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

A fast image compression algorithm based on wavelet transform

引用

International Journal of Circuits, Systems and Signal Processing 2021年 15卷 809-819页

作者： Li, Xiangjun Zhang, Shuili Zhao, Haibo College of Physics and Electronic Information Yan'an University Yan’an Shaanxi716000 China Shaanxi Key Laboratory of Intelligent Processing for Big Energy Data Yan'an University Yan’an Shaanxi716000 China

—With multimedia becoming widely popular, the conflict between mass data and finite memory devices has been continuously intensified;so, it requires more convenient, efficient and high-quality transmission and storage technology and meanwhile, this is also the researchers’ pursuit for highly efficient compression technology and it is the fast image transmission that is what people really seek. This paper mainly further studies wavelet analysis and fractal compression coding, proposes a fast image compression coding method based on wavelet transform and fractal theory, and provides the theoretical basis and specific operational approaches for the algorithm. It makes use of the smoothness of wavelet, the high compression ratio of fractal compression coding and the high quality of reconstructed image. It firstly processes the image through wavelet transform. Then it introduces fractal features and classifies the image according to the features of image sub-blocks. Each class selects the proper features. In this way, for any sub-block, it only needs to search the best-matched block in a certain class according to the corresponding features. With this method, it can effectively narrow the search in order to speed up coding and build the relation of inequality between the sub-block and the matching mean square error. So, it can effectively combine wavelet transform with fractal theory and further improves the quality of reconstructed image. By comparing the simulation experiment, it. © 2021, North Atlantic University Union NAUN. All rights reserved.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

Partial Label Feature Selection: An Adaptive Approach

引用

IEEE Transactions on Knowledge and data Engineering 2024年第8期36卷 4178-4191页

作者： Zan Zhang Jialu Yao Lin Liu Jiuyong Li Lei Li Xindong Wu Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) Hefei Anhui China School of Computer Science and Information Engineering Hefei University of Technology Hefei Anhui China Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei Anhui China UniSA STEM University of South Australia Adelaide SA Australia Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) School of Computer Science and Information Engineering Hefei University of Technology Hefei Anhui China Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) Hefei University of Technology Hefei Anhui China

As an emerging weakly supervised learning framework, partial label learning aims to induce a multi-class classifier from ambiguous supervision information where each training example is associated with a set of candidate labels, among which only one is the true label. Traditional feature selection methods, either for single label and multiple label problems, are not applicable to partial label learning as the ambiguous information contained in the label space obfuscates the importance of features and misleads the selection process. This makes the selection of a proper feature subset from partial label examples particularly challenging, and therefore has rarely been investigated. In this paper, we propose a novel feature selection algorithm for partial label learning, named PLFS, which considers not only the relationships between features and labels, but also exploits the relationships between instances to select the most informative and important features to enhance the performance of partial label learning. PLFS constructs an adaptive weighted graph to exploit the similarity information among instances, differentiate the label space and weight the feature space, which leads to the selection of a proper feature subset. Extensive experiments over a broad range of benchmark data sets clearly validate the effectiveness of our proposed feature selection approach.

关键词： Feature extraction Supervised learning Training Knowledge engineering Labeling Classification algorithms big data

来源：评论

学校读者我要写书评

暂无评论

RegMixMatch: Optimizing Mixup Utilization in Semi-Supervised Learning 39

RegMixMatch: Optimizing Mixup Utilization in Semi-Supervised...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Han, Haorong Yuan, Jidong Wei, Chixuan Yu, Zhongyang Key Laboratory of Big Data and Artificial Intelligence in Transportation Ministry of Education China School of Computer Science and Technology Beijing Jiaotong University China School of Data Science and Intelligent Media Communication University of China China

ISBN: (纸本)157735897X

Consistency regularization and pseudo-labeling have significantly advanced semi-supervised learning (SSL). Prior works have effectively employed Mixup for consistency regularization in SSL. However, our findings indicate that applying Mixup for consistency regularization may degrade SSL performance by compromising the purity of artificial labels. Moreover, most pseudo-labeling based methods utilize thresholding strategy to exclude low-confidence data, aiming to mitigate confirmation bias;however, this approach limits the utility of unlabeled samples. To address these challenges, we propose RegMixMatch, a novel framework that optimizes the use of Mixup with both high- and low-confidence samples in SSL. First, we introduce semi-supervised RegMixup, which effectively addresses reduced artificial labels purity by using both mixed samples and clean samples for training. Second, we develop a class-aware Mixup technique that integrates information from the top-2 predicted classes into low-confidence samples and their artificial labels, reducing the confirmation bias associated with these samples and enhancing their effective utilization. Experimental results demonstrate that RegMixMatch achieves state-of-the-art performance across various SSL benchmarks. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

RGB-D Based Visual Navigation Using Direction Estimation Module 18th

RGB-D Based Visual Navigation Using Direction Estimation Mod...

引用

18th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2021

作者： Luo, Chao Bi, Sheng Dong, Min Nie, Hongxu School of Computer Science and Engineering South China University of Technology Guangdong Guangzhou510006 China Key Laboratory of Big Data and Intelligent Robot Ministry of Education Guangdong Guangzhou510006 China

ISBN: (纸本)9783030893699

Target-driven visual navigation without mapping works to solve navigation problems that given a target object, mobile robots can navigate to the target object. Recently, visual navigation has been researched and improved largely by learning-based methods. However, their methods lack depth information and spatial perception, using only single RGB images. To overcome these problems, two methods are presented in this paper. Firstly, we encode visual features of objects by dynamic graph convolutional network and extract 3D spatial features for objects by 3D geometry, a high level visual feature for agent to easily understand object relationship. Secondly, as human beings, they solve this problem in two steps, first exploring a new environment to find the target object and second planning a path to arrive. Inspired by the way of humans navigation, we propose direction estimation module (DEM) based on RGB-D images. DEM provides direction estimation of the target object to our learning model by a wheel odometry. Given a target object, first stage, our agent explores an unseen scene to detect the target object. Second stage, when detected the target object, we can estimate current location of the target object by 3D geometry, after that, each step of the agent, DEM will estimate new location of target object, and give direction information of the target object from a first-view image. It can guide our agent to navigate to the target object. Our experiment results outperforms the result of state of the art method in the artificial environment AI2-Thor. © 2021, Springer Nature Switzerland AG.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Load Balancing Strategy Of "Container Virtual Machine" Cloud Microservice Based On Deadline Limit 14

A Load Balancing Strategy Of "Container Virtual Machine" Clo...

引用

14th International Conference on Measuring Technology and Mechatronics Automation, ICMTMA 2022

作者： Xia, Hong Liu, MengDi Chen, YanPing Jin, XiaoMin Wang, ZhongMin Wang, FengWei School of Computer Science and Technology Xi'an University of Posts and Telecommunications Shaanxi Xi'an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Shaanxi Xi'an710121 China Xi'an Key Laboratory of Big Data and Intelligent Computing Shaanxi Xi'an710121 China ZTE Corporation No.55 Hi-tech Road South Shenzhen518057 China

ISBN: (纸本)9781665499781

Aiming at the problem of workflow scheduling under the "container virtual machine" two-tier structure in cloud microservice workflow application, a "container virtual machine" load balancing strategy based on deadline limit (container virtual machine load) is proposed. Balance strategy), CV LBMs strategy first obtains the optimal economic configuration of the corresponding instance of the micro service according to historical data, and calculated the list of remaining resources in the leased virtual machine;Determined whether the virtual machine is on the virtual machine according to the container image list in the virtual machine. Whether a corresponding container image exists, and create a new container on the virtual machine that already has a container image to reduce the time to extract the container image. The workflow simulation results showed that compared with the existing algorithms, the C-V LBMs strategy had the ability to meet the deadline success rate and reduced the cost. © 2022 IEEE

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

Stable Learning via Triplex Learning

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第10期5卷 5267-5276页

作者： Yang, Shuai Jiang, Tingting Dang, Qianlong Gu, Lichuan Wu, Xindong Anhui Agricultural University School of Information and Artificial Intelligence Hefei230036 China Anhui Provincial Engineering Research Center for Agricultural Information Perception and Intelligent Computing Hefei230036 China Northwest A & F University College of Science Yangling712100 China Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data The Ministry of Education of China Hefei230601 China Hefei University of Technology School of Computer Science and Information Engineering Hefei230601 China

Stable learning aims to learn a model that generalizes well to arbitrary unseen target domain by leveraging a single source domain. Recent advances in stable learning have focused on balancing the distribution of confounders for each feature to eliminate spurious correlations. However, previous studies treat all features equally without considering the difficulties of confounder balancing associated with different features, and regard irrelevant features as confounders, deteriorating generalization performance. To tackle these issues, this article proposes a novel triplex learning (TriL) based stable learning algorithm, which performs sample reweighting, causal feature selection, and representation learning to remove spurious correlations. Specifically, first, TriL adaptively assigns weights to the confounder balancing term of each feature in accordance with the difficulties of confounder balancing, and aligns the confounder distribution of each feature by learning a group of sample weights. Second, TriL integrates the sample weights into a weighted cross-entropy model to compute causal effects of features for excluding irrelevant features from the confounder set. Finally, TriL relearns a set of sample weights and uses them to guide a new supervised dual-autoencoder containing two classifiers to learn feature representations. TriL forces the results of two classifiers to remain consistent for removing spurious correlations by using a cross-classifier consistency regularization. Extensive experiments on synthetic and two real-world datasets show the superiority of TriL compared with seven methods. © 2024 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

MambaLCT: Boosting Tracking via Long-term Context State Space Model 39

MambaLCT: Boosting Tracking via Long-term Context State Spac...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Li, Xiaohai Zhong, Bineng Liang, Qihua Li, Guorong Mo, Zhiyi Song, Shuxiang Key Laboratory of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin541004 China Guangxi Colleges Universities Key Laboratory of Intelligent Software Wuzhou University Wuzhou543002 China Key Laboratory of Big Data Mining and Knowledge Management University of Chinese Academy of Sciences Beijing100101 China

ISBN: (纸本)157735897X

Effectively constructing context information with long-term dependencies from video sequences is crucial for object tracking. However, the context length constructed by existing work is limited, only considering object information from adjacent frames or video clips, leading to insufficient utilization of contextual information. To address this issue, we propose MambaLCT, which constructs and utilizes target variation cues from the first frame to the current frame for robust tracking. First, a novel unidirectional Context Mamba module is designed to scan frame features along the temporal dimension, gathering target change cues throughout the entire sequence. Specifically, target-related information in frame features is compressed into a hidden state space through selective scanning mechanism. The target information across the entire video is continuously aggregated into target variation cues. Next, we inject the target change cues into the attention mechanism, providing temporal information for modeling the relationship between the template and search frames. The advantage of MambaLCT is its ability to continuously extend the length of the context, capturing complete target change cues, which enhances the stability and robustness of the tracker. Extensive experiments show that long-term context information enhances the model’s ability to perceive targets in complex scenarios. MambaLCT achieves new SOTA performance on six benchmarks while maintaining real-time running speeds. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Landslide hazard susceptibility evaluation based on SBAS-InSAR technology and SSA-BP neural network algorithm:A case study of Baihetan Reservoir Area

引用

Journal of Mountain Science 2024年第3期21卷 952-972页

作者： GUO Junqi XI Wenfei YANG Zhiquan SHI Zhengtao HUANG Guangcai YANG Zhengrong YANG Dongqing Faculty of Geography Yunnan Normal UniversityKunming 650500China Key Laboratory of Early Rapid Identification Prevention and Control of Geological Diseases in Traffic Corridor of High Intensity Earthquake Mountainous Area of Yunnan ProvinceKunming 650093China Faculty of Public Safety and Emergency Management Kunming University of Science and TechnologyKunming 650093China Key Laboratory of Geological Disaster Risk Prevention and Control and Emergency Disaster Reduction of Ministry of Emergency Management of the People’s Republic of China Kunming University of Science and TechnologyKunming 650093China Guizhou Geological Survey Institute Guiyang 550081China College of Big Data and Intelligent Engineering Southwest Forestry UniversityKunming 650224China

Landslide hazard susceptibility evaluation takes on critical significance in early warning and disaster prevention and *** order to solve the problems of poor effectiveness of landslide data and complex calculation of weights for multiple evaluation factors in the existing landslide susceptibility evaluation models,in this study,a method of landslide hazard susceptibility evaluation is proposed by combining SBAS-InSAR(Small Baseline Subsets-Interferometric Synthetic Aperture Radar)and SSA-BP(Sparrow Search Algorithm-Back Propagation)neural network *** SBAS-InSAR technology is adopted to identify potential landslide hazards in the study area,update the cataloging data of landslide hazards,and 11 evaluation factors are chosen for constructing the SSA-BP model for training and *** Reservoir area is selected as a case study for *** indicated by the results,the application of SBAS-InSAR technology,combined with both ascending and descending orbit data,effectively addresses the incomplete identification of landslide hazards caused by geometric distortion of single orbit SAR data(e.g.,shadow,overlay,and perspective contraction)in deep canyon areas,thereby enabling the acquisition of up-to-date landslide hazard ***,in comparison to the conventional BP(Back Propagation)algorithm,the accuracy of the model constructed by the SSA-BP algorithm exhibits a significant increase,with mean squared error and mean absolute error reduced by 0.0142 and 0.0607,***,during the process of susceptibility evaluation,the SSA-BP model effectively circumvents the issue of considerable manual interventions in calculating the weight of evaluation *** area under the curve of this model reaches 0.909,surpassing BP(0.835),random forest(0.792),and the information value method(0.699).The risk of landslide occurrence in the Baihetan Reservoir area is positively correlated with slope,surface temperature,and deformation ra

关键词： Baihetan SBAS-InSAR SSA-BP Landslide hazard susceptibility evaluation

来源：评论

学校读者我要写书评

暂无评论

ReconBoost: Boosting Can Achieve Modality Reconcilement 41

ReconBoost: Boosting Can Achieve Modality Reconcilement

引用

41st International Conference on Machine Learning, ICML 2024

作者： Hua, Cong Xu, Qianqian Bao, Shilong Yang, Zhiyong Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores a novel multi-modal alternating learning paradigm pursuing a reconciliation between the exploitation of uni-modal features and the exploration of cross-modal interactions. This is motivated by the fact that current paradigms of multi-modal learning tend to explore multi-modal features simultaneously. The resulting gradient prohibits further exploitation of the features in the weak modality, leading to modality competition, where the dominant modality overpowers the learning process. To address this issue, we study the modality-alternating learning paradigm to achieve reconcilement. Specifically, we propose a new method called ReconBoost to update a fixed modality each time. Herein, the learning objective is dynamically adjusted with a reconcilement regularization against competition with the historical models. By choosing a KL-based reconcilement, we show that the proposed method resembles Friedman's Gradient-Boosting (GB) algorithm, where the updated learner can correct errors made by others and help enhance the overall performance. The major difference with the classic GB is that we only preserve the newest model for each modality to avoid overfitting caused by ensembling strong learners. Furthermore, we propose a memory consolidation scheme and a global rectification scheme to make this strategy more effective. Experiments over six multi-modal benchmarks speak to the efficacy of the method. We release the code at https://***/huacong/ReconBoost. Copyright 2024 by the author(s)

关键词： Contrastive 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：