检索结果-内蒙古大学图书馆

A GENERALIZED PENALTY METHOD FOR DIFFERENTIAL VARIATIONAL-HEMIVARIATIONAL INEQUALITIES

Acta Mathematica Scientia 2022年第1期42卷 247-264页

作者： Liang LU Lijie LI Mircea SOFONEA Guangxi Key Laboratory of Cross-border E-commerce Intelligent Information Processing Guangxi University of Finance and EconomicsNanning 530003China Guangxi Colleges and Universities Key Laboratory of Complex System Optimization and Big Data Processing Yulin Normal UniversityYulin 537000China Laboratoire de Mathématiques et Physique Universitéde Perpignan Via Domitia52 Avenue Paul Alduy66860 PerpignanFrance

We consider a differential variational-hemivariational inequality with constraints,in the framework of reflexive Banach *** existence of a unique mild solution of the inequality,together with its stability,was proved in[1].Here,we complete these results with existence,uniqueness and convergence results for an associated penalty-type *** this end,we construct a sequence of perturbed differential variational-hemivariational inequalities governed by perturbed sets of constraints and penalty *** prove the unique solvability of each perturbed inequality as well as the convergence of its solution to the solution of the original ***,we consider a mathematical model which describes the equilibrium of a viscoelastic rod in unilateral *** weak formulation of the model is in a form of a differential variational-hemivariational inequality in which the unknowns are the displacement field and the history of the *** apply our abstract penalty method in the study of this inequality and provide the corresponding mechanical interpretations.

关键词： differential variational-hemivariational inequality generalized penalty method Mosco convergence viscoelastic rod unilateral constraint

来源：评论

学校读者我要写书评

暂无评论

Extraction of transitional relations in healthcare processes from Chinese medical text based on deep learning 2019

Extraction of transitional relations in healthcare processes...

引用

4th International Conference on Mathematics and Artificial Intelligence, ICMAI 2019

作者： Ren, Fangwen Yuan, Song Gao, Feng School of Computer Science and Technology Key Laboratory of Intelligent Information Processing and Real-time Industrial System in Hubei Province Institute of Big Data Science and Engineering Wuhan University of Science and Technology China

ISBN: (纸本)9781450362580

Knowledge extraction in healthcare has become a recent research hotspot due to the rapid development of AI technology as well as the urgent demand in the medicine research and practice. Traditional methods focus on extracting terms and relations using pattern matching and machine learning, but they depend on the construction of rules and the accuracy of feature extraction. In contrast, deep learning methods have a stronger ability to process data with high dimensions. Moreover, current study neglects the fact that the key knowledge in medicine is the process of diagnosing and treating patients, i.e., the relations that causes the status change in a healthcare workflow. This paper first identifies the relations relevant for medical processes, and adopts the method of relationship extraction based on Bidirection Gated Recurrent Unit (BiGRU) model and attention mechanism (BiGRU-ATT), in order to retrieve these relations from Chinese medical text. The experimental results show that regarding Chinese medical entity relationship extraction, we can achieve better accuracy rate and recall rate than using convolutional neural network(CNN). © 2019 Association for Computing Machinery.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Multimodal Image-Text Representation Learning for Sketch-Less Facial Image Retrieval

Multimodal Image-Text Representation Learning for Sketch-Les...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Dawei Dai Yingge Liu Shiyu Fu Guoyin Wang Chongqing Key Laboratory of Computational Intelligence Key Laboratory of Big Data Intelligent Computing Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing University of Posts and Telecommunications Chongqing China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Sketch-less facial image retrieval (SLFIR) framework aims to break the barriers that drawing a high-quality facial sketch requires excellent skills and substantial time, it performs the retrieval using a partial sketch with as few strokes as possible. However, such early-stage sketches often contain only local details, resulting in poor retrieval performance. In this study, we propose learning of the representation by fusing the sketches with prior human semantic knowledge to improve the early retrieval performance. Specifically, (1) based on the LAION-Face dataset, a facial language-image pretraining (FLIP) model is constructed to learn the aligned representations of facial image and text; (2) subsequently, using FLIP as the backbone, multiscale features of sketch and text are extracted and fused to learn the efficient representation for the final retrieval. The proposed method achieves state-of-the-art early retrieval performance on all two public datasets and exhibits a good generalization ability in practical testing.

关键词： Representation learning Semantics Image retrieval Feature extraction Faces Testing

来源：评论

学校读者我要写书评

暂无评论

Community Detection Based on Deep Network Embedding with Dual Self-supervised Training 3rd

Community Detection Based on Deep Network Embedding with Dua...

引用

3rd International Conference on Big data and security, ICBDS 2021

作者： Chen, Yunfang Mao, Haotian Wang, Li Zhang, Wei School of Computer Science Nanjing University of Posts and Telecommunications Jiangsu Nanjing210023 China Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing University of Posts and Telecommunications Jiangsu Nanjing210023 China

ISBN: (纸本)9789811908514

We propose a community discovery method based on deep auto-encoding (DGAE_DST). Firstly, we use the pre-trained two-layer neural network and k-means algorithm to initialize the centroid vector, and then use the DNN module and the GCN module to capture the structure features and attributes respectively. The attribute information is fed to the GCN layer to integrate the structure information and attributes. Finally, DNN and GCN respectively output the reconstructed adjacency matrix and feature matrix, and minimize their loss from the original matrix. The experimental results on four datasets show that the DGAE_DST method has higher stability and accuracy. © 2022, Springer Nature Singapore Pte Ltd.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Binary particle swarm optimization with multiple evolutionary strategies

引用

Science China(Information Sciences) 2012年第11期55卷 2485-2494页

作者： ZHAO Jing1,HAN ChongZhao1 & WEI Bin2 1Ministry of Education key Lab For intelligent Networks and Network security,State key laboratory for Manufacturing systems Engineering,Institute of Integrated Automation,School of Electronics and Information Engineering,Xi'an Jiaotong University,Xi'an 710049,China 2Institute of system Engineering,School of Electronics and Information Engineering,Xi'an Jiaotong University,Xi'an 710049,China 1. Ministry of Education Key Lab For Intelligent Networks and Network Security State Key Laboratory for Manufacturing Systems Engineering Institute of Integrated Automation School of Electronics and Information Engineering Xi’an Jiaotong University Xi’an 710049 China2. Institute of System Engineering School of Electronics and Information Engineering Xi’an Jiaotong University Xi’an 710049 China

This paper introduces a novel variation of binary particle swarm optimization(BPSO) algorithm and a further extension to improve its ***,mimicking the behaviors of some creatures group,multiple evolutionary strategies BPSO(MBPSO) is introduced which takes different evolutionary strategies for various particles according to their ***,on the basis of MBPSO,a new strategy is discussed to improve the performance of the MBPSO(M2BPSO) which adopts the concept of the mutation operator aiming to overcome the premature convergence and slow convergent speed during the later stages of the *** proposed two algorithms are tested on seven benchmark functions and their results are compared with those obtained by other *** results show that our methods outperform the other algorithms.

关键词： binary particle swarm optimizer evolutionary strategies swarm intelligence

来源：评论

学校读者我要写书评

暂无评论

PSRAKA: Physically Secure and Robust Authenticated key Agreement for VANETs

引用

IEEE Transactions on Vehicular Technology 2024年第5期74卷 7953-7968页

作者： Liu, Gao Li, Hao Liang, Yangfan Le, Junqing Wang, Ning Mu, Nankun Liu, Zhiquan Liu, Yining Xiang, Tao Chongqing University College of Computer Science Chongqing400044 China Jiaxing University Provincial Key Laboratory of Multimodal Perceiving and Intelligent Systems The Institute of Information Network and Artificial Intelligence The Key Laboratory of Medical Electronics and Digital Health of Zhejiang Province The Engineering Research Center of Intelligent Human Health Situation Awareness of Zhejiang Province Jiaxing314001 China Jinan University College of Cyber Security Guangzhou510632 China Wenzhou University of Technology School of Data Science and Artificial Intelligence Wenzhou325000 China

Authenticated key agreement (AKA) allows vehicles and road side units (RSUs) to mutually authenticate and establish shared session keys, which can be implemented to secure vehicular ad-hoc networks (VANETs). However, most of existing relative schemes fail to support physical security and tracing robustness, and lack a mechanism to balance pseudonym unlinkability and system efficiency. In this paper, we propose PSRAKA, a physically secure and robust authenticated key agreement scheme for VANETs, which enables anonymous authentication on vehicles through chameleon hash functions. In particular, physical security is guaranteed by integrating physical unclonable functions and fuzzy extractors to resist against physical capture attacks. Our scheme is the first to support robustness by allowing the vehicle and central authority to jointly sign or commit to the vehicle's real identity, chameleon hash value and public key for binding to ensure public verification and prevent malicious accusations during tracing. Meanwhile, it is the first to model the relationship of vehicle pseudonym unlinkability and system efficiency for balance by formulating the unlinkability based on the frequency of pseudonym updates. PSRAKA achieves anonymity, conditional privacy, robustness, key escrow freeness and physical security, and resists against most known attacks. Comprehensive performance analysis and evaluation suggest the potential usability of PSRAKA. © 1967-2012 IEEE.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

BSL: Understanding and Improving Softmax Loss for Recommendation 40

BSL: Understanding and Improving Softmax Loss for Recommenda...

引用

40th IEEE International Conference on data Engineering, ICDE 2024

作者： Wu, Junkang Chen, Jiawei Wu, Jiancan Shi, Wentao Zhang, Jizhi Wang, Xiang University of Science and Technology of China MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition Hefei China Zhejiang Unversity The State Key Laboratory of Blockchain and Data Security China Institute of Artificial Intelligence Institute of Dataspace Hefei Comprehensive National Science Center. China

ISBN: (纸本)9798350317152

Loss functions steer the optimization direction of recommendation models and are critical to model performance, but have received relatively little attention in recent recommendation research. Among various losses, we find Softmax loss (SL) stands out for not only achieving remarkable accuracy but also better robustness and fairness. Nevertheless, the current literature lacks a comprehensive explanation for the efficacy of SL. Toward addressing this research gap, we conduct theoretical analyses on SL and uncover three insights: 1) Optimizing SL is equivalent to performing Distributionally Robust Optimization (DRO) on the negative data, thereby learning against perturbations on the negative distribution and yielding robustness to noisy negatives. 2) Comparing with other loss functions, SL implicitly penalizes the prediction variance, resulting in a smaller gap between predicted values and and thus producing fairer results. Building on these insights, we further propose a novel loss function Bilateral SoftMax Loss (BSL) that extends the advantage of SL to both positive and negative sides. BSL augments SL by applying the same Log-Expectation-Exp structure to positive examples as is used for negatives, making the model robust to the noisy positives as well. Remarkably, BSL is simple and easy-to-implement -requiring just one additional line of code compared to SL. Experiments on four real-world datasets and three representative backbones demonstrate the effectiveness of our proposal. The code is available at https://***/junkangwu/BSL. © 2024 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Byzantine-Robust Federated Learning on Non-IID data via Inversing Artificial Gradients

Byzantine-Robust Federated Learning on Non-IID Data via Inve...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Li, Minyang Tang, Xiangyun Zhang, Tao Liu, Guangyuan Weng, Yu Minzu University of China Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance China Beijing Jiaotong University School of Software Engineering China Nanyang Technological University College of Computing and Data Science Singapore

ISBN: (纸本)9798350351255

Federated Learning (FL) is a distributed machine learning framework that enhances privacy by enabling multiple participants to train a global model without sharing their raw data. However, FL still faces the threat posed by data and Byzantine attacks (e.g., data poisoning and model poisoning attacks) from malicious clients aimed to decrease the FL global training accuracy. Previous studies have proposed solutions to improve the robustness of FL systems. However, these robust approaches have not effectively defended against Byzantine attacks from malicious clients in non-Independent and Identically Distributed (non-IID) environments, decreasing overall training accuracy. In this work to address this issues, we propose a new defence framework that aims to enhance model accuracy against Byzantine attacks from malicious clients in non-IID environments. In our approach, the central server performs the Inverse Deep Learning Gradient attack using the gradient data submitted by users in each round, obtaining an inversed artificial gradient. We then assess the squared L2 norm difference between this inversed gradient and the actual gradients to detect malicious clients. Simultaneously, we assign weights to each client involved in the aggregation based on differences in the squared L2 norm, aiming to minimize the impact of malicious actors on the overall model. We have experimentally evaluated our method and demonstrated its ability to maintain training accuracy under attack in non-IID environments using standard datasets. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Robust Network For Segmenting Roof Planes From Sparse Point Clouds 36

Robust Network For Segmenting Roof Planes From Sparse Point ...

引用

36th International Conference on Software Engineering and Knowledge Engineering, SEKE 2024

作者： Fu, Hang Zeng, Cheng Key Laboratory of Intelligent Sensing System and Security Hubei University Ministry of Education Wuhan China School of Computer and Information Engineering Hubei University Wuhan China School of Artificial Intelligence Hubei University Wuhan China

ISBN: (纸本)1891706594

The plane is the fundamental characteristic for describing the shape of polyhedral buildings. Roof plane segmentation of airborne LiDAR point clouds is an important step in 3D building model reconstruction. Existing methods are either non-automatic and efficient traditional methods, or hindered by the lack of datasets for roof plane segmentation and therefore fail to achieve good training for deep learning methods. To address the above issues, we proposes an end-to-end network called PUTr for roof plane segmentation of sparse point clouds. This network integrates a Point-cloud Upsampling module and Transformer to ensure effective generalization even when trained on low-density datasets, while also capturing dependency relationships within point cloud neighborhoods. Our model overcomes the low automation and manual intervention of existing methods, and the limited generalization of deep learning due to scarce high-quality datasets. Evaluations also demonstrate its effectiveness in roof plane segmentation of laser point cloud data. © 2024 Knowledge systems Institute Graduate School. All rights reserved.

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

FedCSA: Boosting the Convergence Speed of Federated Unlearning under data Heterogeneity 21

FedCSA: Boosting the Convergence Speed of Federated Unlearni...

引用

21st IEEE International Symposium on Parallel and Distributed Processing with Applications, 13th IEEE International Conference on Big data and Cloud Computing, 16th IEEE International Conference on Social Computing and Networking and 13th International Conference on Sustainable Computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2023

作者： Wang, Zhen Alghazzawi, Daniyal M Cheng, Li Liu, Gaoyang Wang, Chen Cheng, Zeng Yang, Yang Hubei University Key Laboratory of Intelligent Sensing System and Security Ministry of Education School of Artificial Intelligence Wuhan China King Abdulaziz University Jeddah Saudi Arabia Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9798350329223

The exponential growth of the Internet and the widespread availability of personal data have raised significant concerns regarding personal privacy and societal security. In response, the 'right to be forgotten' has emerged as a fundamental principle, empowering individuals to request the removal of their personal data. Though relieving the privacy concerns at a certain degree by doing so, Artificial Intelligence (AI) models, trained by personal data, still suffers from privacy leakage risks. Therefore, machine unlearning attracts great attention from both industry and academia, aiming at erasing the risks of privacy leakage of AI models. However, existing machine unlearning methods primarily operate within centralized frame-works, limiting their applicability to decentralized Federated Learning (FL) settings where data is decentralized and not directly accessible. Additionally, current federated unlearning methods only approximate data deletion, leaving a potential risk of data leakage. To address these issues, this paper presents FedCSA, The FedCSA approach adopts a divide-and-conquer strategy by clustering and slicing the users' data. Subsequently, submodels are trained on each individual slice, and their aggregation yields the global model. During the unlearning task, only the corresponding sub-model undergoes retraining, significantly reducing training time while ensuring data privacy and achieving precise data deletion. Extensive experiments are conducted on real-world datasets, including MNIST, Fashion-MNIST, and CIFAR-10, to evaluate the performance of FedCSA. The results demonstrate that FedCSA outperforms state-of-the-art machine learning methods, such as retrain and SISA, in terms of efficiency and global model performance. Our code is publicly available at https://***/ZhenWang9/FedCSA. © 2023 IEEE.

关键词： data privacy

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：