检索结果-内蒙古大学图书馆

Analyzing topics in social media for improving digital twinning based product development

Digital Communications and Networks 2024年第2期10卷 273-281页

作者： Wenyi Tang Ling Tian Xu Zheng Ke Yan School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu611731China

Digital twinning enables manufacturers to create digital representations of physical entities,thus implementing virtual simulations for product *** efforts of digital twinning neglect the decisive consumer feedback in product development stages,failing to cover the gap between physical and digital *** work mines real-world consumer feedbacks through social media topics,which is significant to product *** specifically analyze the prevalent time of a product topic,giving an insight into both consumer attention and the widely-discussed time of a *** primary body of current studies regards the prevalent time prediction as an accompanying task or assumes the existence of a preset ***,these proposed solutions are either biased in focused objectives and underlying patterns or weak in the capability of generalization towards diverse *** this end,this work combines deep learning and survival analysis to predict the prevalent time of *** propose a specialized deep survival model which consists of two *** first module enriches input covariates by incorporating latent features of the time-varying text,and the second module fully captures the temporal pattern of a rumor by a recurrent network ***,a specific loss function different from regular survival models is proposed to achieve a more reasonable *** experiments on real-world datasets demonstrate that our model significantly outperforms the state-of-the-art methods.

关键词： Digital twinning Product development Topic analysis Social media

来源：评论

学校读者我要写书评

暂无评论

A Global-Local Parallel Dual-Branch Deep Learning Model with Attention-Enhanced Feature Fusion for Brain Tumor MRI Classification

引用

computers, Materials & Continua 2025年第4期83卷 739-760页

作者： Zhiyong Li Xinlian Zhou School of Computer Science and Engineering Hunan University of Science and TechnologyXiangtan411100China

Brain tumor classification is crucial for personalized treatment *** deep learning-based Artificial Intelligence(AI)models can automatically analyze tumor images,fine details of small tumor regions may be overlooked during global feature ***,we propose a brain tumor Magnetic Resonance Imaging(MRI)classification model based on a global-local parallel dual-branch *** global branch employs ResNet50 with a Multi-Head Self-Attention(MHSA)to capture global contextual information from whole brain images,while the local branch utilizes VGG16 to extract fine-grained features from segmented brain tumor *** features from both branches are processed through designed attention-enhanced feature fusion module to filter and integrate important ***,to address sample imbalance in the dataset,we introduce a category attention block to improve the recognition of minority *** results indicate that our method achieved a classification accuracy of 98.04%and a micro-average Area Under the Curve(AUC)of 0.989 in the classification of three types of brain tumors,surpassing several existing pre-trained Convolutional Neural Network(CNN)***,feature interpretability analysis validated the effectiveness of the proposed *** suggests that the method holds significant potential for brain tumor image classification.

关键词： Deep learning attention mechanism feature fusion dual-branch structure brain tumor MRI classification

来源：评论

学校读者我要写书评

暂无评论

Total ionizing dose effect modeling method for CMOS digital-integrated circuit

引用

Nuclear science and Techniques 2024年第2期35卷 32-46页

作者： Bo Liang Jin-Hui Liu Xiao-Peng Zhang Gang Liu Wen-Dan Tan Xin-Dan Zhang School of Computer Science and Technology Xidian UniversityXi’an 710071China

Simulating the total ionizing dose(TID)of an electrical system using transistor-level models can be difficult and expensive,particularly for digital-integrated circuits(ICs).In this study,a method for modeling TID effects in complementary metaloxide semiconductor(CMOS)digital ICs based on the input/output buffer information specification(IBIS)was *** digital IC was first divided into three parts based on its internal structure:the input buffer,output buffer,and functional *** of these three parts was separately *** the IBIS model,the transistor V-I characteristic curves of the buffers were processed,and the physical parameters were extracted and modeled using *** the functional area,logic functions were modeled in VHDL according to the data sheet.A golden digital IC model was developed by combining the input buffer,output buffer,and functional area ***,the golden ratio was reconstructed based on TID experimental data,enabling the assessment of TID effects on the threshold voltage,carrier mobility,and time series of the digital *** experiments were conducted using a CMOS non-inverting multiplexer,NC7SZ157,and the results were compared with the simulation results,which showed that the relative errors were less than 2%at each dose *** confirms the practicality and accuracy of the proposed modeling *** TID effect model for digital ICs developed using this modeling technique includes both the logical function of the IC and changes in electrical properties and functional degradation impacted by TID,which has potential applications in the design of radiation-hardening tolerance in digital ICs.

关键词： CMOS digital-integrated circuit Total ionizing dose IBIS model Behavior-physical hybrid model Physical parameters

来源：评论

学校读者我要写书评

暂无评论

Incorporating contextual evidence to improve implicit discourse relation recognition in Chinese

引用

Frontiers of computer science 2024年第3期18卷 91-104页

作者： Sheng XU Peifeng LI Qiaoming ZHU School of Computer Science and Technology Soochow UniversitySuzhou 215000China

The discourse analysis task,which focuses on understanding the semantics of long text spans,has received increasing attention in recent *** a critical component of discourse analysis,discourse relation recognition aims to identify the rhetorical relations between adjacent discourse units(e.g.,clauses,sentences,and sentence groups),called arguments,in a *** works focused on capturing the semantic interactions between arguments to recognize their discourse relations,ignoring important textual information in the surrounding ***,in many cases,more than capturing semantic interactions from the texts of the two arguments are needed to identify their rhetorical relations,requiring mining more contextual *** this paper,we propose a method to convert the RST-style discourse trees in the training set into dependency-based trees and train a contextual evidence selector on these transformed *** this way,the selector can learn the ability to automatically pick critical textual information from the context(i.e.,as evidence)for arguments to assist in discriminating their *** we encode the arguments concatenated with corresponding evidence to obtain the enhanced argument ***,we combine original and enhanced argument representations to recognize their *** addition,we introduce auxiliary tasks to guide the training of the evidence selector to strengthen its selection *** experimental results on the Chinese CDTB dataset show that our method outperforms several state-of-the-art baselines in both micro and macro F1 scores.

关键词： discourse parsing discourse relation recognition contextual evidence selection

来源：评论

学校读者我要写书评

暂无评论

Penetration resistance of Al_(2)O_(3) ceramic-ultra-high molecular weight polyethylene(UHMWPE)composite armor:Experimental and numerical investigations

引用

Theoretical & Applied Mechanics Letters 2024年第5期14卷 346-359页

作者： Wencheng Lu Yiding Wu Minghui Ma Yilei Yu Xuan Zhou Guangfa Gao School of Mechanical Engineering Nanjing University of Science and TechnologyNanjing 210094China

To enhance the protective performance of ceramic composite armor,ballistic penetration experiments were conducted on Al_(2)O_(3) ceramic-ultra-high molecular weight polyethylene(UHMWPE)composite armor with different thickness *** damage and failure modes of hard projectiles and ceramic-fiber composite targets were *** recovered projectiles and ceramic fragments were sieved and weighed at multiple stages,revealing a positive correlation between the degree of fragmentation of the projectiles and ceramics and the overall ballistic resistance of the composite *** simulations were performed using the LS-DYNA finite element software,and the simulation results showed high consistency with the experimental results,confirming the validity of the material *** results indicate that the projectile heads primarily exhibited crushing and abrasive *** projectile fragments mainly resulted from tensile and shear stress-induced *** failure modes of the composite targets included the formation of ceramic cones and radial cracks under high-velocity *** UHMWPE laminated plates exhibited interlayer separation caused by tensile waves,permanent plastic deformation of the rear surface bulging,and perforation failure primarily due to shear *** extended numerical simulations,while maintaining the same areal density and configuration of9 mm Al_(2)O_(3) ceramic+12 mm UHMWPE laminated composite armor,the thickness configurations of the Al_(2)O_(3) ceramic and UHMWPE laminated backplates were varied,and various thicknesses of UHMWPE laminates were simulated as the cover layer for the ceramic *** simulation results indicated that the composite armor configuration of 10 mm Al_(2)O_(3) ceramic+8 mm UHMWPE composite armor increased energy absorption by13.48%.When altering the cover layer thickness,a 4 mm UHMWPE+9 mm Al_(2)O_(3)+8 mm UHMWPE composite armor demonstrated a 27.11%improvement in energy abso

关键词： Composite armor Al_(2)O_(3) ceramic UHMWPE laminates Damage and failure modes Ballistic performance Numerical simulation

来源：评论

学校读者我要写书评

暂无评论

Towards Effective Author Name Disambiguation by Hybrid Attention

引用

Journal of computer science & technology 2024年第4期39卷 929-950页

作者： Qian Zhou Wei Chen Peng-Peng Zhao An Liu Jia-Jie Xu Jian-Feng Qu Lei Zhao School of Computer Science and Technology Soochow UniversitySuzhou 215006China

Author name disambiguation(AND)is a central task in academic search,which has received more attention recently accompanied by the increase of authors and academic *** tackle the AND problem,existing studies have proposed various approaches based on different types of information,such as raw document features(e.g.,co-authors,titles,and keywords),the fusion feature(e.g.,a hybrid publication embedding based on multiple raw document features),the local structural information(e.g.,a publication's neighborhood information on a graph),and the global structural information(e.g.,interactive information between a node and others on a graph).However,there has been no work taking all the above-mentioned information into account and taking full advantage of the contributions of each raw document feature for the AND problem so *** fill the gap,we propose a novel framework named EAND(Towards Effective Author Name Disambiguation by Hybrid Attention).Specifically,we design a novel feature extraction model,which consists of three hybrid attention mechanism layers,to extract key information from the global structural information and the local structural information that are generated from six similarity graphs constructed based on different similarity coefficients,raw document features,and the fusion *** hybrid attention mechanism layer contains three key modules:a local structural perception,a global structural perception,and a feature ***,the mean absolute error function in the joint loss function is used to introduce the structural information loss of the vector *** results on two real-world datasets demonstrate that EAND achieves superior performance,outperforming state-of-the-art methods by at least+2.74%in terms of the micro-F1 score and+3.31%in terms of the macro-F1 score.

关键词： author name disambiguation multiple-feature information hybrid attention pruning strategy structural information loss of vector space

来源：评论

学校读者我要写书评

暂无评论

A Context-Aware Edge-Cloud Collaboration Framework for QoS Prediction

引用

清华大学学报自然科学版（英文版） 2025年第3期30卷 1201-1214页

作者： Yong Cheng Weihao Cao Hao Fang Shaobo Zang School of Software Nanjing University of Information Science and TechnologyNanjing 210044China Reading Academy Nanjing University of Information Science and TechnologyNanjing 210044China

The rapid growth of online services has led to the emergence of many with similar functionalities,making it necessary to predict their non-functional attributes,namely quality of service(QoS).Traditional QoS prediction approaches require users to upload their QoS data to the cloud for centralized training,leading to high user data upload *** the help of edge computing,users can upload data to edge servers(ESs)adjacent to them for training,reducing the upload ***,shallow models like matrix factorization(MF)are still used,which cannot sufficiently extract context features,resulting in low prediction *** this paper,we propose a context-aware edge-cloud collaboration framework for QoS prediction,named ***,to reduce the users upload latency,a distributed model training algorithm is designed with the collaboration of ESs and ***,a context-aware prediction model based on convolutional neural network(CNN)and integrating attention mechanism is proposed to improve the *** based on real-world dataset demonstrate that CQEC outperforms the baselines.

关键词： QoS prediction context-aware edge-cloud collaboration web service

来源：评论

学校读者我要写书评

暂无评论

Exploring spatial impacts of transportation infrastructure on financial agglomeration: A moderating role of knowledge spillovers

引用

Transport Policy 2025年 169卷 150-166页

作者： Lu, Ke Wei, Yunlin School of Management Science and Engineering Nanjing University of Information Science & Technology Nanjing210044 China

With the rapid development of economy and ongoing financial reform in China, the phenomenon of financial agglomeration has aroused considerable attention. Currently, the determinants for financial agglomeration have been extensively studied. However, there remains a dearth of research exploring the relationship between transportation infrastructure and financial agglomeration from the perspective of external factors. To better understand the impact of transportation infrastructure on financial agglomeration, this study considers knowledge spillovers as a moderating factor. An empirical analysis was conducted using data collected in China from 2003 to 2022. The Spatial Durbin Model was employed to analyze the spatial impact of transportation infrastructure on financial agglomeration. Moreover, the moderating effect of knowledge spillovers and heterogeneity across geographical regions and urban scales was investigated. The results indicate that: (1) The development of transportation infrastructure has been evidenced to promote financial agglomeration. (2) Knowledge spillovers, as a moderating variable, weakens the driving effect of transportation infrastructure on financial agglomeration. (3) Transportation infrastructure enhances financial agglomeration in eastern and large-scale regions. Conversely, in western and small-scale regions, its impact is not significant. The findings shed light on the understanding of relationship between transportation infrastructure and financial agglomeration, and provide practical insights for policymakers. © 2025 Elsevier Ltd

关键词： Urban transportation

来源：评论

学校读者我要写书评

暂无评论

LogCSS: Log anomaly detection based on BERT-CNN with context-semantics-statistics features

引用

Journal of Intelligent and Fuzzy Systems 2024年第4期46卷 7659-7676页

作者： Li, Zhongliang Tu, Xuezhen Gao, Hong Huang, Shiyue Ma, Zongmin College of Computer Science & Technology Nanjing University of Aeronautics and Astronautics Nanjing China School of Computer Science Peking University Beijing China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing China

With the development of artificial intelligence, deep-learning-based log anomaly detection proves to be an important research topic. In this paper, we propose LogCSS, a novel log anomaly detection framework based on the Context-Semantics-Statistics Convolutional Neural Network (CSSCNN). It is the first model that uses BERT (Bidirectional Encoder Representation from Transformers) and CNN (Convolutional Neural Network) to extract the semantic, temporal, and correlational features of the logs. We combine the features with the statistic information of log templates for the classification model to improve the accuracy. We also propose a technique, DOOT (Deals with the Out-Of-Templates), for online template matching. The experimental research shows that our framework improves the average F1 score of the six best algorithms in the industry by more than 5% on the open-source dataset HDFS, and improves the average F1 score of the six best algorithms in the industry by more than 8% on the BGL dataset, LogCSS also performs better than other similar methods on our own constructed dataset. © 2024 – IOS Press.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Adaptive Fine-Tuning and Feature Enhancement of SAM for Remote Sensing Instance Segmentation 9

Adaptive Fine-Tuning and Feature Enhancement of SAM for Remo...

引用

9th IEEE International Conference on Progress in Informatics and Computing, PIC 2024

作者： Zhao, Zhixin Liu, Yangguang Meng, Lingwu Zhang, Haochen Zhu, Mingyang Xiao, Liang School of Computer Science and Technology Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9798350363203

Remote sensing image instance segmentation aims to accurately separate independent objects and automatically identify land attributes. Recent advancements in large models have propelled self-supervised learning, especially with the segment anything model (SAM). Although SAM can generate instance segmentation masks without additional training, its application to remote sensing images still faces challenges, such as a severe reliance on manual prior prompts, inaccuracies in detail segmentation, and insufficient generalization capability. Therefore, to enhance the generalization capability of SAM in the field of remote sensing images, we propose a SAM-based fine-tuning model called AFFE-SAM. This model combines adaptive low-rank (AdaLoRA) and variable adapter (MiMi-Adapter) fine-tuning methods. Additionally, it improves mask quality in the decoder by employing adaptive multi-scale feature enhancement. We conducted experiments on two datasets, obtaining mAP scores of 66.5 for the NWPU VHR-10 dataset and 67.1 for the SSDD dataset. The evaluation results validate the effectiveness of our method. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：