检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Wu, Weijia Hu, Yaozhong Sun, Hongli Yang, Donghui School of Mathematics and Statistics Central South University Changsha410083 China Department of Mathematical and Statistical Sciences University of Alberta EdmontonABT6G 2G1 Canada School of Mathematics Physics and Big data Chongqing University of Science and Technology Chongqing401331 China

This paper extends the Carleman estimates to high dimensional parabolic equations with highly degenerate symmetric coefficients on a bounded domain of Lipschitz boundary and use these estimates to study the controllability the corresponding equations. Due to the nonsmoothness and degeneracy of boundary, the partial integration by parts in Carleman estimates have no meaning on the degenerate and nonsmooth parts of the boundary. To get around of this difficulty, we construct special weight function, and transform some integral terms in degenerate regions into a non-degenerate ones carefully so that the obtained Carleman estimates can still be used to the controllability problem. Our results includes some well-known works as some special cases as well as some interesting new examples. Copyright © 2023, The Authors. All rights reserved.

关键词： Controllability

来源：评论

学校读者我要写书评

暂无评论

Gradient Amplification: An Efficient Way to Train Deep Neural Networks

引用

big data Mining and Analytics 2020年第3期3卷 196-207页

作者： Sunitha Basodi Chunyan Ji Haiping Zhang Yi Pan Department of Computer Science Georgia State UniversityAtlantaGA 30302USA Center for High Performance Computing Joint Engineering Research Center for Health Big Data Intelligent Analysis TechnologyShenzhen Institutes of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China

Improving performance of deep learning models and reducing their training times are ongoing challenges in deep neural *** are several approaches proposed to address these challenges,one of which is to increase the depth of the neural *** deeper networks not only increase training times,but also suffer from vanishing gradients problem while *** this work,we propose gradient amplification approach for training deep learning models to prevent vanishing gradients and also develop a training strategy to enable or disable gradient amplification method across several epochs with different learning *** perform experiments on VGG-19 and Resnet models(Resnet-18 and Resnet-34),and study the impact of amplification parameters on these models in *** proposed approach improves performance of these deep learning models even at higher learning rates,thereby allowing these models to achieve higher performance with reduced training time.

关键词： deep learning gradient amplification learning rate backpropagation vanishing gradients

来源：评论

学校读者我要写书评

暂无评论

Ipmmg: Information Propagation with Multi-Granularity Morphology-Guided for Nuclear Segmentation and Classification

SSRN

引用

SSRN 2025年

作者： Fan, Dawei Li, Jun Cai, Chengfei Lin, Lihui Chen, Riqing Chen, Yanping Wei, Lifang College of Computer and Information Science Fujian Agriculture and Forestry University Fuzhou350002 China College of Future Technology Fujian Agriculture and Forestry University Fuzhou350002 China Department of Pathology Clinical Oncology School of Fujian Medical University Fujian Cancer Hospital Fuzhou350014 China School of Artificial Intelligence Nanjing University of Information Science and Technology Nanjing210044 China School of Mathematics and Computer Science Fujian Key Laboratory of Big Data Application and Intellectualization for Tea Industry Wuyi University Wuyishan354300 China

Nuclear segmentation and classification play a pivotal role in pathological image analysis. However, it is often hindered by blurred nuclear boundaries and complex structures in digital pathology slides, caused by factors such as staining techniques and imaging methods, presenting a significant challenge for accurate segmentation and classification. To address this issue, we propose a novel and efficient approach for nuclear identification, termed Information Propagation with Multi-Granularity Morphology-Guided Network (IPMMG). IPMMG progressively captures edge morphology information from different network layers while simultaneously incorporating structural morphology features at multiple granularities. By explicitly propagating features related to both the edge and structure, our approach constrains semantic features to focus on the region of interest's contour, thereby alleviating the challenge of blurred morphology. Experiments on public datasets demonstrate that IPMMG achieves state-of-the-art performance in segmentation, as measured by Dice and IoU scores, while also attaining competitive results in classification with DQ, SQ, and PQ metrics. In particular, it excels in handling nuclei with blurred edges and complex structures. © 2025, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

State-Aware Perturbation Optimization for Robust Deep Reinforcement Learning

arXiv

引用

arXiv 2025年

作者： Zhang, Zongyuan Duan, Tianyang Lin, Zheng Huang, Dong Fang, Zihan Sun, Zekai Xiong, Ling Liang, Hongbin Cui, Heming Cui, Yong Department of Computer Science The University of Hong Kong Hong Kong Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong Department of Computer Science City University of Hong Kong Hong Kong School of Computer and Software Engineering Xihua University Chengdu610039 China National United Engineering Laboratory of Integrated and Intelligent Transportation The National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China Department of Computer Science and Technology Ts-inghua University Beijing100084 China

Recently, deep reinforcement learning (DRL) has emerged as a promising approach for robotic control. However, the deployment of DRL in real-world robots is hindered by its sensitivity to environmental perturbations. While existing white-box adversarial attacks rely on local gradient information and apply uniform perturbations across all states to evaluate DRL robustness, they fail to account for temporal dynamics and state-specific vulnerabilities. To combat the above challenge, we first conduct a theoretical analysis of white-box attacks in DRL by establishing the adversarial victim-dynamics Markov decision process (AVD-MDP), to derive the necessary and sufficient conditions for a successful attack. Based on this, we propose a selective state-aware reinforcement adversarial attack method, named STAR, to optimize perturbation stealthiness and state visitation dispersion. STAR first employs a soft mask-based state-targeting mechanism to minimize redundant perturbations, enhancing stealthiness and attack effectiveness. Then, it incorporates an information-theoretic optimization objective to maximize mutual information between perturbations, environmental states, and victim actions, ensuring a dispersed state-visitation distribution that steers the victim agent into vulnerable states for maximum return reduction. Extensive experiments demonstrate that STAR outperforms state-of-the-art benchmarks. Copyright © 2025, The Authors. All rights reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Investigation of Vertically Stacked Horizontal Gate-All-Around SI Nanosheet Ion Sensitive Field Effect Transistor For Detection of C-Reactive Protein

Investigation of Vertically Stacked Horizontal Gate-All-Arou...

引用

China Semiconductor technology International Conference (CSTIC)

作者： Yang Liu Qingzhu Zhang Junjie Li Cinan Wu Lei Cao Yanna Luo Zhaohao Zhang Shuhua Wei Qianhui Wei Jiaxin Yao Jiawei Hu Meiyan Qin Enxu Liu Yanchu Han LianLian Li YingLu Li Tao Yang Na Zhou Jianfeng Gao Junfeng Li Key Laboratory of Microelectronic Devices and Integration Technology Institute of Microelectronics Chinese Academy of Sciences Beijing China College of Big Data and Information Engineering Guizhou University Guiyang China School of Information Science and Technology North China University of Technology Beijing China State Key Laboratory of Advanced Materials for Smart Sensing GRINM Group Co. Ltd. Beijing China

In this work, based on advanced gate-all-around (GAA) technology, the extended sensing gate (ESG) GAA Si nanosheet (SiNS) ion sensitive field effect transistor (ISFET) sensor was fabricated and reported for the first time. Due to the GAA structures and the vertically-stacked SiNS channels, the average sensitivity of the ESG GAA SiNS ISFET sensor can be reached 58.8 mV/pH, which provides good gate control and ultra-sensitive detection capabilities. In addition, the actual minimum detection concentration of C-reactive protein (CRP) by ESG GAA SiNS ISFET sensor in 1$\times$ PBS environment is as low as 100pg/mL, which is much lower than the normal concentration of human body.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Replace2Self: Self-Supervised Denoising based on Voxel Replacing and Image Mixing for Diffusion MRI

引用

IEEE Transactions on Medical Imaging 2025年 PP卷 PP页

作者： Wu, Linhai Wang, Lihui Deng, Zeyu Zhu, Yuemin Wei, Hongjiang Guizhou University Key Laboratory of Advanced Medical Imaging and Intelligent Computing of Guizhou Province Engineering Research Center of Text Computing & Cognitive Intelligence Ministry of Education State Key Laboratory of Public Big Data College of Computer Science and Technology 550025 China Univ Lyon INSA Lyon CNRS Inserm CREATIS UMR 5220 LyonF-69621 France Shanghai Jiao Tong University School of Biomedical Engineering Shanghai200030 China

Low signal to noise ratio (SNR) remains one of the limitations of diffusion weighted (DW) imaging. How to suppress the influence of noise on the subsequent analysis about the tissue microstructure is still challenging. This work proposed a novel self-supervised learning model, Replace2Self, to effectively reduce spatial correlated noise in DW images. Specifically, a voxel replacement strategy based on similar block matching in Q-space was proposed to destroy the correlations of noise in DW image along one diffusion gradient direction. To alleviate the signal gap caused by the voxel replacement, an image mixing strategy based on complementary mask was designed to generate two different noisy DW images. After that, these two noisy DW images were taken as input, and the non-correlated noisy DWimage after voxel replacement was taken as learning target, a denoising network was trained for denoising. To promote the denoising performance, a complementary mask mixing consistency loss and an inverse replacement regularization loss were also proposed. Through the comparisons against several existing DW image denoising methods on extensive simulation data with different noise distributions, noise levels and b-values, as well as the acquisition datasets and the ablation experiments, we verified the effectiveness of the proposed method. Regardless of the noise distribution and noise level, the proposed method achieved the highest PSNR, which was at least 1.9% higher than the suboptimal method when the noise level reaches 10%. Furthermore, our method has superior generalization ability due to the use of the proposed strategies. © 2025 IEEE. All rights reserved.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Randomized Latent Factor Model for High-dimensional and Sparse Matrices from Industrial Applications

引用

IEEE/CAA Journal of Automatica Sinica 2019年第1期6卷 131-141页

作者： Mingsheng Shang Xin Luo Zhigang Liu Jia Chen Ye Yuan MengChu Zhou the Chongqing Engineering Research Center of Big Data Application for Smart Cities and Chongqing Key Laboratory of Big Data and Intelligent ComputingChongqing Institute of Green and Intelligent TechnologyChinese Academy of Sciences the School of Computer Science and Engineering Beihang University the Department of Electrical and Computer Engineering New Jersey Institute of Technology

Latent factor(LF) models are highly effective in extracting useful knowledge from High-Dimensional and Sparse(HiDS) matrices which are commonly seen in various industrial applications. An LF model usually adopts iterative optimizers,which may consume many iterations to achieve a local optima,resulting in considerable time cost. Hence, determining how to accelerate the training process for LF models has become a significant issue. To address this, this work proposes a randomized latent factor(RLF) model. It incorporates the principle of randomized learning techniques from neural networks into the LF analysis of HiDS matrices, thereby greatly alleviating computational burden. It also extends a standard learning process for randomized neural networks in context of LF analysis to make the resulting model represent an HiDS matrix *** results on three HiDS matrices from industrial applications demonstrate that compared with state-of-the-art LF models, RLF is able to achieve significantly higher computational efficiency and comparable prediction accuracy for missing data.I provides an important alternative approach to LF analysis of HiDS matrices, which is especially desired for industrial applications demanding highly efficient models.

关键词： big data high-dimensional and sparse matrix latent factor analysis latent factor model randomized learning

来源：评论

学校读者我要写书评

暂无评论

Linear and Nonlinear Event-Triggered Extended State Observers for Uncertain Stochastic Systems

arXiv

引用

arXiv 2023年

作者： Wu, Ze-Hao Deng, Feiqi Zhou, Hua-Cheng Zhao, Zhi-Liang School of Mathematics and Big Data Foshan University Foshan528000 China Systems Engineering Institute South China University of Technology Guangzhou510640 China School of Mathematics and Statistics Central South University Changsha410075 China School of Mathematics and Information Science Shaanxi Normal University Xi’an710119 China

In this paper, linear and nonlinear event-triggered extended state observers are designed for a class of uncertain stochastic systems driven by bounded and colored noises. Two event-generators with an ensured positive minimum inter-event time for every sample path solution of the stochastic systems, are proposed for the designs of linear and nonlinear event-triggered extended state observers, respectively. The mean square and almost sure convergence of the estimation errors of unmeasured state and stochastic total disturbance including internal uncertainty and external stochastic noises is presented with rigorous theoretical proofs. Compared with the linear event-triggered extended state observer, the theoretical results show that the nonlinear one via homogeneity possesses higher estimation accuracy but is at the price of higher triggering frequency. Some numerical simulations are performed to authenticate the theoretical results. Copyright © 2023, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Research on Power Enterprise data Model Online Management Decision System Based on big data 7

Research on Power Enterprise Data Model Online Management De...

引用

2020 7th International Conference on Computer-Aided Design, Manufacturing, Modeling and Simulation, CDMMS 2020

作者： Cheng, Zhihua Ye, Yong Huang, Wensi Zhang, Yiqi Lan, Liang Big Data Center of State Grid Corporation of China Beijing100052 China State Grid Info-Telecom Great Power Science and Technology Co. Ltd Fuzhou Fujian350003 China State Grid Fujian Electric Power CO.LTD Fuzhou350003 China

At present, with the development of cloud computing and data analysis technology, big data technology based on cloud computing is also making continuous progress. As a cutting-edge technology based on cloud computing processing technology, big data technology is widely used in our daily production and life, bringing great convenience to our work, study and life. Under the background of today's big data era, the new era has brought great impact on all walks of life. If everything wants to keep pace with the development pace of the times, it is necessary to carry out reform, innovation and development. In order to deal with the challenge brought by this impact, this paper proposes a research method of online management decision system of power enterprise data model based on big data background. Through big data technology, the current research status of online management decision system of power enterprise data model is analyzed. Combined with the new requirements of big data era, a set of electric power suitable for the new era is formulated Development plan of enterprise data model online management decision system. Through long-term research and observation, it can be found that the method proposed in this paper is of great significance to the research of power enterprise level data model online management decision-making system based on big data background. © Published under licence by IOP Publishing Ltd.

关键词： big data

来源：评论

学校读者我要写书评

暂无评论

ToFM: Topic-specific Facet Mining by Facet Propagation within Clusters 12

ToFM: Topic-specific Facet Mining by Facet Propagation withi...

引用

12th IEEE International Conference on big Knowledge, ICBK 2021

作者： Li, Hongxuan Wei, Bifan Liu, Jun Guo, Zhaotong Qi, Jingchao Wu, Bei Liu, Yong Shi, Yuanyuan Xi'An Jiaotong University School of Computer Science and Technology Xi'an China Xi'An Jiaotong University National Engineering Lab For Big Data Analytics Xi'an China School of Continuous Education Xi'An Jiaotong University Xi'an China Servyou Software Group Co. Ltd. China

ISBN: (纸本)9781665438582

Mining the facets of topics is an essential task for information retrieval, information extraction and knowledge base construction. For the topics in courses, there are three challenges: different topics have different facet, the labels of facets rarely appear in the topic description text and not all topics have enough textural information to mine facets. In this paper we propose a weakly-supervised algorithm for topic-specific facet mining (ToFM for short) based on our finding that similar topics in a cluster have similar facet sets. For example, topics Binary Search Tree, Suffix Tree and AVL tree in Tree cluster have example, insertion, deletion, traversal and other similar facets. ToFM first splits topics in a domain into several topic clusters based on the topic description text. Then ToFM extracts initial facet sets for all topics from the corresponding Wikipedia article pages. Finally, ToFM performs a normalized facet propagation within each topic cluster to acquire final facet sets of every topic. We evaluate the performance of ToFM on six real-world datasets and experimental results show that ToFM achieves better performance than the existing facet mining algorithms. © 2021 IEEE.

关键词： Information retrieval

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：