检索结果-南通市图书馆

Microstructure recognition of steels by machine learning based on visual attention mechanism

在线全文

学校读者我要写书评

暂无评论

Journal of Iron and Steel Research International 2024年第4期31卷 909-923页

作者： Xing-yu Chen lin Cheng Cheng-yang Hu Yu-peng Zhang kai-ming Wu The State Key Laboratory of Refractories and Metallurgy Hubei Province Key Laboratory of Systems Science on Metallurgical ProcessingInternational Research Institute for Steel TechnologyCollaborative Center on Advanced SteelsWuhan University of Science and TechnologyWuhan 430081HubeiChina Metals Valley and Band(Foshan)Metallic Composite Materials Co. Ltd.Foshan 528000GuangdongChina

U-Net has achieved good performance with the small-scale datasets through skip connections to merge the features of the low-level layers and high-level layers and has been widely utilized in biomedical image segmentation as well as recent microstructure image segregation of the *** representative visual attention mechanism modules,named as squeeze-and-excitation networks,convolutional block attention module,and extended calibration algorithm,were intro-duced into the traditional U-Net architecture to further improve the prediction *** is found that compared with the original U-Net architecture,the evaluation index of the improved U-Net architecture has been significantly improved for the microstructure segmentation of the steels with the ferrite/martensite composite microstructure and pearlite/ferrite composite microstructure and the complex martensite/austenite island/bainite microstructure,which demonstrates the advantages of the utilization of the visual attention mechanism in the microstructure *** reasons for the accuracy improvement were discussed based on the feature maps analysis.

关键词： Microstructure recognition-Steel Machine learning Visual attention mechanism Visualization

Quasinormal oscillations and late-time tail of massless scalar perturbations of a magnetized black hole in Rastall gravity

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Physics C 2022年第10期46卷 215-229页

作者： Cai-Ying Shao Yu-Jie Tan Cheng-Gang Shao kai lin Wei-Liang Qian MOE Key Laboratory of Fundamental Physical Quantities Measurement Hubei Key Laboratory of Gravitation and Quantum PhysicsPGMFand School of PhysicsHuazhong University of Science and Technology430074 WuhanChina Hubei Subsurface Multi-scale Imaging Key Laboratory Institute of Geophysics and GeomaticsChina University of Geosciences430074 WuhanChina Escola de Engenharia de Lorena Universidade de Sao Paulo12602-810LorenaSPBrazil Faculdade de Engenharia de Guaratinguetá Universidade Estadual Paulista12516-410GuaratinguetáSPBrazil and Center for Gravitation and Cosmology School of Physical Science and TechnologyYangzhou University225002 YangzhouChina

In this study,we investigate the quasinormal mode and late-time tail of charged massless scalar perturbations of a black hole in generalized Rastall *** black hole metric in question is spherically symmetric,accompanied by a power-Maxwell field surrounded by a quintessence *** show that the massless scalar field,when dressed up with the magnetic field,acquires an effective mass,which significantly affects the properties of the resultant quasinormal oscillations and late-time ***,the quasinormal frequencies become distorted and might even be unstable for particular spacetime ***,the exponent of the usual power-law tail is modified according to the modification in the structure of the branch cut of the retarded Green s *** particular,as the effective mass is generated dynamically owing to the presence of the magnetic field,we may consider a process through which the field is gradually removed from the spacetime *** this context,while the quasinormal oscillations converge to the case of massless perturbations,we argue that the properties of resultant late-time tails do not fall back to their massless *** relevant characteristics are investigated using numerical and analytic approaches.

关键词： black hole quasinormal modes late-time tail Rastall gravity

Modeling and Scheduling Optimization for Bulk Ore Blending Process

在线全文

学校读者我要写书评

暂无评论

Journal of Iron and Steel Research International 2012年第9期19卷 20-28页

作者： SONG Chun-yue , HU kai-lin , LI Ping ( State Key Laboratory of Industrial Control Technology , Zhejiang University , Hangzhou 310027 , Zhejiang , China ) State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou Zhejiang China

A new scheduling model for the bulk ore blending process in iron-making industry is presented , by converting the process into an assembly flow shop scheduling problem with sequence-depended setup time and limited intermediate buffer , and it facilitates the scheduling optimization for this *** find out the optimal solution of the scheduling problem , an improved genetic algorithm hybridized with problem knowledge-based heuristics is also proposed , which provides high-quality initial solutions and fast searching *** efficiency of the algorithm is verified by the computational experiments.

关键词： bulk ore blending assembly flow shop sequence-depended setup time limited intermediate buffer genetic algorithm

Rational design multi-color-emissive chemiluminescent carbon nanodots in a single solvothermal reaction

在线全文

学校读者我要写书评

暂无评论

Nano Research 2024年第6期17卷 4651-4660页

作者： Guang-Song Zheng Cheng-Long Shen Yuan Deng kai-kai Liu Jin-Hao Zang lin Dong Qing Lou Chong-Xin Shan Henan Key Laboratory of Diamond Optoelectronic Materials and Devices Key Laboratory of Materials PhysicsMinistry of Educationand School of Physics and MicroelectronicsZhengzhou UniversityZhengzhou 450052China

Recently,the chemiluminescence(CL)induced by carbon nanodots(CDs)has intrigued researchers’extensive interests in various applications due to its special light emission ***,the difficulty of synthesizing chemiluminescent CDs with full-spectrum emission severely hinders the further regulation of the CL emission ***,the multi-color-emissive chemiluminescent CDs are rational designed and further synthesized by regulating the sp2-hybrid core and sp3-hybrid surface from the citrate-ammonia molecular in a single solvothermal *** experimental characterizations and density functional theory calculations reveal that the higher temperature can promote the crosslinking polymerization/carbonization of carbon core and the higher protonation of solvent can determine the core size of final CDs,resulting in the variant CL emission from molecular-,crosslinking-and ***,the CL emission of the CDs can be further synthesized by tuning the luminescence chromophores in the formation process via regulating the temperature and solvent,enabling the applications of the CL CDs in illumination and information *** study paves a new technology to understand the luminescence of CDs and affords an industry translational potential over traditional chemiluminescent molecular.

关键词： carbon nanodots chemiluminescence regulation energy level alignment mechanism

纳米氧化镍长期暴露对活性污泥物化特性及微生物代谢的影响

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

中国环境科学 2024年第5期44卷 2449-2459页

作者：王宇超杨垒崔珅郭淋凯路颢琪李玉彩孟红艳任勇翔西安建筑科技大学陕西省环境工程重点实验室西安710055 西安建筑科技大学西北水资源与环境生态教育部重点实验室西安710055

为揭示纳米氧化镍(NiO NPs)在复杂环境体系中的生物毒性效应,以活性污泥为研究对象,探讨了NiO NPs(0~200mg/L)长期暴露对序批式生物反应器运行效能、污泥性能以及微生物代谢作用的影响.结果表明,低浓度(0~50mg/L)NiO NPs对活性污泥运行... 详细信息

为揭示纳米氧化镍(NiO NPs)在复杂环境体系中的生物毒性效应,以活性污泥为研究对象,探讨了NiO NPs(0~200mg/L)长期暴露对序批式生物反应器运行效能、污泥性能以及微生物代谢作用的影响.结果表明,低浓度(0~50mg/L)NiO NPs对活性污泥运行效能影响不显著,高浓度(100~200mg/L)NiO NPs对氨氮和COD去除有明显抑制作用,分别降低了8%和20%.随着NiO NPs的浓度增加,硝化过程关键功能酶氨单加氧酶(AMO)和羟胺氧化酶(HAO)活性分别降低55.71%和62.09%,乳酸脱氢酶(LDH)释放量增加了113.06%.同时,NiO NPs对活性污泥絮凝性产生负面影响,污泥平均粒度增加,絮体形状松散,絮凝性略有降低.胞外聚合物(EPS)整体呈下降趋势,高浓度下蛋白质(N-H,C=O)和多糖(C-O,C-C,C-O-C,C-O-H)相关官能团的强度减弱,三维荧光蛋白特征峰强度大幅降低.但死亡微生物的生物分解和应激反应促进了EPS中微生物代谢和酪氨酸蛋白类物质生成.此外,活性污泥中微生物群落的多样性和稳定性均受到NiO NPs的影响.PICRUSt2预测显示,微生物的代谢和遗传信息处理相关的代谢通路均受到NiO NPs的显著抑制.因此,NiO NPs通过改变微生物群落结构和代谢通路影响活性污泥硝化作用和有机物的去除.

关键词：纳米氧化镍活性污泥生物硝化胞外聚合物微生物群落代谢

24个月内疾病进展在套细胞淋巴瘤中的预后意义

在线全文

学校读者我要写书评

暂无评论

中国实验血液学杂志 2024年第3期32卷 702-707页

作者：马瑞雪张芊芊陈惠敏胡瑾陆丰艺韩倩楠李振宇徐开林陈伟徐州医科大学附属医院血液科江苏徐州221002 江苏省宿迁市第一人民医院血液科江苏宿迁223800

目的:探讨24个月内疾病进展(POD24)对套细胞淋巴瘤(MCL)患者总生存的影响,比较POD24和非POD24患者的临床特征。方法:回顾性分析2010年1月至2020年8月徐州医科大学附属医院收治的有治疗指征且经过正规治疗的MCL患者50例,根据POD24发生情... 详细信息

目的:探讨24个月内疾病进展(POD24)对套细胞淋巴瘤(MCL)患者总生存的影响,比较POD24和非POD24患者的临床特征。方法:回顾性分析2010年1月至2020年8月徐州医科大学附属医院收治的有治疗指征且经过正规治疗的MCL患者50例,根据POD24发生情况进行分组,进行预后评估及临床特征比较。结果:单因素Cox回归分析结果显示,是否发生POD24、PLT、白蛋白、MIPI评分、ECOG PS评分、LDH均是影响初诊MCL患者OS的因素(P<0.05)。对单因素分析中有意义的指标进行多因素Cox回归分析,结果显示,发生POD24[HR=16.797(95%CI:3.671-76.861),P=0.001]、白蛋白<40 g/L[HR=3.238(95%CI:1.095-9.572),P=0.034]、ECOG PS≥2分[HR=4.005(95%CI:1.033-15.521),P=0.045]是影响MCL患者OS的独立危险因素。POD24患者较非POD24患者起病时PLT<100×10^(9)/L的发生率(33.3%vs 5.9%,P=0.033)及ECOG PS≥2分的发生率(45.5%vs 5.9%,P=0.040)明显增高。结论:POD24为影响MCL患者总生存的独立预后不良因素,起病时伴PLT<100×10^(9)/L、ECOG PS≥2分的患者发生POD24比例较高。

关键词：套细胞淋巴瘤 24个月内疾病进展预后

Deep learning CNN-APSO-LSSVM hybrid fusion model for feature optimization and gas-bearing prediction

在线全文

学校读者我要写书评

暂无评论

Petroleum Science 2024年第4期21卷 2329-2344页

作者： Jiu-Qiang Yang Nian-Tian lin kai Zhang Yan Cui Chao Fu Dong Zhang College of Earth Sciences and Engineering Shandong University of Science and Technology Laboratory for Marine Mineral Resources Qingdao National Laboratory for Marine Science and Technology Transportation Institute of Inner Mongolia University Key Laboratory of Gas Hydrate Qingdao Institute of Marine Geology Ministry of Natural Resources

Conventional machine learning(CML) methods have been successfully applied for gas reservoir prediction. Their prediction accuracy largely depends on the quality of the sample data; therefore, feature optimization of the input samples is particularly important. Commonly used feature optimization methods increase the interpretability of gas reservoirs; however, their steps are cumbersome, and the selected features cannot sufficiently guide CML models to mine the intrinsic features of sample data efficiently. In contrast to CML methods, deep learning(DL) methods can directly extract the important features of targets from raw data. Therefore, this study proposes a feature optimization and gas-bearing prediction method based on a hybrid fusion model that combines a convolutional neural network(CNN)and an adaptive particle swarm optimization-least squares support vector machine(APSO-LSSVM). This model adopts an end-to-end algorithm structure to directly extract features from sensitive multicomponent seismic attributes, considerably simplifying the feature optimization. A CNN was used for feature optimization to highlight sensitive gas reservoir information. APSO-LSSVM was used to fully learn the relationship between the features extracted by the CNN to obtain the prediction results. The constructed hybrid fusion model improves gas-bearing prediction accuracy through two processes of feature optimization and intelligent prediction, giving full play to the advantages of DL and CML methods. The prediction results obtained are better than those of a single CNN model or APSO-LSSVM model. In the feature optimization process of multicomponent seismic attribute data, CNN has demonstrated better gas reservoir feature extraction capabilities than commonly used attribute optimization methods. In the prediction process, the APSO-LSSVM model can learn the gas reservoir characteristics better than the LSSVM model and has a higher prediction accuracy. The constructed CNN-APSO-LSSVM mode

关键词： Multicomponent seismic data Deep learning Adaptive particle swarm optimization Convolutional neural network Least squares support vector machine Feature optimization Gas-bearing distribution prediction

BAR:a branch-alternation-resorting algorithm for locality exploration in graph processing

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

High Technology Letters 2024年第1期30卷 31-42页

作者：邓军勇 WANG Junjie JIANG lin XIE Xiaoyan ZHOU kai School of Electronic Engineering Xi'an University of Posts and TelecommunicationsXi'an 710121P.R.China School of Computer Xi'an University of Science and TechnologyXi'an 710054P.R.China School of Computer Xi'an University of Posts and TelecommunicationsXi'an 710121P.R.China

Unstructured and irregular graph data causes strong randomness and poor locality of data accesses in graph *** paper optimizes the depth-branch-resorting algorithm(DBR),and proposes a branch-alternation-resorting algorithm(BAR).In order to make the algorithm run in parallel and improve the efficiency of algorithm operation,the BAR algorithm is mapped onto the reconfigurable array processor(APR-16)to achieve vertex reordering,effectively improving the locality of graph *** paper validates the BAR algorithm on the GraphBIG framework,by utilizing the reordered dataset with BAR on breadth-first search(BFS),single source shortest paht(SSSP)and betweenness centrality(BC)algorithms for *** results show that compared with DBR and Corder algorithms,BAR can reduce execution time by up to 33.00%,and 51.00%*** terms of data movement,the BAR algorithm has a maximum reduction of 39.00%compared with the DBR algorithm and 29.66%compared with Corder *** terms of computational complexity,the BAR algorithm has a maximum reduction of 32.56%compared with DBR algorithm and53.05%compared with Corder algorithm.

关键词： graph processing vertex reordering branch-alternation-resorting algorithm(BAR) reconfigurable array processor

基于CiteSpace的中医药防治心肌缺血再灌注损伤知识图谱分析

在线全文

学校读者我要写书评

暂无评论

世界中西医结合杂志 2024年第1期19卷 9-21页

作者：贾海女李瑞菡黄凯琳张健真张笑笑张雨晴王茜吴焕林北京中医药大学东直门医院心血管科北京100007

目的探讨国内外中医药防治心肌缺血再灌注损伤(Myocardial ischemia reperfusion injury,MIRI)的发展前沿及研究热点,为进一步相关研究提供参考。方法检索CNKI和WOS建库至2023年10月31日期间中医药防治MIRI的文献,用CiteSpace 6.2.R4进... 详细信息

目的探讨国内外中医药防治心肌缺血再灌注损伤(Myocardial ischemia reperfusion injury,MIRI)的发展前沿及研究热点,为进一步相关研究提供参考。方法检索CNKI和WOS建库至2023年10月31日期间中医药防治MIRI的文献,用CiteSpace 6.2.R4进行作者合作网络图谱、机构合作网络图谱、关键词聚类图谱、关键词突现图谱展示并进行分析。结果共纳入2865篇中文文献,160篇英文文献,国内外主要受关注的研究作者分别是李冀和Jin Chen、主要研究机构分别是黑龙江中医药大学和Chinese Academy of Medical Sciences-Peking Union Medical College,关键词共现及突现分析表明国内外MIRI中医药干预措施包括中药、中药复方、中药单体、电针,研究热点为铁死亡、细胞焦亡和内质网应激。结论在中医药防治MIRI研究中,应加强国内研究团队之间的合作,促进国内研究机构的联系,结合研究热点,全面发展该领域。

关键词：心肌缺血再灌注损伤 MIRI 中医药 CiteSpace