072293)
  • 山西省基础研究计划(202303021221054)
  • 山西省回国留学人员科研教研资助项目(2024-002)
  • 山西省研究生教育教学改革课题(2022YJJG010)
参考文献 引证文献
排序方式:
[1]
许振浩, 马文, 李术才, 等. 岩性识别: 方法、现状及智能化发展趋势[J]. 地质论评, 2022, 68(6): 2290-2304.
Xu Zhenhao, Ma Wen, Li Shucai, et al. Lithological identification: methods, current situation, and intelligent development trend[J]. Geological Review, 2022, 68(6): 2290-2304.
[2]
夏文鹤, 谢万洋, 唐印东, 等. 砂样岩屑图像特征的岩性智能高效识别[J]. 石油地球物理勘探, 2023, 58(3): 495-506.
Xia Wenhe, Xie Wanyang, Tang Yindong, et al. Intelligent and efficient identification of lithology based on image features of sand samples and rock debris[J]. Petroleum Geophysical Exploration, 2023, 58(3): 495-506.
[3]
仝容超. 机器学习在岩性智能识别中的应用研究进展[J]. 化工矿物与加工, 2022, 51(8): 43-47, 54.
Tong Rongchao. Research progress on the application of machine learning in intelligent lithology recognition[J]. Chemical Minerals and Processing, 2022, 51(8): 43-47, 54.
[4]
高婷, 杨洋, 何江. 人工智能在岩石图像上的应用综述[J]. 中国石油和化工标准与质量, 2020, 40(20): 98-100.
Gao Ting, Yang Yang, He Jiang. Overview of the application of artificial intelligence in rock images[J]. Chinese Petroleum and Chemical Standards and Quality, 2020, 40(20): 98-100.
[5]
Xu Z H, Ma W, Lin P, et al. Deep learning of rock microscopic images for intelligent lithology identification: neural network comparison and selection[J]. Journal of Rock Mechanics and Geotechnical Engineering, 2022, 14(4): 1140-1152.
[6]
Hou Z, Wei J, Shen J, et al. Intelligent lithology identification methods for rock images based on object detection[J]. Natural Resources Research, 2023, 32(6): 2965-2980.
[7]
王李管, 陈斯佳, 贾明滔, 等. 基于深度学习的黑钨矿图像识别选矿方法[J]. 中国有色金属学报, 2020, 30(5): 1192-1201.
Wang Liguan, Chen Sijia, Jia Mingtao, et al. Deep learning based image recognition and beneficiation method for tungsten ore[J]. Chinese Journal of Nonferrous Metals, 2020, 30(5): 1192-1201.
[8]
许振浩, 马文, 林鹏, 等. 基于岩石图像迁移学习的岩性智能识别[J]. 应用基础与工程科学学报, 2021, 29(5): 1075-1092.
Xu Zhenhao, Ma Wen, Lin Peng, et al. Intelligent lithology recognition based on rock image transfer learning[J]. Journal of Applied Fundamentals and Engineering Science, 2021, 29(5): 1075-1092.
[9]
谭永健, 田苗, 徐德馨, 等. 基于Xception网络的岩石图像分类识别研究[J]. 地理与地理信息科学, 2022, 38(3): 17-22.
Tan Yongjian, Tian Miao, Xu Dexin, et al. Research on rock image classification and recognition based on Xception network[J]. Geography and Geographic Information Science, 2022, 38(3): 17-22.
[10]
赵兴东, 王宏宇, 白夜. 基于卷积神经网络迁移学习模型的矿岩智能识别方法[J]. 矿床地质, 2023, 42(5): 1003-1010.
Zhao Xingdong, Wang Hongyu, Bai Ye. A mining and rock intelligent recognition method based on convolutional neural network transfer learning model[J]. Deposit Geology, 2023, 42(5): 1003-1010.
[11]
袁硕, 刘玉敏, 安志伟, 等. 基于改进ShuffleNetV2网络的岩石图像识别[J]. 吉林大学学报(信息科学版), 2023, 41(3): 450-458.
Yuan Shuo, Liu Yumin, An Zhiwei, et al. Rock image recognition based on improved ShuffleNetV2 network[J]. Journal of Jilin University (Information Science Edition), 2023, 41(3): 450-458.
[12]
熊峰, 廖一凡, 曹伟腾, 等. 基于卷积神经网络-深度迁移学习的岩性自动识别研究[J]. 安全与环境工程, 2023, 30(4): 26-34.
Xiong Feng, Liao Yifan, Cao Weiteng, et al. Research on automatic lithology recognition based on convolutional neural network deep transfer learning[J]. Safety and Environmental Engineering, 2023, 30(4): 26-34.
[13]
肖振久, 杨晓迪, 魏宪, 等. 改进的轻量型网络在图像识别上的应用[J]. 计算机科学与探索, 2021, 15(4): 743-753.
Xiao Zhenjiu, Yang Xiaodi, Wei Xian, et al. The application of improved lightweight networks in image recognition[J]. Computer Science and Exploration, 2021, 15(4): 743-753.
[14]
杜睿山, 宋健辉, 孟令东. 基于注意力机制的岩石铸体薄片轻量化分割[J]. 计算机技术与发展, 2023, 33(10): 128-134.
Du Ruishan, Song Jianhui, Meng Lingdong. Lightweight segmentation of rock casting thin sections based on attention mechanism[J]. Computer Technology and Development, 2023, 33(10): 128-134.
[15]
陈开峰, 俞伟聪, 唐雁文, 等. 基于轻量化深度学习网络的数字仪表识别[J]. 科学技术与工程, 2023, 23(2): 674-680.
Chen Kaifeng, Yu Weicong, Tang Yanwen, et al. Digital instrument recognition based on lightweight deep learning networks[J]. Science Technology and Engineering, 2023, 23(2): 674-680.
[16]
刘今子, 杜文颖, 董驰, 等. 基于色彩空间和深度残差网络ResNet-50的复杂岩性油气藏岩石样本智能分类及识别[J]. 科学技术与工程, 2023, 23(29): 12628-12637.
Liu Jinzi, Du Wenying, Dong Chi, et al. Intelligent classification and recognition of complex lithology oil and gas reservoir rock samples based on color space and depth residual network ResNet-50[J]. Science Technology and Engineering, 2023, 23(29): 12628-12637.
[17]
王明明, 孙寅静, 孙晓云, 等. 基于深度残差网络与迁移学习的地形识别方法[J]. 科学技术与工程, 2023, 23(9): 3779-3786.
Wang Mingming, Sun Yinjing, Sun Xiaoyun, et al. A terrain recognition method based on deep residual networks and transfer learning[J]. Science Technology and Engineering, 2023, 23(9): 3779-3786.
[18]
Marriam N, Ali J, Aun I. ResNet-Swish-Dense54: a deep learning approach for deepfakes detection[J]. The Visual Computer, 2022, 39(12): 6323-6344.
[19]
翟晓岩, 高刚, 李勇根, 等. 融合注意力机制的二维卷积神经网络测井曲线重构方法[J]. 石油地球物理勘探, 2023, 58(5): 1031-1041.
Zhai Xiaoyan, Gao Gang, Li Yonggen, et al. A two-dimensional convolutional neural network well logging curve reconstruction method integrating attention mechanism[J]. Petroleum Geophysical Exploration, 2023, 58(5): 1031-1041.
[20]
凌同华, 陈梓浓, 张胜, 等. 岩石岩性轻量化网络识别方法及其隧道工程应[J]. 铁道科学与工程学报, 2023, 20(9): 3604-3615.
Ling Tonghua, Chen Zinong, Zhang Sheng, et al. A lightweight network recognition method for rock lithology and its application in tunnel engineering[J]. Journal of Railway Science and Engineering, 2023, 20(9): 3604-3615.
[21]
Jin G, Liu Y L, Qin P L, et al. An end-to-end steel surface classification approach based on EDCGAN and MobileNet V2[J]. Sensors, 2023, 23(4): 1953-1953.
[22]
Rajendra B S P, Sai B C. Mobilenetv3: a deep learning technique for human face expressions identification[J]. International Journal of Information Technology, 2023, 15(6): 3229-3243.
[23]
Zhang R C, Yuan Y C, Meng X, et al. A multitask model based on MobileNetV3 for fine-grained classification of jujube varieties[J]. Journal of Food Measurement and Characterization, 2023, 17(5): 4305-4317.
[24]
Yang Y, Han J. Real-time object detector based MobileNetV3 for UAV applications[J]. Multimedia Tools and Applications, 2022, 82(12): 18709-18725.
[25]
孔二伟, 张亚邦, 李佳悦, 等. 面向煤矿井下低光照图像的增强方[J]. 工矿自动化, 2023, 49(4): 62-69, 85.
Kong Erwei, Zhang Yabang, Li Jiayue, et al. An enhancement method for low light images in coal mine underground[J]. Industrial and Mining Automation, 2023, 49(4): 62-69, 85.
2025年第25卷第5期
PDF下载
351
138
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2400859
  • 接收时间:2024-01-30
  • 首发时间:2025-07-29
  • 出版时间:2025-02-18
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-01-30
  • 修回日期:2024-11-15
基金
国家自然科学基金(61976128)
国家自然科学基金(62072293)
山西省基础研究计划(202303021221054)
山西省回国留学人员科研教研资助项目(2024-002)
山西省研究生教育教学改革课题(2022YJJG010)
作者信息
    山西大学数学科学学院, 太原 030006
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2400859
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