检索结果-南通市图书馆

Towards Semi-supervised Classification of Abnormal Spectrum Signals Based on Deep Learning

维普期刊数据库博看期刊评论

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2024年第3期33卷 721-731页

作者： Tao JIANG Wanqing CHEN Hangping ZHOU Jinyang HE peihan QI School of Cyber Engineering Xidian University State Key Laboratory of Integrate Service Networks Xidian University Guangzhou Institute of Technology Xidian University

In order to cope with the heavy labor cost challenge of the manual abnormal spectrum classification and improve the effectiveness of existing machine learning schemes for spectral datasets with interference-to-signal ratios,we proposes a semi-supervised classification of abnormal spectrum signals(SSC-ASS),aimed at addressing some of the challenges in abnormal spectrum signal(ASS) classification tasks.A significant advantage of SSC-ASS is that it does not require manual labeling of every abnormal data,but instead achieves high-precision classification of ASSs using only a small number of labeled ***,the method can to some extent avoid the introduction of erroneous information resulting from the complex and variable nature of abnormal signals,thereby improving classification ***,SSC-ASS uses a memory AutoEncoder module to efficiently extract features from abnormal spectrum signals by learning from the reconstruction ***,SSC-ASS combines convolutional neural network and the K-means using a DeepCluster framework to fully utilize the unlabeled ***,SSC-ASS also utilizes pre-training,category mean memory module and replaces pseudo-labels to further improve the classification accuracy of *** we verify the classification effectiveness of SSC-ASS on synthetic spectrum datasets and real on-air spectrum dataset.

关键词： Deep learning Costs Memory management Memory modules Manuals Feature extraction Labeling

A salt-induced tackifying polymer for enhancing oil recovery in high salinity reservoirs: Synthesis, evaluation, and mechanism

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

GREEN ENERGY & ENVIRONMENT 2024年第11期9卷 1747-1758页

作者： Wu, Yining Li, peihan Yan, Bin Li, Xiaohan Huang, Yongping Yuan, Juncong Feng, Xiang Dai, Caili China Univ Petr East China Dept Petr Engn Qingdao 266580 Peoples R China Sichuan Univ Coll Biomass Sci & Engn Dept Natl Engn Lab Clean Technol Leather Manufacture Chengdu 610065 Peoples R China Princeton Univ Dept Civil & Environm Engn Princeton NJ 08544 USA China Univ Petr East China Dept Chem Engn Qingdao 266580 Peoples R China

Polymer flooding is an effective method widely applied for enhancing oil recovery (EOR) by reducing the mobility ratio between the injected water and crude oil. However, traditional polymers encounter challenges in high salinity reservoirs due to their salt sensitivity. To overcome this challenge, we synthesized a zwitterion polymer (PAMNS) with salt-induced tackifying property through copolymerization of acrylamide and a zwitterion monomer, methylacrylamide propyl-N, N-dimethylbutylsulfonate (NS). NS monomer is obtained from the reaction between 1,4-butanesultone and dimethylamino propyl methylacrylamide. In this study, the rheological properties, salt responsiveness, and EOR efficiency of PAMNS were evaluated. Results demonstrate that PAMNS exhibits desirable salt-induced tackifying characteristics, with viscosity increasing up to 2.4 times as the NaCl concentration reaches a salinity of 30 x 10(4) mg L-1. Furthermore, high valence ions possess a much stronger effect on enhancing viscosity, manifested as Mg2+ > Ca2+ > Na+. Molecular dynamics simulations (MD) and fluid dynamics experiment results demonstrate that PAMNS molecules exhibit a more stretched state and enhanced intermolecular associations in high-salinity environments. It is because of the salt-induced tackifying, PAMNS demonstrates superior performance in polymer flooding experiments under salinity ranges from 5 x 10(4) mg L-1 to 20 x 10(4) mg L-1, leading to 10.38-19.83% higher EOR than traditional polymers. (c) 2023 Institute of Process Engineering, Chinese Academy of Sciences. Publishing services by Elsevier B.V. on behalf of KeAi Communications Co., Ltd. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/).

关键词： High salinity reservoirs Salt-induced tackifying polymer Anti-polyelectrolyte behavior Enhanced oil recovery ZWITTERIONIC POLYMER BRUSHES SURFACE WATER BEHAVIOR

Spatial Dynamics of Chickenpox Outbreaks in Rapidly Developing Regions:Implications for Global Public Health

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

Biomedical and Environmental Sciences 2024年第7期37卷 687-697页

作者： Li Wang Miaomiao Wang Chengdong Xu peihan Wang Meiying You Zihan Li Xinmei Chen Xinyu Liu Xudong Li Yuanyuan Wang Yuehua Hu Dapeng Yin College of Geography and Environmental Science Henan UniversityKaifeng 475001HenanChina State Key Laboratory of Resources and Environmental Information System Institute of Geographic Science and Natural Resource ResearchChinese Academy of SciencesBeijing 100101BeijingChina Key Laboratory of Geospatial Technology for the Middle and Lower Yellow River Regions(Henan University) Ministry of EducationKaifeng 475001HenanChina Office of Epidemiology Chinese Center for Disease Control and PreventionBeijing 102206BeijingChina University of Chinese Academy of Sciences(UCAS) Beijing 100101BeijingChina Weifang Municipal Center for Disease Control and Prevention Weifang 261061ShandongChina Hainan Center for Disease Control and Prevention Haikou 570203HainanChina

Objective The occurrence of chickenpox in rapidly developing areas poses substantial seasonal risk to ***,certain factors influencing local chickenpox outbreaks have not been ***,we examined the relationship between spatial clustering,heterogeneity of chickenpox outbreaks,and socioeconomic factors in Southern *** We assessed chickenpox outbreak data from Southern China between 2006 and 2021,comprising both relatively fast-growing parts and slower sub-regions,and provides a representative sample of many developing *** analyzed the spatial clustering attributes associated with chickenpox outbreaks using Moran’s I and local indicators of spatial association and quantified their socioeconomic determinants using Geodetector q *** There were significant spatial heterogeneity in the risk of chickenpox outbreaks,with strong correlations between chickenpox risk and various factors,particularly demographics and living ***,interactive effects among specific are factors,such as population density and per capita residential building area,percentage of households with toilets,percentage of rental housing,exhibited q statistics of 0.28,0.25,and 0.24,*** This study provides valuable insights into the spatial dynamics of chickenpox outbreaks in rapidly developing regions,revealing the socioeconomic factors affecting disease *** implications extend the formulation of effective public health strategies and interventions to prevent and control chickenpox outbreaks in similar global contexts.

关键词： Chickenpox Spatial dynamics Socioeconomic factors

基于股骨头颈部三维精细解剖特征的倒直角构型空心螺钉固定股骨颈骨折的初步研究

在线全文

学校读者我要写书评

暂无评论

中华创伤骨科杂志 2024年第9期26卷 768-774页

作者：刘长剑柳佩含侯炀大连医科大学附属第一医院创伤骨科大连116000

目的基于CT三维重建分析股骨头颈部及股骨近端的精细解剖形态,探讨3枚空心螺钉固定股骨颈骨折术中如何避免后上方螺钉in-out-in。方法回顾性收集2021年9月至2024年3月期间大连医科大学附属第一医院创伤骨科收治的22例髋部骨折患者健侧股... 详细信息

目的基于CT三维重建分析股骨头颈部及股骨近端的精细解剖形态,探讨3枚空心螺钉固定股骨颈骨折术中如何避免后上方螺钉in-out-in。方法回顾性收集2021年9月至2024年3月期间大连医科大学附属第一医院创伤骨科收治的22例髋部骨折患者健侧股骨CT数据。男12例,女10例;年龄(52.5±16.8)岁。将患者健侧股骨CT数据导入Mimics19.0软件,建立股骨近端3D模型,测量并分析股骨头颈部及股骨近端的精细解剖,确定股骨颈轴位髓腔最狭窄处3枚空心螺钉分散排布的最佳构型。3D模型模拟分析不同构型3枚空心螺钉固定股骨颈骨折后上方螺钉in-out-in的发生情况。测量股骨颈后上方皮质斜面倾斜角度(即负前倾角),模拟负前倾角位透视,观察3枚空心螺钉固定股骨颈骨折后上方螺钉发生in-out-in的情况。并在2例股骨颈骨折患者(1例为51岁男性患者,另1例为68岁女性患者)的临床治疗中验证最佳构型与负前倾角位透视。结果3D模型显示:股骨头颈部髓腔与股骨近端髓腔并非同一平面,而是较股骨近端向前偏移1/4左右,偏移距离为(6.16±0.86)mm;股骨颈髓腔最狭窄处为不规则形态,3枚空心螺钉分散排布最合理构型为接近倒直角形态(改良倒直角构型),而不是传统倒三角构型。3D模型模拟传统倒三角构型置入3枚螺钉,后上方螺钉发生in-out-in;而模拟改良倒直角构型置入3枚螺钉,后上方螺钉未发生in-out-in。术中采用负前倾角(31.02°±3.32°)位透视可以发现后上方螺钉是否发生in-out-in。2例股骨颈骨折患者均采用改良倒直角构型3枚空心螺钉固定,术中负前倾角位透视及术后CT扫描均未发现螺钉in-out-in。结论股骨头颈部及股骨近端的精细解剖形态决定了传统倒三角构型空心螺钉固定股骨颈骨折时后上方螺钉易发生in-out-in,改良倒直角构型3枚空心螺钉固定能有效降低后上方螺钉in-out-in的发生风险。术中采用负前倾角位透视可以及时发现后上方螺钉是否发生in-out-in。

关键词：股骨颈骨折骨折固定术,内骨钉倒直角构型负前倾角

基于小生境遗传算法与径向基代理模型的短期风电功率预测

在线全文

学校读者我要写书评

暂无评论

太阳能学报 2024年第8期45卷 554-564页

作者：刘沛汉尹翠贾娜樊小朝杨青斌新疆工程学院能源工程学院乌鲁木齐830023 国网新疆电力有限公司超高压分公司乌鲁木齐830002 中国电力科学研究院有限公司可再生能源并网全国重点实验室南京210009

为提高短期功率预测精度,以赋予风电被电网资产更大规模消纳的优势,建立一种基于主导特征影响因素和小生境遗传算法改进的径向基代理模型的滚动式短期(0~72 h)风电功率预测模型。首先,基于罚函数和排挤机制的小生境技术对传统基本遗传... 详细信息

为提高短期功率预测精度,以赋予风电被电网资产更大规模消纳的优势,建立一种基于主导特征影响因素和小生境遗传算法改进的径向基代理模型的滚动式短期(0~72 h)风电功率预测模型。首先,基于罚函数和排挤机制的小生境技术对传统基本遗传算法进行改进,以径向基代理模型(RBF)作为建模基础,利用改进后的遗传算法以反传误差极小为目标函数对RBF模型的连接权值进行优化,借助其寻优能力来获取最佳权值,以达成对RBF网络的改进和二次训练;然后,基于主导特征气象因素,结合改进的RBF模型最终建立N-SGA-RBF风电出力预测模型,对风电场连续3日0~72 h输出功率进行预测;最后,对N-SGA-RBF模型、RBF模型以及BP模型做预测结果趋势变化、各采样点绝对/相对误差分布、发电预测预报准确率和合格率的对比。以新疆东部某风电场实测数据进行算例验证分析,仿真结果表明,所建预测模型具有较高的精度。

关键词：风电功率预测径向基代理模型小生境遗传算法智能优化

维普期刊数据库博看期刊

在线全文

学校读者我要写书评

暂无评论

大模型知识管理系统

中兴通讯技术 2024年第2期30卷 63-71页

作者：周扬蔡霈涵董振江南京邮电大学南京210023

企业知识管理至关重要,而传统企业知识管理系统存在构建成本高、知识利用率低的问题。提出了基于大模型检索增强生成(RAG)技术构建企业知识管理系统的方案。首先介绍了整体方案架构、业务流程与4类知识构建技术,然后重点介绍了检索前处... 详细信息

企业知识管理至关重要,而传统企业知识管理系统存在构建成本高、知识利用率低的问题。提出了基于大模型检索增强生成(RAG)技术构建企业知识管理系统的方案。首先介绍了整体方案架构、业务流程与4类知识构建技术,然后重点介绍了检索前处理、知识检索、检索后处理等全流程知识检索技术,并设计了全面的测评框架。经过实践检验,该方案具有知识构建效率高且成本低、意图理解精确、知识检索准确等特点与优势。

关键词： RAG 知识管理系统大模型知识工程

Side-Chain Type Ferrocene Macrocycles

在线全文

学校读者我要写书评

暂无评论

Precision Chemistry 2024年第4期2卷 143-150页

作者： Bin Lan Jindong Xu Lingyun Zhu Xinyu Chen Hideya Kono peihan Wang Xin Zuo Jianfeng Yan Akiko Yagi Yongshen Zheng Songhua Chen Yaofeng Yuan Kenichiro Itami Yuanming Li Key Laboratory of Molecule Synthesis and Function Discovery(Fujian Province University) College of ChemistryFuzhou UniversityFuzhou 350108China Institute of Transformative Bio-Molecules(WPI-ITbM) Nagoya UniversityNagoya 464-8602Japan School of Materials Science and Engineering National Institute for Advanced MaterialsNankai UniversityTianjin 300350China Institute of Transformative Bio-Molecules(WPIITbM) Nagoya UniversityNagoya 464-8602Japan College of Chemistry and Material Science Longyan UniversityLongyan 364012China

A class of side-chain type ferrocene macrocycles with a radially conjugated system is introduced in this *** stereo configurations of these ferrocene rings were determined through single-crystal X-ray diffraction ***,in the solid state,the ferrocene rings exhibit a distinctive herringbone stacking pattern imposed by a ferrocene-to-ring host−guest *** UV−vis absorption spectroscopy,electrochemical measurements,and theoretical calculations,valuable insights into the electronic properties of these rings were *** addition,the single crystal of macrocycle A_(2)B demonstrates a second-order nonlinear optical *** a class of organometallic nanorings,this work holds great potential for further exploration in the fields of organometallic chemistry,molecular electronics,and host−guest chemistry.

关键词： Ferrocene Conjugated Macrocycles Organometallic Macrocycles Second-Order Nonlinear Optical Nanoring

基于偏最小二乘回归的谷子冠层氮素含量高光谱估测研究

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

中国农业科技导报 2024年第6期26卷 91-101页

作者：蒋沛含杨晓楠杨晨旭张爱军河北农业大学资源与环境科学学院河北保定071000 河北农业大学国家北方山区农业工程技术研究中心河北保定071000 河北省山区研究所河北保定071000

为构建多品种谷子冠层氮素含量的高光谱监测模型,通过设置不同氮素水平和多品种谷子田间试验,分别获取谷子全生育期冠层高光谱反射率和叶片氮素含量,采用卷积平滑、一阶导数变换对光谱曲线进行预处理,利用光谱数据与氮素含量相关性分析... 详细信息

为构建多品种谷子冠层氮素含量的高光谱监测模型,通过设置不同氮素水平和多品种谷子田间试验,分别获取谷子全生育期冠层高光谱反射率和叶片氮素含量,采用卷积平滑、一阶导数变换对光谱曲线进行预处理,利用光谱数据与氮素含量相关性分析、连续投影算法(successive projections algorithm,SPA)筛选出谷子各生育期和全生育期的氮素敏感波段、植被指数、高光谱特征参数,利用三者组合建立谷子冠层氮素含量的偏最小二乘回归(partial least square regression,PLSR)估测模型,并筛选各生育期最优模型。结果表明,不同生育期最优估测模型有所差异,拔节期基于敏感波段、植被指数、高光谱特征参数的模型精度最高;抽穗期基于敏感波段、植被指数的模型精度最高;灌浆期基于植被指数、高光谱特征参数的模型精度最高;成熟期基于敏感波段、植被指数的模型精度最高;全生育期基于敏感波段与植被指数的模型精度最高(R2=0.903,RPD=3.01)。多输入级综合模型可以充分利用光谱信息,有效提高模型预测精度和稳定性,其中基于敏感波段和植被指数的综合模型表现效果最好,预测集R2均在0.82以上、均方根误差均小于0.119、相对分析误差均大于2.1。以上研究结果为高光谱遥感诊断谷子全生育期氮素盈缺状况与施肥决策提供了理论依据和技术支撑。

关键词：谷子冠层氮素含量高光谱遥感偏最小二乘回归

冠状动脉疾病报告与数据系统在冠心病患者危险因素分析中的应用

同方期刊数据库博看期刊评论

在线全文

学校读者我要写书评

暂无评论

吉林大学学报（医学版） 2017年第3期43卷 617-621页

作者：周宏刘进才罗光华谢佩含杨娟董宇岚卿伟鹏张晶晶南华大学附属第一医院放射科湖南衡阳421001 南华大学附属第一医院心血管内科湖南衡阳421001

目的:探讨冠状动脉疾病报告与数据系统(CAD-RADS)在冠状动脉粥样硬化性心脏病(冠心病)诊断中的应用及其危险因素,阐明危险因素对CAD-RADS诊断冠心病的影响强度。方法:收集266例临床怀疑冠心病患者的冠状动脉CT血管造影(CTA)影像资料和... 详细信息

目的:探讨冠状动脉疾病报告与数据系统(CAD-RADS)在冠状动脉粥样硬化性心脏病(冠心病)诊断中的应用及其危险因素,阐明危险因素对CAD-RADS诊断冠心病的影响强度。方法:收集266例临床怀疑冠心病患者的冠状动脉CT血管造影(CTA)影像资料和临床相关资料,采用CAD-RADS分级法将患者分为冠心病组(n=174)和非冠心病组(n=69)。分析2组患者年龄、性别、高血压、高血脂、糖尿病、吸烟、尿酸(UA)水平和血浆纤维蛋白原(FIB)水平;采用单因素和多因素Logistic回归分析方法分析CAD-RADS系统诊断冠心病的相关危险因素。结果:与非冠心病组比较,冠心病组患者中男性、高血压、糖尿病和吸烟者所占比例明显升高(P<0.05),冠心病组患者平均年龄大、UA水平高(P<0.05)。多因素Logistic回归分析,年龄和糖尿病是冠状动脉CAD-RADS诊断冠心病的最显著危险因素。结论:CAD-RADS诊断冠心病受到多种危险因素的影响,其中年龄和糖尿病是最显著的独立相关危险因素。

关键词：冠状动脉疾病报告与数据系统 CT血管造影冠状动脉粥样硬化性心脏病危险因素