检索结果-内蒙古大学图书馆

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

An intelligent matching method for the equivalent circuit of electrochemical impedance spectroscopy based on Random Forest

引用

材料科学技术（英文版） 2025年第6期209卷 300-310页

作者： Wenbo Chen Bingjun Yan Aidong Xu Xin Mu Xiufang Zhou Maowei Jiang Changgang Wang Rui Li Jie Huang Junhua Dong Key Laboratory of Networked Control Systems Chinese Academy of SciencesShenyang 110169China Shenyang Institute of Automation Chinese Academy of SciencesShenyang 110169China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of SciencesShenyang 110169China University of Chinese Academy of Sciences Beijing 100049China Key Laboratory of Networked Control Systems Chinese Academy of SciencesShenyang 110169China Shenyang Institute of Automation Chinese Academy of SciencesShenyang 110169China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of SciencesShenyang 110169China Shenyang National Laboratory for Materials Science Institute of Metal ResearchChinese Academy of SciencesShenyang 110016China General Research Institute China Oil & Gas Pipeline Network CorporationLangfang 065000China

One of the core works of analyzing Electrochemical Impedance Spectroscopy(EIS)data is to select an appropriate equivalent circuit model to quantify the parameters of the electrochemical reaction ***,this process often relies on human experience and judgment,which will introduce subjectivity and *** this paper,an intelligent approach is proposed for matching EIS data to their equivalent circuits based on the Random Forest *** can automatically select the most suitable equivalent circuit model based on the characteristics and patterns of EIS *** the typical scenario of metal corrosion,an atmospheric corrosion EIS dataset of low-carbon steel is constructed in this paper,which includes five different corrosion *** dataset was used to validate and evaluate the pro-posed method in this *** contributions of this paper can be summarized in three aspects:(1)This paper proposes a method for selecting equivalent circuit models for EIS data based on the Random Forest algorithm.(2)Using authentic EIS data collected from metal atmospheric corrosion,the paper es-tablishes a dataset encompassing five categories of metal corrosion scenarios.(3)The superiority of the proposed method is validated through the utilization of the established authentic EIS *** ex-periment results demonstrate that,in terms of equivalent circuit matching,this method surpasses other machine learning algorithms in both precision and ***,it shows strong applicability in the analysis of EIS data.

关键词： Electrochemical impedance spectroscopy Random forest Corrosion Equivalent circuit model

来源：评论

学校读者我要写书评

暂无评论

Exploring Token-Level Augmentation in Vision Transformer for Semi-Supervised Semantic Segmentation

引用

IEEE Signal Processing Letters 2025年 32卷 1885-1889页

作者： Zhang, Dengke Tang, Quan Liu, Fagui Mei, Haiqing Chen, C. L. Philip South China University of Technology School of Computer Science and Engineering Guangzhou510006 China Pengcheng Laboratory Department of New Network Shenzhen518000 China China Tobacco Guangdong Industrial Corporation Guangzhou510385 China Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems Institute of Automation Beijing100080 China

Semi-supervised semantic segmentation has witnessed remarkable advancements in recent years. However, existing algorithms are based on convolutional neural networks, and directly applying them to Vision Transformers poses certain limitations due to conceptual disparities. To this end, we propose TokenSwap, a data augmentation technique designed explicitly for semi-supervised semantic segmentation with Vision Transformers. TokenSwap aligns well with the global attention mechanism by mixing images at the token level, enhancing the learning capability for contextual information among image patches and the utilization of unlabeled data. We further incorporate image augmentation and feature augmentation to promote the diversity of augmentation. Moreover, to enhance consistency regularization, we propose a dual-branch framework where each branch applies image and feature augmentation to the input image. We conduct extensive experiments across multiple benchmark datasets, including Pascal VOC 2012, Cityscapes, and COCO. Results suggest that the proposed method outperforms state-of-the-art algorithms with notably observed accuracy improvement, especially under limited fine annotations. © 1994-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

An Improved DeeplabV3+ Tile Image Positioning Method

An Improved DeeplabV3+ Tile Image Positioning Method

引用

2024 International Conference Optoelectronic Information and Optical Engineering, OIOE 2024

作者： Li, Xiaoyang Wang, Rui Tong, Xing Niu, Lianqiang Shenyang University of Technology Shenyang China Key Laboratory of Network Control Systems Chinese Academy of Sciences China Shenyang Institute of Automation Chinese Academy of Sciences China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China

ISBN: (数字)9781510688209

ISBN: (纸本)9781510688193

In order to improve the detection accuracy and efficiency of surface defects on ceramic tiles, a detection model based on DeepLabV3+and combined with MobileNetv2 for feature extraction was constructed. Using ECA attention mechanism and multi branch receptive field cascade fusion structure to expand the sampling range of global and local element features for the empty space pyramid pooling module ASPP of the original model. Meanwhile, the model decoder uses depthwise separable convolutions instead of the original standard convolutions. Experimental results have shown that the improved model has an MPA value of 96.12%, a MIou value of 97.29%, an F1 value of 90.03%, and an Accuracy value of 99.89%. Compared with the previous model, the improved model's indicators have increased by 4.07%, 4.44%, 2.04%, and 1.02%, respectively. The segmentation accuracy and detection speed have been significantly improved. The experimental results fully demonstrate that the algorithm proposed in this article can effectively complete the task of detecting surface defects on ceramic tiles. © 2025 SPIE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Stability Analysis of Connected Vehicle Platoons with Markovian Packet Losses

引用

IEEE Internet of Things Journal 2025年

作者： Wu, Yilin Zhao, Xiaoyan Shen, Zhiping Liu, Yonggui Li, Zeming Guangdong University of Education School of Computer Science Guangzhou510310 China Henan Normal University School of Mathematics and Statistics Xinxiang453007 China South China University of Technology Key Laboratory of Autonomous Systems and Network Control Ministry of Education The College of Automatic Science and Engineering Guangzhou510640 China

This article focuses on discussing the effects of inter-vehicular communication on the performance of platoon control. Different from the existing results established under a critical assumption that the fading channels are independent, this paper models the inter-vehicular communication as Markovian packet loss channel which can capture the temporal interdependencies of packet losses. Our aim is to decide whether there exists a distributed controller such that the underlying vehicle platoon can achieve mean square stability (MSS) over Markovian packet loss channels. First, for the scenario with identical Markovian packet losses, we begin by deriving a necessary and sufficient condition for the platoon MSS, which is established by utilizing the stability principles of Markov jump linear systems. Additionally, we propose a numerically verifiable criterion for MSS, which can be validated through the feasibility of linear matrix inequalities (LMIs). Furthermore, based on the modified Riccati inequality (MRI), we provide an analytical sufficient condition that ensures MSS for vehicle platoons. This condition is expressed in terms of the information flow topology (IFT) and the statistical parameters of Markov channels. Second, for the case with nonidentical packet dropouts, we introduce a Markovian loss channel based switching (MLCBS) model. Building upon this model, we further propose a sufficient conditon related to IFT and the transition probability matrix, and a distributed controller that is not only easy to implement but also enables the achievement of MSS for vehicle platoons with nonidentical packet dropouts. Ultimately, numerical experiments are performed to validate the obtained outcomes. © 2014 IEEE.

关键词： Intelligent Transportation systems Resource-Constrained networks Vehicular networks

来源：评论

学校读者我要写书评

暂无评论

Brain-Conditional Multimodal Synthesis: A Survey and Taxonomy

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第5期6卷 1080-1099页

作者： Mai, Weijian Zhang, Jian Fang, Pengfei Zhang, Zhijun South China University of Technology School of Automation Science and Engineering Guangzhou510640 China Southeast University School of Computer Science and Engineering Nanjing210096 China South China University of Technology Key Library of Autonomous Systems and Network Control Ministry of Education The School of Automation Science and Engineering Guangzhou510640 China Institute for Super Robotics Huangpu Guangzhou510555 China Nanchang University Jiangxi Thousand Talents Plan Nanchang330031 China Jishou University College of Computer Science and Engineering Jishou416000 China Guangdong Artificial Intelligence and Digital Economy Laboratory Pazhou Lab Guangzhou510335 China Shaanxi University of Technology Shaanxi Provincial Key Laboratory of Industrial Automation School of Mechanical Engineering Hanzhong723001 China Changsha Normal University School of Information Science and Engineering Changsha410100 China Guangdong University of Petrochemical Technology School of Automation Science and Engineering Institute of Artificial Intelligence and Automation Maoming525000 China

In the era of artificial intelligence generated content (AIGC), conditional multimodal synthesis technologies (e.g., text-to-image) are dynamically reshaping the natural content. Brain signals, serving as potential reflections of how the brain interprets external information, exhibit a distinctive one-to-many correspondence with various external modalities. This correspondence makes brain signals emerge as a promising guiding condition for multimodal synthesis (e.g., image, text, and audio), which is crucial for developing practical brain–computer interface systems and unraveling complex mechanisms underlying human perception. This survey comprehensively examines the emerging field of brain-conditional multimodal synthesis, termed AIGC-brain, to delineate the current landscape and future directions. To begin, related neuroimaging datasets and generative models are introduced as the foundation of AIGC-brain decoding and analysis. Next, we present a comprehensive taxonomy according to AIGC-brain methodologies, followed by task-specific representative work and implementation details to facilitate in-depth comparison and analysis. Quality assessments are then introduced for both qualitative and quantitative evaluation. Finally, this survey explores insights gained, outlining current challenges and prospects of AIGC-brain. As a pioneering survey, this article paves the way for future advances in AIGC-brain research. © 2020 IEEE.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

Exploring Token-Level Augmentation in Vision Transformer for Semi-Supervised Semantic Segmentation

arXiv

引用

arXiv 2025年

作者： Zhang, Dengke Tang, Quan Liu, Fagui Mei, Haiqing Chen, C.L. Philip The School of Computer Science and Engineering South China University of Technology Guangzhou510006 China The Department of New Network Pengcheng Laboratory Shenzhen518000 China The China Tobacco Guangdong Industrial Corporation Guangzhou510385 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100080 China

Semi-supervised semantic segmentation has witnessed remarkable advancements in recent years. However, existing algorithms are based on convolutional neural networks and directly applying them to Vision Transformers poses certain limitations due to conceptual disparities. To this end, we propose TokenMix, a data augmentation technique specifically designed for semi-supervised semantic segmentation with Vision Transformers. TokenMix aligns well with the global attention mechanism by mixing images at the token level, enhancing learning capability for contextual information among image patches. We further incorporate image augmentation and feature augmentation to promote the diversity of augmentation. Moreover, to enhance consistency regularization, we propose a dual-branch framework where each branch applies image and feature augmentation to the input image. We conduct extensive experiments across multiple benchmark datasets, including Pascal VOC 2012, Cityscapes, and COCO. Results suggest that the proposed method outperforms state-of-the-art algorithms with notably observed accuracy improvement, especially under limited fine annotations. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Recurrent Neural network Based Bicriteria Repetitive Motion Collision Avoidance Scheme for Motion Planning of Dual Redundant Manipulators 13

A Recurrent Neural Network Based Bicriteria Repetitive Motio...

引用

13th International Conference on Intelligent control and Information Processing, ICICIP 2025

作者： Chen, Shirui Gao, Huanli Hu, Shaolin Zhang, Zhijun The School of Automation Science and Engineering South China University of Technology Guangzhou510640 China The School of Automation Guangdong University of Petrochemical Technology Maoming Guangzhou525000 China The Guangzhou Key Laboratory of Brain-Computer Interaction and Applications Guangzhou China The Key Library of Autonomous Systems and Network Control Ministry of Education The School of Automation Science and Engineering South China University of Technology Guangzhou510640 China Guangzhou510555 China The Jiangxi Thousand Talents Plan Nanchang University Nanchang330031 China The College of Computer Science and Engineering Jishou University Jishou416000 China Guangzhou510335 China The Shaanxi Provincial Key Laboratory of Industrial Automation School of Mechanical Engineering Shaanxi University of Technology Hanzhong723001 China The School of Information Science and Engineering Changsha Normal University Changsha410100 China The School of Automation Science and Engineering Maoming525000 China The Institute of Artificial Intelligence and Automation Guangdong University of Petrochemical Technology Maoming525000 China

ISBN: (纸本)9798331516147

To achieve low joint-angle drift and avoid mutual collision between dual redundant manipulators (DRMs) when they are doing collaboration works, a recurrent neural network based bicriteria repetitive motion collision avoidance (BRMCA) scheme is proposed for motion planning of DRMs. By designing a combined optimization objective encompassing both repetitive motion criterion and collision avoidance criterion, the BRMCA scheme has larger feasible region and less constraint contradiction issues compared with traditional inequality constraints based method. Furthermore, by incorporating velocity-level kinematic model and physical limits of DRMs into the scheme, a time varying quadratic programming (TVQP) problem is formulated. The linear variational inequality-based primal–dual neural network (LVI-PDNN) is used to solve the proposed scheme due to the high accuracy and low computation complexity. Finally, through comparison simulations of tracking Circle-shape and C-shape trajectories between BRMCA scheme and minimum velocity norm (MVN) scheme, it exhibits that the proposed BRMCA scheme can achieve low joint-angle drift, collision avoidance and high tracking accuracy when DRMs are doing cooperative tasks. © 2025 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Mobile Robot Navigation Using ORB-SLAM3: A Multi-Modal Autonomous System

Mobile Robot Navigation Using ORB-SLAM3: A Multi-Modal Auton...

引用

Electrical Automation and Artificial Intelligence (ICEAAI), International Conference on

作者： Ariano Da Conceicao Lianfang Tian Qiliang Du Ling Yuan School of Automation Science and Engineering South China University of Technology Guangzhou China Research Institute of Modern Industrial Innovation South China University of Technology Guangzhou China Guangdong Engineering Research Center of Cloud-Edge-End Collaboration Technology for Smart City Guangzhou China Key Laboratory of Autonomous Systems and Network Control of Ministry of Education Guangzhou China Key Laboratory of Large-Model Embodied-Intelligent Humanoid Robot (2024KSYS004) Guangzhou China Sino-Singapore International Joint Research Institute Guangzhou China

ISBN: (数字)9798331506797

ISBN: (纸本)9798331506803

Indoor mobile robots require reliable solutions for mapping, localization, and navigation tasks. This paper presents a mobile robot system that implements the ability to realize mapping using visual SLAM with ORB-SLAM3 and LiDAR-based mapping with Gmapping for indoor perception and navigation through a modular ROS architecture. The framework also implements autonomous navigation and an autonomous Rapidly-exploring Random Trees (RRT) exploration module with adaptive reset mechanisms. The system operates on a ROS-based platform equipped with an Intel RealSense D435i RGB-D camera and LDS-02 LiDAR scanner. Experimental validation in simulated indoor environments demonstrates the system's capabilities and the presented architecture achieves computational efficiency through selective utilization of mapping modules while maintaining mapping accuracy through complementary sensor modalities.

关键词： Visualization Simultaneous localization and mapping Accuracy Laser radar Navigation Service robots Heuristic algorithms Computer architecture Mobile robots Autonomous robots

来源：评论

学校读者我要写书评

暂无评论

Node coordination mechanism based on distributed estimation and control in wireless sensor and actuator networks

引用

控制理论与应用（英文版） 2013年第4期11卷 570-578页

作者： Lei MO Bugong XU Key Laboratory of Autonomous Systems and Network Control Ministry of EducationCollege of Automation Science and EngineeringSouth China University of Technology

Wireless sensor and actuator networks （WSANs） have a wide range of applications. To perform effective sensing and acting tasks, multiple coordination mechanisms among the nodes are required. As attempt in this direction, this paper describes collaborative estimation and control algorithms design for WSANs. First, a sensor-actuator coordination model is proposed based on distributed Kalman filter in federated configuration. This method provides the capability of fault tolerance and multi-source information fusion. On this basis, an actuator-actuator coordination model based on even-driven task allocation is introduced. Actuators utilize fused sensory information to adjust their action that incur the minimum energy cost to the system subject to the constraints that user＇s preferences regarding the states of the system are approximately satisfied. Finally, according to system requirements, a distributed algorithm is proposed to solve the task allocation problem. Simulations demonstrate the effectiveness of our proposed methods.

关键词： Wireless sensor and actuator networks Federated Kalman filter Task allocation Distributed control

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：