检索结果-内蒙古大学图书馆

Decentralized Unlearning for Trustworthy AI-Generated Content (AIGC) Services

IEEE Network 2025年第3期39卷 285-292页

作者： Lin, Yijing Du, Hongyang Gao, Zhipeng Yao, Jing Jiang, Bingting Niyato, Dusit Li, Ruidong Zhang, Ping Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing100876 China The University of Hong Kong Department of Electrical and Electronic Engineering Pokfulam Hong Kong Central South University School of Computer Science and Engineering Changsha410083 China Hunan University College of Computer Science and Electronic Engineering Changsha410082 China Nanyang Technological University College of Computing and Data Science Jurong West 639798 Singapore Kanazawa University Institute of Science and Engineering Kanazawa920-1192 Japan

The widespread adoption of AI-Generated Content (AIGC) has captured remarkable interests from academia and industry. However, this advancement brings forth challenges in data ownership, as emphasized by the General data Protection Regulation’s right to be forgotten. The right to be forgotten allows participants to erase their data contributions from well-trained AIGC models. Training AIGC models demands an extensive amount of data and computations, often surpassing the capabilities of individual participants. As a solution, Federated Learning (FL) is employed to collaboratively train an AIGC model without sharing raw data directly. To protect the right to be forgotten in FL, "federated unlearning" has been introduced to eradicate the data contributions of unlearning participants from fully trained AIGC models, achieved by deleting historical model updates. However, given that historical updates are distributed among various participants, they may still hold contributions from the unlearning participants. This presents a challenge to the trustworthiness of federated unlearning. In this paper, we first provide an overview of both centralized and federated learning and unlearning methods. We survey relevant works and classify four main categories for federated unlearning. Subsequently, we introduce a comprehensive decentralized unlearning architecture designed for trustworthy AIGC services. To address the challenge of participants retaining historical contributions from unlearning participants, we integrate a coded computing-based interaction mechanism, ensuring both scalability and security. We further present a case study using NanoGPT to demonstrate the effectiveness of the proposed framework for decentralized unlearning. We conclude by identifying potential future research directions. © 1986-2012 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Simulation study on stratification and homogeneous combustion of an H2O2-ethanol/gasoline combined injection engine 5

Simulation study on stratification and homogeneous combustio...

引用

5th International Conference on Mechanical engineering and Materials, ICMEM 2024

作者： Sun, Ping Zhang, Jufang Yu, Xiumin Li, Decheng College of Automotive Engineering Jilin University Changchun130022 China State Key Laboratory of Automotive Simulation and Control Jilin University Changchun130022 China State Key Laboratory of Automotive Simulation and Control Jilin University Renmin Street 5988 Changchun130022 China

ISBN: (数字)9781510688971

ISBN: (纸本)9781510688964

Due to the imperfect fuel characteristics, the specific fuel consumption of ethanol fuel was larger than that of gasoline, which limited the application of ethanol fuel in the engine field. H2O2 is a strong activity additive to regulate fuel properties. In this paper, the Converge simulation platform was used to study the effects of H2O2 additive on temperature field distribution and micro-active radicals of an SI combined injection engine fueled by ethanol/gasoline under the stratification and homogeneous combustion. The research results showed that the H2O2 additive could effectively promote flame core formation and development and have a more significant effect on the stratification combustion. Considering the whole power stroke, the combustion of the homogeneous mixture was more complete, the active groups were more, the heat loss was less, and the output power of the engine was greater. In general, 20% H2O2 additive plus DIT = 300°CA BTDC could contribute to the power and ultra-low emissions of the engine. © 2025 SPIE.

关键词： Flame research

来源：评论

学校读者我要写书评

暂无评论

Detection and interpretation of the time-varying seasonal signals in china with multi-geodetic measurements

引用

Geodesy and Geodynamics 2025年第1期16卷 42-54页

作者： Liansheng Deng Yugang Xiao Qusen Chen Wei Peng Zhao Li Hua Chen Zhiwen Wu School of Electrical and Electronic Information Engineering Hubei Polytechnic UniversityHuangshi 435003China Hubei Luojia Laboratory GNSS Research CenterWuhan UniversityWuhan 430079China Changjiang Spatial Information Technology Engineering Co. Ltd.Wuhan 430010China Key Laboratory of Spatial Data Mining&Information Sharing of the Ministry of Education Fuzhou UniversityFuzhou 350108China School of Geodesy and Geomatics Wuhan UniversityWuhan 430079China The First Surveying and Mapping Institute of Hunan Province Changsha 410114China

The time-varying periodic variations in Global Navigation Satellite System(GNSS)stations affect the reliable time series analysis and appropriate geophysical *** this study,we apply the singular spectrum analysis(SSA)method to characterize and interpret the periodic patterns of GNSS deformations in china using multiple geodetic *** include 23-year observations from the Crustal Movement Observation Network of china(CMONOC),displacements inferred from the Gravity Recovery and Climate Experiment(GRACE),and loadings derived from Geophysical models(GM).The results reveal that all CMONOC time series exhibit seasonal signals characterized by amplitude and phase modulations,and the SSA method outperforms the traditional least squares fitting(LSF)method in extracting and interpreting the time-varying seasonal signals from the original time *** decrease in the root mean square(RMS)correlates well with the annual cycle variance estimated by the SSA method,and the average reduction in noise amplitudes is nearly twice as much for SSA filtered results compared with those from the LSF *** SSA analysis,the time-varying seasonal signals for all the selected stations can be identified in the reconstructed components corresponding to the first ten ***,both RMS reduction and correlation analysis imply the advantages of GRACE solutions in explaining the GNSS periodic variations,and the geophysical effects can account for 71%of the GNSS annual amplitudes,and the average RMS reduction is 15%.The SSA method has proved to be useful for investigating the GNSS timevarying seasonal *** could be applicable as an auxiliary tool in the improvement of nonlinear variations investigations.

关键词： GNSS coordinate time series Singularspectrumanalysis Time-varying seasonal signals Loading effects GRACE

来源：评论

学校读者我要写书评

暂无评论

A Novel Spatiotemporal Correlation Anomaly Detection Method Based on Time-Frequency-Domain Feature Fusion and a Dynamic Graph Neural Network in Wireless Sensor Network

引用

IEEE Sensors Journal 2025年第9期25卷 15548-15563页

作者： Ye, Miao Jiang, Zhibang Xue, Xingsi Li, Xingwang Wen, Peng Wang, Yong School of Information and Communication Guilin University of Electronic Technology Guilin541004 China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fujian Fuzhou350118 China School of Physics and Electronic Information Engineering Henan Polytechnic University Jiaozuo454099 China

Attention-based transformers have played an important role in wireless sensor network (WSN) timing anomaly detection due to their ability to capture long-term dependencies. However, there are several issues that must be addressed, such as the fact that their ability to capture long-term dependencies is not completely reliable, their computational complexity levels are high, and the spatiotemporal features of WSN timing data are not sufficiently extracted for detecting the correlation anomalies of multinode WSN timing data. To address these limitations, this article proposes a WSN anomaly detection method that integrates frequency-domain features with dynamic graph neural networks (GNNs) under a designed self-encoder reconstruction framework. First, the discrete wavelet transform (DWT) effectively decomposes trend and seasonal components of time series to solve the poor long-term reliability of transformers. Second, a frequency-domain attention mechanism (FDAM) is designed to make full use of the difference between the amplitude distributions of normal data and anomalous data in this domain. Finally, a multimodal fusion-based dynamic graph convolutional network (MFDGCN) is designed by combining an attention mechanism and a graph convolutional network (GCN) to adaptively extract spatial correlation features. A series of experiments conducted on public datasets and their results demonstrate that the anomaly detection method designed in this article exhibits superior precision and recall than the existing methods do, with an F1 score of 93.5%, representing an improvement of 2.9% over that of the existing models. © 2025 IEEE. All rights reserved.

关键词： Normal distribution

来源：评论

学校读者我要写书评

暂无评论

PyionNet: Pyramid Progressive Cross-Fusion Network for Joint Classification of Hyperspectral and LiDAR data

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年 18卷 12042-12058页

作者： Pan, Haizhu Zhang, Quanxiu Ge, Haimiao Liu, Moqi Shi, Cuiping Qiqihar University College of Computer and Control Engineering Qiqihar161000 China Qiqihar University Heilongjiang Key Laboratory of Big Data Network Security Detection and Analysis Qiqihar161000 China Xi'an Jiaotong University School of Information and Communications Engineering Shanxi Xi'an710049 China Huzhou University College of Information Engineering Huzhou313000 China

Joint hyperspectral (HS) and Light Detection and Ranging (LiDAR) data for land cover classification have received widespread attention. Nevertheless, existing methods often struggle with multi-scale feature extraction and multi-source feature fusion. To address these issues, this paper proposes a pyramid progressive cross-fusion network, named PyionNet, for joint classification of HS and LiDAR data. Technically, the proposed PyionNet incorporates a pyramid multi-scale extraction (PME) module cascaded with a progressive cross-fusion (PCF) module, which are designed to extract multi-scale features and fuse multi-source features, respectively. Specifically, the PME module employs pyramid spectral and spatial convolutional blocks to extract and aggregate features from HS and LiDAR data, respectively, then uses an expansion-compression strategy to eliminate redundant information, and thus achieve a compact multi-scale feature representation. Moreover, the PCF module utilizes the transformer architecture and introduces two innovative feature fusion blocks, i.e., the discrepancy feature fusion (DFF) block and the common feature fusion (CFF) block, to progressively integrate multi-source and multi-scale features extracted by the PME module. The DFF block is designed to integrate discrepancy features between HS and LiDAR data to enhance complementary information. Subsequently, the CFF block focuses on fusing common features to progressively enrich the fused representation of the DFF block and further enhance the representation power. Experiments on three real-world datasets demonstrate that the proposed PyionNet outperforms state-of-the-art methods in both qualitative and quantitative results. © 2008-2012 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

SSMamba: Superpixel Segmentation With Mamba

引用

IEEE Signal Processing Letters 2025年 32卷 1715-1719页

作者： Jia, Xiaohong Li, Yonghui Jiao, Jianjun Zhao, Yao Xia, Zhiwei Lanzhou Jiaotong University School of Electronic and Information Engineering Lanzhou730070 China Beijing Jiaotong University Key Laboratory of Big Data and Artiffcial Intelligence in Transportation Ministry of Education Beijing100044 China Beijing Jiaotong University Institute of Information Science Beijing100044 China

Deep convolutional networks have achieved remarkable success in superpixel segmentation. However, they only focus on local features ignoring global attributes. The visual Mamba demonstrates an exceptional capability to capture long-range dependencies and offers a lower computational cost compared to the Transformer. Building on this inspiration, we propose a novel superpixel segmentation with Mamba, termed SSMamba. In SSMamba, Mamba is integrated into a global-local architecture, enabling efficient interaction between global attributes and local features to produce high-quality superpixels. The designed activation function further enhances the effectiveness of SSMamba. Extensive experiments on four public datasets demonstrate that SSMamba outperforms existing state-of-the-art methods, achieving competitive average values of ASA = 0.9541, BR = 0.8768, BP = 0.2124, UE = 0.0910, and CO = 0.3698. © 1994-2012 IEEE.

关键词： Convolutional neural networks

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

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

Semantic Scene Completion via Semantic-Aware Guidance and Interactive Refinement Transformer

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年第5期35卷 4212-4225页

作者： Xiao, Haihong Kang, Wenxiong Liu, Hao Li, Yuqiong He, Ying South China University of Technology School of Automation Science and Engineering Guangzhou510641 China South China University of Technology School of Automation Science and Engineering School of Future Technology Guangzhou510641 China Pazhou Laboratory Guangzhou510335 China Nanyang Technological University College of Computing and Data Science Jurong West 639798 Singapore Institute of Mechanics Chinese Academy of Sciences Key Laboratory for Mechanics in Fluid Solid Coupling Systems Beijing100190 China

Predicting per-voxel occupancy status and corresponding semantic labels in 3D scenes is pivotal to 3D intelligent perception in autonomous driving. In this paper, we propose a novel semantic scene completion framework that can generate complete 3D volumetric semantics from a single image at a low cost. To the best of our knowledge, this is the first endeavor specifically aimed at mitigating the negative impacts of incorrect voxel query proposals caused by erroneous depth estimates and enhancing interactions for positive ones in camera-based semantic scene completion tasks. Specifically, we present a straightforward yet effective Semantic-aware Guided (SAG) module, which seamlessly integrates with task-related semantic priors to facilitate effective interactions between image features and voxel query proposals in a plug-and-play manner. Furthermore, we introduce a set of learnable object queries to better perceive objects within the scene. Building on this, we propose an Interactive Refinement Transformer (IRT) block, which iteratively updates voxel query proposals to enhance the perception of semantics and objects within the scene by leveraging the interaction between object queries and voxel queries through query-to-query cross-attention. Extensive experiments demonstrate that our method outperforms existing state-of-the-art approaches, achieving overall improvements of 0.30 and 2.74 in mIoU metric on the SemanticKITTI and SSCBench-KITTI-360 validation datasets, respectively, while also showing superior performance in the aspect of small object generation. © 1991-2012 IEEE.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

Segregation behaviors in{101^(-)1}compressive twin boundaries of Mg-RE alloy under deformation at room temperature

引用

Journal of Magnesium and Alloys 2025年第1期13卷 330-337页

作者： Yujie Cui Lili Guo Yunwei Gui Kenta Aoyagi Haotian Tong Qinqin Wei Fangzhou Liu Yuichiro Hayasaka Akihiko Chiba Beijing Advanced Innovation Center for Materials Genome Engineering University of Science and Technology BeijingBeijing 100083China Key Laboratory for Advanced Materials Processing(MOE) University of Science and Technology BeijingBeijing 100083China Beijing Laboratory of Metallic Materials and Processing for Modern Transportation Institute for Advanced Materials and TechnologyUniversity of Science and Technology BeijingBeijing 100083China School of Materials Science and Engineering University of Science and Technology BeijingBeijing 100083China Institute for Materials Research Tohoku University2-1-1 KatahiraAoba-kuSendaiMiyagi 980-8577Japan Department of Materials Science and Engineering Jilin University5988 Renmin StreetChangchunJilin 130025China School of Materials Science and Engineering Wuhan University of TechnologyWuhan 430070China The Electron Microscopy Center Tohoku UniversitySendai 980-8577Japan

Solute atoms and precipitates significantly influence the mechanical properties of Mg *** studies have mainly focused on the segregation behaviors of Mg alloys after *** this study,we investigated the segregation behaviors of an Mg-RE alloy under *** found that the enrichment of solute atoms occurred in{101^(-)1}compressive twin boundaries under compression at 298 K without any annealing in an Mg-RE alloy by scanning transmission electron microscopy and energy-dispersive X-ray *** segregated solutes and precipitates impeded the twin growth,partially contributing to the formation of small-sized{101^(-)1}compressive *** research indicates the twin boundaries can be strengthened by segregated solutes and precipitates formed under deformation at room temperature.

关键词： Magnesium alloys Compression test Scanning/transmission electron microscopy(STEM) Segregation Twin boundaries

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：