检索结果-南通市图书馆

Aspect-Guided Multi-Graph Convolutional Networks for Aspect-based Sentiment Analysis

在线全文

学校读者我要写书评

暂无评论

Data Intelligence 2024年第3期6卷 771-791页

作者： Yong wang Ningchuang Yang Duoqian miao Qiuyi Chen Schoole of Artificial Intelligence Chongqing University of Technology401135ChongqingChina Department of Computer Science and Technology Tongji University201804ShanghaiChina

The Aspect-Based Sentiment Analysis(ABSA)task is designed to judge the sentiment polarity of a particular aspect in a *** studies have proved that GCN can capture syntactic and semantic features from dependency graphs generated by dependency trees and semantic graphs generated by Multi-headed self-attention(MHSA).However,these approaches do not highlight the sentiment information associated with aspect in the syntactic and semantic *** propose the Aspect-Guided Multi-Graph Convolutional Networks(AGGCN)for Aspect-Based Sentiment ***,we reconstruct two kinds of graphs,changing the weight of the dependency graph by distance from aspect and improving the semantic graph by Aspect-guided *** interactive learning of syntax and semantics,we dynamically fuse syntactic and semantic diagrams to generate syntactic-semantic graphs to learn emotional features *** addition,Multi-dropout is added to solve the overftting of AGGCN in *** experimental results on extensive datasets show that our model AGGCN achieves particularly advanced results and validates the effectiveness of the model.

关键词： Graph convolutional networks Aspect-based sentiment analysis Multi-headed attention BERT encoder

ConvNeXt-UperNet-Based Deep Learning Model for Road Extraction from High-Resolution Remote Sensing Images

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第8期80卷 1907-1925页

作者： Jing wang Chen Zhang Tianwen lin Geographic Information and Tourism College Chuzhou UniversityChuzhou239000China Anhui Province Key Laboratory of Physical Geographic Environment Chuzhou UniversityChuzhou239000China

When existing deep learning models are used for road extraction tasks from high-resolution images,they are easily affected by noise factors such as tree and building occlusion and complex backgrounds,resulting in incomplete road extraction and low *** propose the introduction of spatial and channel attention modules to the convolutional neural network ***,ConvNeXt is used as the backbone network,which cooperates with the perceptual analysis network UPerNet,retains the detection head of the semantic segmentation,and builds a new model ConvNeXt-UPerNet to suppress noise *** on the open-source DeepGlobe and CHN6-CUG datasets and introducing the DiceLoss on the basis of CrossEntropyLoss solves the problem of positive and negative sample *** results show that the new network model can achieve the following performance on the DeepGlobe dataset:79.40%for precision(Pre),97.93% for accuracy(Acc),69.28% for intersection over union(IoU),and 83.56% for mean intersection over union(MIoU).On the CHN6-CUG dataset,the model achieves the respective values of 78.17%for Pre,97.63%for Acc,65.4% for IoU,and 81.46% for *** with other network models,the fused ConvNeXt-UPerNet model can extract road information better when faced with the influence of noise contained in high-resolution remote sensing *** also achieves multiscale image feature information with unified perception,ultimately improving the generalization ability of deep learning technology in extracting complex roads from high-resolution remote sensing images.

关键词： Deep learning semantic segmentation remote sensing imagery road extraction

Functional Optical Fiber Sensors Detecting Imperceptible Physical/Chemical Changes for Smart Batteries

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Nano-Micro Letters 2024年第8期16卷 268-308页

作者： Yiding Li Li wang Youzhi Song Wenwei wang Cheng lin Xiangming He Institute of Nuclear and New Energy Technology Tsinghua UniversityBeijing 100084People’s Republic of China National Engineering Research Center of Electric Vehicles Beijing Institute of Technology(BIT)Beijing 100081People’s Republic of China Shenzhen Automotive Research Institute of BIT(Shenzhen Research Institute of National Engineering Research Center of Electric Vehicles) Shenzhen 518118People’s Republic of China

The battery technology progress has been a contradictory process in which performance improvement and hidden risks *** the battery is still a“black box”,thus requiring a deep understanding of its internal *** battery should“sense its internal physical/chemical conditions”,which puts strict requirements on embedded sensing *** paper summarizes the application of advanced optical fiber sensors in lithium-ion batteries and energy storage technologies that may be mass deployed,focuses on the insights of advanced optical fiber sensors into the processes of one-dimensional nano-micro-level battery material structural phase transition,electrolyte degradation,electrode-electrolyte interface dynamics to three-dimensional macro-safety *** paper contributes to understanding how to use optical fiber sensors to achieve“real”and“embedded”*** the inherent advantages of the advanced optical fiber sensor,it helps clarify the battery internal state and reaction mechanism,aiding in the establishment of more detailed *** advancements can promote the development of smart batteries,with significant importance lying in essentially promoting the improvement of system ***,with the help of smart batteries in the future,the importance of consistency can be weakened or even *** application of advanced optical fiber sensors helps comprehensively improve the battery quality,reliability,and life.

关键词： Smart battery Advanced embedded optical fiber sensor Battery internal physical/chemical state Quality-reliability-life characteristic

A low-profile metamaterial absorber with ultrawideband reflectionless and wide-angular stability

在线全文

学校读者我要写书评

暂无评论

Defence Technology（防务技术） 2024年第4期34卷 258-268页

作者： Feihong lin Zhongming Yan Ping wang Yu wang Hongcheng Zhou Haoran Lu School of Electrical Engineering Southwest Jiaotong UniversityChengdu 611756China Key Laboratory of Magnetic Suspension Technology and Maglev Vehicle Ministry of EducationChengdu 610031China China Academy of Launch Vehicle Technology Beijing 100076China

An ultrawideband reflectionless metamaterial absorber(MA)is proposed by replacing the metallic ground with the complementary split-ring resonator(CSRR)*** proposed MA exhibits-10 d B reflectivity spectrum from 1 GHz to 20 GHz,which maintains more than 90%absorption from 1.5 GHz to20 ***,it achieves angle stability for TE and TM polarization at oblique incident angles up to 40°and 65°,*** achieve broadband absorption spectrum,we have adopted a single-layer high-impedance surface(HIS)loaded with a double-layer magnetic material(MM)*** further realize the RCS reduction into a lower frequency range,we have employed the scattering cancellation technology into the traditional metallic ***,we have fabricated a sample exhibiting the 10 d B RCS reduction from 1 GHz to 20 GHz with a thickness of 10 *** and simulation results confirm that the proposed MA exhibits excellent comprehensive performance,making it suitable for many practical applications.

关键词： Metamaterial absorber(MA) Magnetic material(MM) High-impedance surface(HIS) Scattering cancellation technology Ultrawideband Wide-angular stable

Rheological Behaviors of Polymers with Nanoparticles Tethered at Each End

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Polymer Science 2024年第3期42卷 400-406,I0009页

作者： Song-Qi Zhang Wen-Qing wang Jia-Ping lin Li-Quan wang Shanghai Key Laboratory of Advanced Polymeric Materials Key Laboratory for Ultrafine Materials of Ministry of EducationSchool of Materials Science and EngineeringEast China University of Science and TechnologyShanghai 200237China

The polymer with nanoparticles tethered at each end is a unique model for unraveling the effect of chain ends on the polymer dynamics. We investigated the rheological behavior of this kind of polymer by using nonequilibrium molecular dynamics simulation. The effect of polymer lengths and nanoparticle radii on the complex moduli and viscosity was examined. The dependence of complex moduli on the frequency becomes less pronounced as the polymer is short or the nanoparticle is large. The shear thinning behavior was revealed for these systems, and the scaling exponent of complex viscosity with respect to the frequency was found to change from-1/2 to-3/4 as the polymer shortens or the nanoparticle enlarges. The rheological behavior was further explained by analyzing the mean square distance of nanoparticles. The simulation results were compared with the existing experimental finding, showing an agreement. The work provides information for understanding the chain end effect on polymer rheology.

关键词： Polymer rheology Modulus Viscosity Molecular dynamics

Optimization of tracheoesophageal fistula model established with Tshaped magnet system based on magnetic compression technique

在线全文

学校读者我要写书评

暂无评论

World Journal of Gastroenterology 2024年第16期30卷 2272-2280页

作者： miao-miao Zhang Jian-Qi Mao lin-Xin Shen Ai-Hua Shi Xin Lyu Jia Ma Yi Lyu Xiao-Peng Yan Department of Hepatobiliary Surgery The First Affiliated Hospital of Xi’an Jiaotong UniversityXi’an 710061Shaanxi ProvinceChina Shaanxi Provincial Key Laboratory of Magnetic Medicine The First Affiliated Hospital of Xi’an Jiaotong UniversityXi’an 710061Shaanxi ProvinceChina Zonglian College Xi’an Jiaotong UniversityXi’an 710061Shaanxi ProvinceChina National Local Joint Engineering Research Center for Precision Surgery&Regenerative Medicine The First Affiliated Hospital of Xi’an Jiaotong UniversityXi’an 710061Shaanxi ProvinceChina Department of Pulmonary and Critical Care Medicine The Second Affiliated Hospital of Xi’an Jiaotong UniversityXi’an 710004Shaanxi ProvinceChina Department of Surgical Oncology Shaanxi Provincial People’s HospitalXi’an 710068Shaanxi ProvinceChina

BACKGROUND The magnetic compression technique has been used to establish an animal model of tracheoesophageal fistula(TEF),but the commonly shaped magnets present limitations of poor homogeneity of TEF and poor model *** designed a Tshaped magnet system to overcome these problems and verified its effectiveness via animal *** To investigate the effectiveness of a T-shaped magnet system for establishing a TEF model in beagle *** Twelve beagles were randomly assigned to groups in which magnets of the Tshaped scheme(study group,n=6)or normal magnets(control group,n=6)were implanted into the trachea and esophagus separately under *** time,operation success rate,and accidental injury were *** operation,the presence and timing of cough and the time of magnet shedding were *** in the control group were euthanized after X-ray and gastroscopy to confirm establishment of TEFs after coughing,and gross specimens of TEFs were *** in the study group were euthanized after X-ray and gastroscopy 2 wk after surgery,and gross specimens were *** size was measured in all animals,and then harvested fistula specimens were examined by hematoxylin and eosin(HE)and Masson trichrome *** The operation success rate was 100%for both *** time did not differ between the study group(5.25 min±1.29 min)and the control group(4.75 min±1.70 min;P=0.331).No bleeding,perforation,or unplanned magnet attraction occurred in any animal during the *** the early postoperative period,all dogs ate freely and were generally in good *** in the control group had severe cough after drinking water at 6-9 d after surgery.X-ray indicated that the magnets had entered the stomach,and gastroscopy showed TEF *** specimens of TEFs from the control group showed the formation of fistulas with a diameter of 4.94 mm±1.29 mm(range,3.52-6.56 mm).HE and Masson trichrome staining showed s

关键词： Magnetic surgery Magnetic compression technique Tracheoesophageal fistula Magnet Animal model Beagles

Machine learning model based on non-convex penalized huberized-SVM

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Electronic Science and Technology 2024年第1期22卷 81-94页

作者： Peng wang Ji Guo lin-Feng Li School of Finance and Economics Xizang Minzu UniversityXianyang712082China Research Center for Quality Development of Xizang Special Industries Xianyang712082China School of Computer Science and Technology Xinjiang UniversityUrumqi830017China

The support vector machine(SVM)is a classical machine learning *** the hinge loss and least absolute shrinkage and selection operator(LASSO)penalty are usually used in traditional ***,the hinge loss is not differentiable,and the LASSO penalty does not have the Oracle *** this paper,the huberized loss is combined with non-convex penalties to obtain a model that has the advantages of both the computational simplicity and the Oracle property,contributing to higher accuracy than traditional *** is experimentally demonstrated that the two non-convex huberized-SVM methods,smoothly clipped absolute deviation huberized-SVM(SCAD-HSVM)and minimax concave penalty huberized-SVM(MCP-HSVM),outperform the traditional SVM method in terms of the prediction accuracy and classifier *** are also superior in terms of variable selection,especially when there is a high linear correlation between the *** they are applied to the prediction of listed companies,the variables that can affect and predict financial distress are accurately filtered *** all the indicators,the indicators per share have the greatest influence while those of solvency have the weakest *** companies can assess the financial situation with the indicators screened by our algorithm and make an early warning of their possible financial distress in advance with higher precision.

关键词： Huberized loss Machine learning Non-convex penalties Support vector machine(SVM)

LncRNA MEG3 Inhibits the Epithelial-mesenchymal Transition of Bladder Cancer Cells through the Snail/E-cadherin Axis

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

当代医学科学（英文） 2024年第4期44卷 726-734页

作者： Liang wang Ping wang Bing LIU Hui ZHANG Cheng-cheng WEI Ming XIONG Gang LUO miao wang Department of Urology Union HospitalTongji Medical CollegeHuazhong University of Science and TechnologyWuhan 430022China Department of Clinical Laboratory Union HospitalTongji Medical CollegeHuazhong University of Science and TechnologyWuhan 430022China Department of Urology The Central Hospital of WuhanTongji Medical CollegeHuazhong University of Science and TechnologyWuhan 430014China

Objective:This study aimed to investigate the role of the long noncoding RNA(lncRNA)maternally expressed gene 3(MEG3)in the epithelial-mesenchymal transition(EMT)of bladder cancer cells and the potential ***:Cell invasion,migration,and wound healing assays were conducted to assess the effects of MEG3 on the invasive and migratory capabilities of bladder cancer *** expression levels of E-cadherin were measured using Western blotting,RT-qPCR,and dual luciferase reporter *** immunoprecipitation and pull-down assays were performed to investigate the interactions between MEG3 and its downstream ***:MEG3 suppressed the invasion and migration of bladder cancer cells and modulated the transcription of *** binding of MEG3 to the zinc finger region of the transcription factor Snail prevented its ability to transcriptionally repress ***,MEG3 suppressed the phosphorylation of extracellular regulated protein kinase(ERK),c-Jun N-terminal kinase(JNK),and P38,thereby decreasing the expression of Snail and stimulating the expression of ***:MEG3 plays a vital role in suppressing the EMT in bladder cancer cells,indicating its potential as a promising therapeutic target for the treatment of bladder cancer.

关键词： Snail bladder cancer epithelial-mesenchymal transition long noncoding RNA maternally expressed gene 3

Materials design and preparation of ultrathin two-dimensional metal halide perovskites

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Nano Research 2024年第7期17卷 6231-6246页

作者： Xiaomin Zhang Sihan Zhao Junran Zhang lin wang School of Flexible Electronics(Future Technologies)and Institute of Advanced Materials Key Laboratory of Flexible ElectronicsJiangsu National Synergetic Innovation Center for Advanced MaterialsSchool of Physical and Mathematical SciencesNanjing Tech UniversityNanjing 211816China

Metal halide perovskites(MHPs)have emerged as highly promising candidates for the next generation of photonics and optoelectronic devices,owing to their prominent optical and excitonic properties,as well as the convenience of ***,ultrathin two-dimensional(2D)MHPs,which are generally prepared by exfoliation,solution growth,and chemical vapor deposition method,have attracted dramatically increasing attentions owing to their combined features of ultrathin 2D morphology and superior performance of *** the growing interest in ultrathin 2D MHPs,there is currently a lack of a comprehensive and systematic overview of the distinct advantages offered by each growth method for producing these *** review critically assesses the preliminary studies on the materials design and preparation of ultrathin ***,it explores heterostructures based on ultrathin MHPs and offers insights into the challenges and opportunities that lie ahead for this enticing class of 2D materials.

关键词： ultrathin perovskites material preparation exfoliation solution growth chemical vapor deposition