检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Qiao, Xiaoyu Li, Weisheng Xiao, Bin Huang, Yuping Yang, Lijian Chongqing Key Laboratory of Image Cognition Chongqing University of Posts and Telecommunications Chongqing China Key Laboratory of Cyberspace Big Data Intelligent Security Chongqing University of Posts and Telecommunications Ministry of Education Chongqing China

ISBN: (纸本)9798350368741

Deep unfolding networks (DUNs) have made significant progress in MRI reconstruction, successfully tackling the problem of prolonged imaging time. However, the ill-conditioned nature of MRI reconstruction often causes slow convergence in iterative optimization, potentially compromising the performance of DUNs. In this study we propose a preconditioned and gates-controlled DUN (PGDUN) to address these challenges. Our approach starts with optimizing the step size of proximal gradient descent (PGD) through a preconditioner. To improve flexibility and adaptability, we relax the constrains on quasi-newton-based optimization procedure. We design ConvLSTM-based modules, where the gate units automatically preserve necessary long- and short-term information, facilitating the learning of optimized variables and their combinations. Furthermore, we design gate units to modulate the features fed to regularizers across different iterations, boosting their robustness against potential accumulated errors. Evaluations using PSNR and SSIM metrics reveal that our approach outperforms existing state-of-the-art methods, achieving superior reconstruction results across various sequences. © 2025 IEEE.

关键词： Compressed Sensing LSTM MRI reconstruction Preconditioner Quasi-Newton

来源：评论

学校读者我要写书评

暂无评论

MMH-FE:AMulti-Precision and Multi-Sourced Heterogeneous Privacy-Preserving Neural Network Training Based on Functional Encryption

引用

Computers, Materials & Continua 2025年第3期82卷 5387-5405页

作者： Hao Li Kuan Shao Xin Wang Mufeng Wang Zhenyong Zhang The State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang550025China Key Laboratory of Computing Power Network and Information Security Ministry of EducationShandong Computer Science CenterQilu University of Technology(Shandong Academy of Sciences)Jinan250014China China Industrial Control Systems Cyber Emergency Response Team Beijing100040China

Due to the development of cloud computing and machine learning,users can upload their data to the cloud for machine learning model ***,dishonest clouds may infer user data,resulting in user data *** schemes have achieved secure outsourced computing,but they suffer from low computational accuracy,difficult-to-handle heterogeneous distribution of data from multiple sources,and high computational cost,which result in extremely poor user experience and expensive cloud computing *** address the above problems,we propose amulti-precision,multi-sourced,andmulti-key outsourcing neural network training ***,we design a multi-precision functional encryption computation based on Euclidean ***,we design the outsourcing model training algorithm based on a multi-precision functional encryption with multi-sourced ***,we conduct experiments on three *** results indicate that our framework achieves an accuracy improvement of 6%to 30%.Additionally,it offers a memory space optimization of 1.0×2^(24) times compared to the previous best approach.

关键词： Functional encryption multi-sourced heterogeneous data privacy preservation neural networks

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Based data-Driven Control Method for Dynamic Systems and Its Application to FLUIDMechatronix Platform 16th

Reinforcement Learning Based Data-Driven Control Method for...

引用

16th International Conference on Modelling, Identification and Control, ICMIC 2024

作者： Zou, Zonghan Gao, Jingjing Yang, Xu Huang, Jian Zhang, Tao Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing100083 China

ISBN: (纸本)9789819617760

With the increasing complexity of industrial process, accurate models of automatic control systems are difficult to be established, which makes model-based control methods become less effective. On this premise, a reinforcement learning (RL) based data-driven control method for dynamic systems is proposed in this paper. For our purposes, a model-free RL controller with an Actor-Critic structure is developed by using neural networks (NN), combining the merits of both value-based and policy-based RL algorithms. Policy of the actor is assessed by the critic, updating parameters of RL controller in real-time for online optimization. The effectiveness of the RL controller is demonstrated by an experimental study on FLUIDMechatronix platform. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Superradiant growth anomaly magnification in evolution of vector bosonic condensates bounded by a Kerr black hole with near-horizon reflection

引用

Science china(Physics,Mechanics & Astronomy) 2025年第4期68卷 62-81页

作者： Nayun Jia Yin-Da Guo Gui-Rong Liang Zhan-Feng Mai Xin Zhang Department of Physics Southern University of Science and TechnologyShenzhen 518055China Key Laboratory of Cosmology and Astrophysics(Liaoning)&College of Sciences Northeastern UniversityShenyang 110819China Institute of Frontier and Interdisciplinary Science Key Laboratory of Particle Physics and Particle Irradiation(Ministry of Education)Shandong UniversityQingdao 266237China School of Materials Science and Physics China University of Mining and TechnologyXuzhou 221116China Kavli Institute for Astronomy and Astrophysics Peking UniversityBeijing 100871China Guangxi Key Laboratory for Relativistic Astrophysics School of Physical Science and TechnologyGuangxi UniversityNanning 530004China Key Laboratory of Data Analytics and Optimization for Smart Industry(Ministry of Education) Northeastern UniversityShenyang 110819China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern UniversityShenyang 110819China

Ultralight vector particles can form evolving condensates around a Kerr black hole(BH)due to superradiant *** study the effect of near-horizon reflection on the evolution of this system:by matching three pieces of asymptotic expansions of the Proca equation in Kerr metric and considering the leading order in the electric mode,we present explicit analytical expressions for the corrected spectrum and the superradiant instability ***,in high-spin BH cases,we identify an anomalous situation where the superradiance rate is temporarily increased by the reflection parameter R,which also occurs in the scalar scenario,but is largely magnified in vector condensates due to a faster growth rate in dominant *** point out that the condition for the growth anomaly in the adiabatic case is that information carried per particle exceeds a certain value δ1/δN>2πκ_(B)√(1+R)/(1-R).We further construct several featured quantities to illustrate it,and formalize the anomalyinduced gravitational wave strain deformation.

关键词： superradiance ultralight boson black hole gravitational wave near-horizon reflection

来源：评论

学校读者我要写书评

暂无评论

Multi-modal Self-perception Enhanced Large Language Model for 3D Region-of-Interest Captioning with Limited data

引用

IEEE Transactions on Multimedia 2025年 27卷 2935-2948页

作者： Shi, Lu Kan, Shichao Jin, Yi Zhang, Linna Cen, Yigang Bejing Jiaotong University and the Beijing Key Laboratory of Advanced Information Science and Network Technology Institute of Information Science Beijing100044 China Central South University School of Computer Science and Engineering Hunan Changsha0410083 China Beijing Jiaotong University Key Laboratory of Big Data and Artificial Intelligence in Transportation Ministry of Education and the School of Computer and lnformation Technology Beijing100044 China Guizhou University School of Mechanical Engineering Guiyang550025 China

3D Region-of-Interest (RoI) Captioning involves translating a model's understanding of specific objects within a complex 3D scene into descriptive captions. Recent advancements in Large Language Models (LLMs) have shown great potential in this area. Existing methods capture the visual information from RoIs as input tokens for LLMs. However, this approach may not provide enough detailed information for LLMs to generate accurate region-specific captions. In this paper, we introduce Self-RoI, a Large Language Model with multi-modal self-perception capabilities for 3D RoI captioning. To ensure LLMs receive more precise and sufficient information, Self-RoI incorporates Implicit Textual Info. Perception to construct a multi-modal vision-language information. This module utilizes a simple mapping network to generate textual information about basic properties of RoI from vision-following response of LLMs. This textual information is then integrated with the RoI's visual representation to form a comprehensive multi-modal instruction for LLMs. Given the limited availability of 3D RoI-captioning data, we propose a two-stage training strategy to optimize Self-RoI efficiently. In the first stage, we align 3D RoI vision and caption representations. In the second stage, we focus on 3D RoI vision-caption interaction, using a disparate contrastive embedding module to improve the reliability of the implicit textual information and employing language modeling loss to ensure accurate caption generation. Our experiments demonstrate that Self-RoI significantly outperforms previous 3D RoI captioning models. Moreover, the Implicit Textual Info. Perception can be integrated into other multi-modal LLMs for performance enhancement. We will make our code available for further research. © 1999-2012 IEEE.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

Multi-Metric Based Client Selection for Backdoor Defense in Federated Learning 1

Multi-Metric Based Client Selection for Backdoor Defense in ...

引用

1st International Conference on Intelligent Manufacturing and Cloud Computing, ICIMCC 2024

作者： Yuan, Changjiang Li, Yidong Chen, Naiyue Zhang, Zikai Key Laboratory of Big Data & Artificial Intelligence in Transportation Beijing Jiaotong University Ministry of Education China School of Computer Science and Technology Beijing Jiaotong University Beijing100044 China

ISBN: (纸本)9781643685779

The distributed nature of federated learning makes it highly susceptible to backdoor attacks, which aim to induce the model to produce incorrect results when specific data is input. Existing defense methods based on distance calculations mostly use one single distance, which can be easily circumvented by backdoor attacks. Therefore, we conducted research on the combination of multiple distances. Based on this, we propose a backdoor defense algorithm based on multi metrics, which evaluates models through distance calculation and normalization to select benign models for aggregation. To verify the effectiveness of our method, we conducted experiments on three datasets, and the results prove that our method can provide good defense without reducing the model's main task accuracy. © 2025 The Authors.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

How to Mitigate Information Loss in knowledge Graphs for GraphRAG: Leveraging Triple Context Restoration and Query-Driven Feedback

arXiv

引用

arXiv 2025年

作者： Huang, Manzong Bu, Chenyang He, Yi Wu, Xindong Key Laboratory of Knowledge Engineering with Big Data [Hefei University of Technology Ministry of Education China School of Data Science William & Mary WilliamsburgVA United States

knowledge Graph (KG)-augmented Large Language Models (LLMs) have recently propelled significant advances in complex reasoning tasks, thanks to their broad domain knowledge and contextual awareness. Unfortunately, current methods often assume KGs to be complete, which is impractical given the inherent limitations of KG construction and the potential loss of contextual cues when converting unstructured text into entity-relation triples. In response, this paper proposes the Triple Context Restoration and Query-driven Feedback (TCR-QF) framework, which reconstructs the textual context underlying each triple to mitigate information loss, while dynamically refining the KG structure by iteratively incorporating query-relevant missing knowledge. Experiments on five benchmark question-answering datasets substantiate the effectiveness of TCR-QF in KG and LLM integration, where it achieves a 29.1% improvement in Exact Match and a 15.5% improvement in F1 over its state-of-the-art GraphRAG competitors. © 2025, CC BY.

关键词： knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Prediction of Rolling Force in Hot Rolling Process Based on Rollformer Model 16th

Prediction of Rolling Force in Hot Rolling Process Based on ...

引用

16th International Conference on Modelling, Identification and Control, ICMIC 2024

作者： Li, Qing Jiang, Pengyuan Yuan, Li School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing100083 China Key Laboratory of Knowledge Automation for Industrial Processes Ministry of Education Beijing100083 China

ISBN: (纸本)9789819617760

In the steel manufacturing industry, the precise forecasting of rolling forces in the hot rolling process is vital for enhancing production efficiency and ensuring product quality. Traditional forecasting methods exhibit limitations when addressing the nonlinearity and variability of industrial data, and current deep learning models are slow to respond to real-time data, with room for improvement in predictive accuracy within dynamic production settings. This paper introduces the Rollformer deep learning model, which adeptly captures intricate nonlinear patterns through the self-attention mechanism's nonlinear transformation capabilities, and boosts sensitivity and adaptability to data variability via adaptive weight distribution. The Rollformer model also pioneers the Roll Self-attention mechanism, leveraging probabilistic sparsity to diminish computational complexity and accelerate the model’s response. Additionally, it employs a generative decoder for swift long-sequence predictions, thereby augmenting the model’s predictive precision. Validated with extensive real-world data from steel mills, the Rollformer model demonstrates superior predictive accuracy and response speed when compared to other Transformer-based deep learning models such as Autoformer and Conformer. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

SlagNet: A Real-Time Slag Segmentation Model Based on Context and Edge Fusion 16th

SlagNet: A Real-Time Slag Segmentation Model Based on Conte...

引用

16th International Conference on Modelling, Identification and Control, ICMIC 2024

作者： Liu, Kecheng Li, Jiangyun Yuan, Li School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing100083 China Key Laboratory of Knowledge Automation for Industrial Processes Ministry of Education Beijing100083 China

ISBN: (纸本)9789819617760

In the process of iron and steel smelting, steel slag is inevitably produced as a byproduct. Accurately identifying steel slag is a prerequisite for controlling the content of steel slag. Conventional vision-based steel slag processing solutions are constrained by real-time performance or robustness against disturbances, rendering them directly applied in industrial sites. To address these issues, SlagNet, a steel slag segmentation network with real-time performance and strong disturbance resistance, is designed in this paper. By designing a lightweight branch to extract rich context information, and combining edge branches to supplement the slag edge information, 77.69 mIOU and 13.25 FPS are achieved in the field collection of slagging data set. The results indicate that SlagNet achieves the optimal balance between real-time performance and accuracy in comparison with other segmentation methods, thereby meeting the requirements of industrial sites. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Slags

来源：评论

学校读者我要写书评

暂无评论

Fine-grained Personalized Hierarchical Federated Learning towards Heterogeneous Internet of Vehicles

引用

IEEE Internet of Things Journal 2025年第11期12卷 16349-16362页

作者： Zhang, Puning Shao, Shuman Wu, Chao Yang, Zhigang Zhang, Ruoying Chongqing University of Posts and Telecommunications School of Communications and Information Engineering Chongqing400065 China Chongqing Key Laboratory of Ubiquitous Sensing and Networking Advanced Network and Intelligent Connection Technology Key Laboratory of Chongqing Education Commission of China Chongqing400065 China Chongqing Innovation Center of Industrial Big-Data Co. Ltd National Engineering Laboratory for Industrial Big-data Application Technology Chongqing400707 China China Merchants Testing Vehicle Technology Research Institute Co. Ltd Chongqing404100 China Chongqing University of Posts and Telecommunications School of Cyber Security and Information Law Chongqing400065 China Chongqing Key Laboratory of Ubiquitous Sensing and Networking Advanced Network and Intelligent Connection Technology Key Laboratory of Chongqing Education Commission of China China China Academy of Information and Communications Beijing100083 China

High mobility and non-independent and identically distributed (non-iid) data in the Internet of Vehicles (IoV) pose challenges for the convergence speed and accuracy of federated learning model training. Traditional federated learning approaches fail to account for the unique characteristics of local vehicle data, limiting the model performances. To address this, we propose a personalized hierarchical federated learning method tailored for heterogeneous IoV. Our approach customizes models for each vehicle, enhancing their performance on local data. We introduce a network-aware client selection method that dynamically chooses vehicle clients based on their spatiotemporal distribution and changing channel conditions. Additionally, our fine-grained personalized learning method leverages frequency domain analysis to extract and retain both fundamental and personalized knowledge from local model parameters. This allows us to build highly accurate personalized models suited to each vehicle's data characteristics. Experimental results show that our method improves model accuracy by up to 10.31% and reduces training time by up to 24.93% compared to the latest personalized federated learning algorithms. © 2025 IEEE.

关键词： Federated 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：