检索结果-南通市图书馆

维普期刊数据库

Joint Feature Encoding and Task Alignment Mechanism for Emotion-Cause Pair Extraction

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2025年第1期82卷 1069-1086页

作者： Shi Li Didi sun College of Computer and Control Engineering Northeast Forestry UniversityHarbin150040China

With the rapid expansion of social media,analyzing emotions and their causes in texts has gained significant ***-cause pair extraction enables the identification of causal relationships between emotions and their triggers within a text,facilitating a deeper understanding of expressed sentiments and their underlying *** comprehension is crucial for making informed strategic decisions in various business and societal ***,recent research approaches employing multi-task learning frameworks for modeling often face challenges such as the inability to simultaneouslymodel extracted features and their interactions,or inconsistencies in label prediction between emotion-cause pair extraction and independent assistant tasks like emotion and cause *** address these issues,this study proposes an emotion-cause pair extraction methodology that incorporates joint feature encoding and task alignment *** model consists of two primary components:First,joint feature encoding simultaneously generates features for emotion-cause pairs and clauses,enhancing feature interactions between emotion clauses,cause clauses,and emotion-cause ***,the task alignment technique is applied to reduce the labeling distance between emotion-cause pair extraction and the two assistant tasks,capturing deep semantic information interactions among *** proposed method is evaluated on a Chinese benchmark corpus using 10-fold cross-validation,assessing key performance metrics such as precision,recall,and F1 *** results demonstrate that the model achieves an F1 score of 76.05%,surpassing the state-of-the-art by 1.03%.The proposed model exhibits significant improvements in emotion-cause pair extraction(ECPE)and cause extraction(CE)compared to existing methods,validating its *** research introduces a novel approach based on joint feature encoding and task alignment mechanisms,contributing to advancements in emotion-c

关键词： Emotion-cause pair extraction interactive information enhancement joint feature encoding label consistency task alignment mechanisms

Microstructure and Wear/corrosion Resistance of Stainless Steel Laser-alloyed with Mn+W_(2)C, Mn+NiWC and Mn+SiC

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 Wuhan University of Technology(Materials Science) 2025年第1期40卷 283-294页

作者： ZHOU Rui DIAO Xiaogang sun Yixin School of Metallurgical Engineering Jiangsu University of Science and TechnologyZhangjiagang 215600China CITIC Heavy Cast Iron Industry Co. Ltd.Luoyang 417039China

In-situ formed high Mn steel coating reinforced by carbides was formed by laser surface alloying(LSA).Laser alloyed layers on 1Cr18Ni9Ti steel with Mn+W_(2)C(specimen A),Mn+NiWC(specimen B)and Mn+SiC(specimen C)powders were fabricated to improve the wear and corrosion behavior of 1Cr18Ni9Ti steel blades in high speed *** evolution,phases,element distribution,microhardness,wear and corrosion behavior of the laser alloyed layers were *** indicated that high Mn steel matrix composites with undissolved W_(2)C,WC and other in-situ formed carbides were formed by LSA with Mn+W_(2)C and Mn+NiWC while SiC totally dissolved into the high Mn matrix when adding Mn+*** as the binding phase in Ni-WC powder decreased the crack sensitivity of the alloyed layer as compared with the addition of W_(2)C *** improvement in average microhardness was achieved in the matrix in specimen A,B and C,with the value of 615,602 and 277 HV_(0.5),while that of the substrate was 212 HV_(0.5).The increase of microhardness,wear and corrosion resistance is highly corelated to microstructure,formed phases,type and content of carbides,micro-hardness and toughness of the alloyed layers.

关键词： laser surface alloying stainless steel carbide type microstructure wear and corrosion resistance

Traffic safety helmet wear detection based on improved YOLOv5 network

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Optoelectronics Letters 2025年第1期21卷 35-42页

作者： GUI Dongdong sun Bo College of Software Southeast University Quanzhou Equipment Research Centre Haixi Institute Chinese Academy of Sciences

Aiming at the problem that the current traffic safety helmet detection model can't balance the accuracy of detection with the size of the model and the poor generalization of the model, a method based on improving you only look once version 5(YOLOv5) is proposed. By incorporating the lightweight Ghost Net module into the YOLOv5 backbone network, we effectively reduce the model size. The addition of the receptive fields block(RFB) module enhances feature extraction and improves the feature acquisition capability of the lightweight model. Subsequently, the high-performance lightweight convolution, GSConv, is integrated into the neck structure for further model size compression. Moreover, the baseline model's loss function is substituted with efficient insertion over union(EIoU), accelerating network convergence and enhancing detection precision. Experimental results corroborate the effectiveness of this improved algorithm in real-world traffic scenarios.

关键词： Traffic control

Brain endothelial cyclic GMP-AMP synthase(cGAS)-stimulator of interferon genes(STING)signaling pathway in aging and neurodegeneration

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Neural Regeneration Research 2025年第7期20卷 2005-2007页

作者： Bryan sun Lulin Li Jian Luo Palo Alto Veterans Institute for Research VA Palo Alto Health Care SystemPalo AltoCAUSA Polytrauma System of Care VA Palo Alto Health Care SystemPalo AltoCAUSA

The cyclic GMP-AMP synthase(cGAS)-stimulator of interferon genes(STING)signaling pathway has emerged as a key mediator of *** current studies primarily attribute its effects to neurons and glial cells,emerging research suggests that cGAS-STING signaling may play a critical role in cerebral vasculature,particularly in brain endothelial ***,studying the role 7of inflammation caused by the cGAS-STING pathway in brain endothelial cells could provide a more comprehensive understanding of neuroinflammatory disease and new avenues for therapeutic ***,we review the multifaceted role of global cGAS-STING signaling in various neurological and neuroinflammatory diseases and the potential contribution of cGAS-STING in brain endothelial cells.

关键词： stimulator interferon inflammation

维普期刊数据库

Malicious Document Detection Based on GGE Visualization

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2025年第1期82卷 1233-1254页

作者： Youhe Wang Yi sun Yujie Li Chuanqi Zhou Henan Province Key Laboratory of Information Security Information Engineering UniversityZhengzhou450000China

With the development of anti-virus technology,malicious documents have gradually become the main pathway of Advanced Persistent Threat(APT)attacks,therefore,the development of effective malicious document classifiers has become particularly ***,detection methods based on document structure and behavioral features encounter challenges in feature engineering,these methods not only have limited accuracy,but also consume large resources,and usually can only detect documents in specific formats,which lacks versatility and *** address such problems,this paper proposes a novel malicious document detection method-visualizing documents as GGE images(Grayscale,Grayscale matrix,Entropy).The GGE method visualizes the original byte sequence of the malicious document as a grayscale image,the information entropy sequence of the document as an entropy image,and at the same time,the grayscale level co-occurrence matrix and the texture and spatial information stored in it are converted into grayscale matrix image,and fuses the three types of images to get the GGE color *** Convolutional Block Attention Module-EfficientNet-B0(CBAM-EfficientNet-B0)model is then used for classification,combining transfer learning and applying the pre-trained model on the ImageNet dataset to the feature extraction process of GGE *** shown in the experimental results,the GGE method has superior performance compared with other methods,which is suitable for detecting malicious documents in different formats,and achieves an accuracy of 99.44%and 97.39%on Portable Document Format(PDF)and office datasets,respectively,and consumes less time during the detection process,which can be effectively applied to the task of detecting malicious documents in real-time.

关键词： Malicious document visualization EfficientNet-B0 convolutional block attention module GGE image

Revisiting Plateau-Rayleigh instability in inorganic synthetic chemistry

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China Materials 2025年

作者： Yugang sun Department of Chemistry Temple University

Wetting-dewetting behavior is a universal phenomenon for fluids on solid surfaces,for instance,the liquid on spider silk and lotus leaves[1].Controlling the wetting-dewetting behavior of fluids in a predictable and generalizable manner is of broad interest in various applications,such as anti-corrosion,antifogging,medicine,oil-water separation,self-cleaning,and water harvesting[2].Specifically,in the one-dimensional （1D） system,it is usually known as the Plateau-Rayleigh （P-R） instability,which describes the volume-constant break-up of a continuous water cylinder into isolated droplets （Fig.1a）[3,4].

关键词：

RF Optimizer Model for Predicting Compressive Strength of Recycled Concrete

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Wuhan University of Technology(Materials Science) 2025年第1期40卷 215-223页

作者： LIU Lin WANG Liuyan WANG Hui sun Huayue School of Civil Engineering and Architecture Shenyang UniversityShenyang 110000China

Traditional machine learning(ML)encounters the challenge of parameter adjustment when predicting the compressive strength of reclaimed *** address this issue,we introduce two optimized hybrid models:the Bayesian optimization model(B-RF)and the optimal model(Stacking model).These models are applied to a data set comprising 438 observations with five input variables,with the aim of predicting the compressive strength of reclaimed ***,we evaluate the performance of the optimized models in comparison to traditional machine learning models,such as support vector regression(SVR),decision tree(DT),and random forest(RF).The results reveal that the Stacking model exhibits superior predictive performance,with evaluation indices including R2=0.825,MAE=2.818 and MSE=14.265,surpassing the traditional ***,we also performed a characteristic importance analysis on the input variables,and we concluded that cement had the greatest influence on the compressive strength of reclaimed concrete,followed by ***,the Stacking model can be recommended as a compressive strength prediction tool to partially replace laboratory compressive strength testing,resulting in time and cost savings.

关键词： machine learning recycled concrete compressive strength

Effect of Progressive Substitution of Cement and Lime by Powdered Shells Used as a Curing Agent for Dredged Soil in a Port Area

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 Wuhan University of Technology(Materials Science) 2025年第1期40卷 88-102页

作者： sun Yang WANG Faxin SU Yaying LI Yiwei HE Feng College of Harbour Coastal and Offshore EngineeringHohai UniversityNanjing 210098China Huai'an Research Institute Hohai UniversityHuai'an 223025China Jiangsu Fangyang Industrial Investment Corp.Ltd. Lianyungang 210098China

This study aimed to address the challenges of solid waste utilization,cost reduction,and carbon reduction in the treatment of deep-dredged soil at Xuwei Port in Lianyungang city of *** research in this area was ***,a curing agent made from powdered shells was used to solidify the dredged soil in *** employed laboratory orthogonal tests to investigate the physical and mechanical properties of the powdered shell-based curing *** was collected by conducting experiments to assess the role of powdered shells in the curing process and to determine the optimal ratios of powdered shells to solidified soil for different *** development of strength in solidified soil was studied in both seawater and pure water *** study revealed that the strength of the solidified soil was influenced by the substitution rate of powdered shells and their interaction with *** cement content had a positive effect on *** high-strength solidified soil,the recommended ratio of wet soil:cement:lime:powdered shells were 100:16:4:4,while for low-strength solidified soil,the recommended ratio was 100:5.4:2.4:***,under appropriate conditions,improved short-term strength by promoting the formation of expansive ettringite minerals that contributed to cementation and *** findings suggest that the combination of cement and powdered shells is synergistic,positively affecting the strength of solidified *** recommended ratios provide practical guidance for achieving desired strength levels while considering factors such as cost and carbon *** role of seawater in enhancing short-term strength through crystal formation is noteworthy and can be advantageous for certain *** conclusion,this research demonstrates the potential of using a powdered shell-based curing agent for solidifying dredged soil in an environmentally friendly and cost-effective *** recommended ratios for different str

关键词： carbon reduction and solidification dredged soil abandoned shells orthogonal test chemical additives(lime and cement) unconfined compressive strength(UCS)

Dual‑Donor‑Induced Crystallinity Modulation Enables 19.23% Efficiency Organic Solar Cells

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 2025年第3期17卷 376-388页

作者： Anhai Liang Yuqing sun Sein Chung Jiyeong Shin Kangbo sun Chaofeng Zhu Jingjing Zhao Zhenmin Zhao Yufei Zhong Guangye Zhang Kilwon Cho Zhipeng Kan Center On Nanoenergy Research Institute of Science and Technology for Carbon Peak&NeutralitySchool of Physical Science&TechnologyGuangxi UniversityNanning 530004People’s Republic of China Department of Chemical Engineering Pohang University of Science and TechnologyPohang 37673South Korea College of New Materials and New Energies Shenzhen Technology UniversityShenzhen 518118People’s Republic of China Zhejiang Engineering Research Center for Fabrication and Application of Advanced Photovoltaic Materials School of Materials Science and EngineeringNingboTech UniversityNingbo 315100People’s Republic of China State Key Laboratory of Featured Metal Materials and Life-Cycle Safety for Composite Structures Nanning 530004People’s Republic of China

Trap-assisted charge recombination is one of the primary limitationsof restricting the performance of organic solar cells. However, effectivelyreducing the presence of traps in the photoactive layer remains ***, wide bandgap polymer donor PTzBI-dF is demonstrated as an effectivemodulator for enhancing the crystallinity of the bulk heterojunction active layerscomposed of D18 derivatives blended with Y6, leading to dense and orderedmolecular packings, and thus, improves photoluminescence quenching *** a result, the photovoltaic devices exhibit reduced trap-assisted charge recombinationlosses, achieving an optimized power conversion efficiency of over 19%.Besides the efficiency enhancement, the devices comprised of PTzBI-dF as athird component simultaneously attain decreased current leakage, improved chargecarrier mobilities, and suppressed bimolecular charge recombination, leading toreduced energy losses. The advanced crystalline structures induced by PTzBI-dFand its characteristics, such as well-aligned energy level, and complementaryabsorption spectra, are ascribed to the promising performance *** findings suggest that donor phase engineering is a feasible approach to tuning the molecular packings in the active layer, providingguidelines for designing effective morphology modulators for high-performance organic solar cells.

关键词： Trap-assisted charge recombination Photoluminescence Miscibility Current leakage Power conversion efficiency