检索结果-内蒙古大学图书馆

TSGFormer: temporal-aware network and spatial encoding GCN for three-dimensional human pose estimation

Multimedia Systems 2025年第3期31卷 1-19页

作者： Xiao, Xinwang Zhao, Huihuang Li, Yuhang Tang, Peng Deng, Yue College of Computer Science and Technology Hengyang Normal University Hengyang421008 China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang Normal University Hengyang421008 China

Transformer-based approaches have significantly driven recent progress in three-dimensional human pose estimation. However, existing transformer-based approaches are still deficient in capturing localized features, and they lack task-specific a priori information by obtaining queries, keys, and values through simple linear mappings. Existing methods lack effective human constraints for model training. We introduce the Spatial Encoding Graph Convolutional Network Transformer (SEGCNFormer), designed to enhance model capacity in capturing local features. In addition, we propose a Temporal-Aware Network, which generates queries, keys, and values possessing a priori knowledge of human motion, enabling the model to better understand the structural information of human poses. Finally, we leverage the knowledge of human anatomy and motion to design the Human Structural Science Loss, which performs a rationality assessment of human actions and imposes physical constraints on the generated poses. Our method outperforms existing methods on the Human3.6M dataset in both 27 and 81 sampling frames, and our predicted poses are closer to the actual poses with less error. For the existing three issues, we proposed effective methods and conducted targeted experiments, which confirmed the effectiveness of our strategies. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

An Efficient Anti-Quantum Blind Signature with Forward Security for Blockchain-Enabled Internet of Medical Things

引用

computers, Materials & Continua 2025年第2期82卷 2293-2309页

作者： Gang Xu Xinyu Fan Xiu-Bo Chen Xin Liu Zongpeng Li Yanhui Mao Kejia Zhang School of Information Science and Technology North China University of TechnologyBeijing100144China State Key Laboratory of Networking and Switching Technology Beijing University of Posts and TelecommunicationsBeijing100876China School of Mathematical Science Heilongjiang UniversityHarbin150080China School of Digtial and Intelligence Industry Inner Mongolia University of Science and TechnologyBaotou014010China Institute for Network Sciences and Cyberspace Tsinghua UniversityBeijing100084China Yunnan Key Laboratory of Blockchain Application Technology Kunming650233China Yunnan Innovation Institute of Beihang University Kunming650233China

Blockchain-enabled Internet of Medical Things (BIoMT) has attracted significant attention from academia and healthcare organizations. However, the large amount of medical data involved in BIoMT has also raised concerns about data security and personal privacy protection. To alleviate these concerns, blind signature technology has emerged as an effective method to solve blindness and unforgeability. Unfortunately, most existing blind signature schemes suffer from the security risk of key leakage. In addition, traditional blind signature schemes are also vulnerable to quantum computing attacks. Therefore, it remains a crucial and ongoing challenge to explore the construction of key-secure, quantum-resistant blind signatures. In this paper, we introduce lattice-based forward-secure blind signature (LFSBS), a lattice-based forward-secure blind signature scheme for medical privacy preservation in BIoMT. LFSBS achieves forward security by constructing a key evolution mechanism using a binary tree structure. This mechanism ensures that even if future encryption keys are leaked, past data can still remain secure. Meanwhile, LFSBS realizes post-quantum security based on the hardness assumption of small integer solution (SIS), making it resistant to potential quantum computing attacks. In addition, we formally define and prove the security of LFSBS in a random oracle model, including blindness and forward-secure unforgeability. Comprehensive performance evaluation shows that LFSBS performs well in terms of computational overhead, with a reduction of 22%–73% compared to previous schemes.

关键词： Internet of Things blockchain forward-secure blind signature

来源：评论

学校读者我要写书评

暂无评论

APWF: A Parallel Website Fingerprinting Attack with Attention Mechanism

引用

computers, Materials & Continua 2025年第2期82卷 2027-2041页

作者： Dawei Xu Min Wang Yue Lv Moxuan Fu Yi Wu Jian Zhao College of Computer Science and Technology Changchun UniversityChangchun130022China School of Cyberspace Science and Technology Beijing Institute of TechnologyBeijing100081China Key Laboratory of Intelligent Rehabilitation and Barrier-Free for the Disabled Changchun UniversityChangchun130022China China Academy of Information and Communications Technology Beijing100083China Key Laboratory of Mobile Application Innovation and Governance Technology Ministry of Industry and Information TechnologyBeijing100846China

Website fingerprinting (WF) attacks can reveal information about the websites users browse by de-anonymizing encrypted traffic. Traditional website fingerprinting attack models, focusing solely on a single spatial feature, are inefficient regarding training time. When confronted with the concept drift problem, they suffer from a sharp drop in attack accuracy within a short period due to their reliance on extensive, outdated training data. To address the above problems, this paper proposes a parallel website fingerprinting attack (APWF) that incorporates an attention mechanism, which consists of an attack model and a fine-tuning method. Among them, the APWF model innovatively adopts a parallel structure, fusing temporal features related to both the front and back of the fingerprint sequence, along with spatial features captured through channel attention enhancement, to enhance the accuracy of the attack. Meanwhile, the APWF method introduces isomorphic migration learning and adjusts the model by freezing the optimal model weights and fine-tuning the parameters so that only a small number of the target, samples are needed to adapt to web page changes. A series of experiments show that the attack model can achieve 83% accuracy with the help of only 10 samples per category, which is a 30% improvement over the traditional attack model. Compared to comparative modeling, APWF improves accuracy while reducing time costs. After further fine-tuning the freezing model, the method in this paper can maintain the accuracy at 92.4% in the scenario of 56 days between the training data and the target data, which is only 4% less loss compared to the instant attack, significantly improving the robustness and accuracy of the model in coping with conceptual drift.

关键词： Website fingerprinting attack transfer learning concept drift

来源：评论

学校读者我要写书评

暂无评论

Kinematic Parameter Identification of Industrial Robots Based on an Improved Zebra Algorithm 16th

Kinematic Parameter Identification of Industrial Robots Base...

引用

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

作者： Zhou, Houchen Gao, Guanbin Wang, Xi Faculty of Mechanical and Electrical Engineering Kunming University of Science and Technology Kunming650500 China Yunnan Key Laboratory of Intelligent Control and Application Kunming650500 China

ISBN: (纸本)9789819617760

Kinematic calibration is one of the main methods to improve the absolute positioning accuracy of industrial robots. Parameter identification is the primary step in determining the calibration effect. However, due to the large number of kinematic parameters of industrial robots and the complex coupling between parameters, the existing parameter identification methods easily fall into local optimal solutions, and it is difficult to obtain accurate kinematic parameters. Therefore, this paper proposes a Particle Swarm Somersault Foraging Zebra Optimization Algorithm (PSSFZOA) for kinematic parameter identification of industrial robots. The proposed PSSFZOA introduces the foraging strategy into the Zebra Optimization Algorithm (ZOA) and linearizes the kinematic error model so that it does not fall into the local optimum in the later stage of optimization, and improves the population diversity in the early stage. In the first stage of the algorithm, the particle swarm strategy is used to provide local optimal particles, which ensures that the algorithm achieves a balance between global search and local search. It has both the ability of deep search and the diversity of breadth search better to find the best in the complex search space. Simulations are carried out to verify the effectiveness of the method. The results show that compared with the existing Grey Wolf Optimization (GWO) and ZOA, the PSSFZOA can avoid falling into local optimum prematurely, accelerate the convergence speed of the algorithm, and improve the absolute positioning accuracy of the industrial robot after parameter identification. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Industrial robots

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Operation and Maintenance Management System for Teaching Building Based on IoT+WebGIS 3D Visualization 24

Design and Implementation of Operation and Maintenance Manag...

引用

8th International Conference on Electronic Information technology and computer Engineering, EITCE 2024

作者： Zhao, Yongheng Seng, Bingfeng Liu, Xiaojing Wang, Shuhong School of Computer Technology and Application Qinghai University Qinghai Xining China Qinghai Provincial Key Laboratory of Media Integration Technology and Communication Qinghai Xining China

ISBN: (纸本)9798400710094

Building an operation and maintenance system for teaching buildings that integrates"three-dimensional visualization" and"digital informatization" is essential for realizing a smart campus. To address the limitations of current systems in real-time monitoring and visualization, this study integrates Internet of Things (IoT) technology with WebGIS three-dimensional visualization techniques to develop an operation and maintenance management system, taking the teaching building of the School of computer Science at Qinghai University as a case study. The system achieves real-time data collection and dynamic monitoring through IoT devices, and integrates multiple functions, including live three-dimensional model display, indoor and outdoor environmental monitoring, fire alarm and early warning, classroom and equipment management, security monitoring, and energy consumption analysis. This system not only facilitates the transformation of traditional teaching buildings into smart and information-based infrastructure, but also provides operational staff with efficient and intelligent management tools. © 2024 Copyright held by the owner/author(s).

关键词： Fire alarm systems

来源：评论

学校读者我要写书评

暂无评论

Adaptive Parameter Estimation with Directional Forgetting for Nonlinear Systems 16th

Adaptive Parameter Estimation with Directional Forgetting f...

引用

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

作者： Wen, Guoli Xing, Yashan Na, Jing Gao, Guanbin Faculty of Mechanical and Electrical Engineering Kunming University of Science and Technology Kunming650500 China Yunnan Key Laboratory of Intelligent Control and Application Kunming University of Science and Technology Kunming650500 China

ISBN: (纸本)9789819617760

This paper proposes a novel adaptive parameter estimation (APE) with directional forgetting (DF) based on the parameter estimation error for nonlinear systems. Most of APE methods are designed to forget the information of the regressor matrix in all direction in order to update the system information. However, some directions of the regressor matrix for systems are insufficient such that forgetting in all directions may trigger windup phenomenon. To prevent this phenomenon, the proposed method in this paper is to divide the regressor matrix into a forgotten part and a retained part via oblique projection. Then, the constant forgetting factor is applied to the forgotten part such that forgetting the regressor matrix is along the direction that the new information comes. Furthermore, the adaptive law is designed based on the parameter estimation error and the exponential convergence of the proposed method can be guaranteed under the persistent excitation (PE) condition. Finally, comparative simulation related to the proposed method and the classic APE method driven by the parameter estimation error is provided. Simulation results show that the proposed APE with DF algorithm has a better estimation performance than the classic APE method. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Enhancing performance of fullerene-based organic electrochemical transistors via side-chain engineering

引用

Nano Research 2025年第2期18卷 905-912页

作者： Wenxin Fang Zijie Li Chengdong Wang Xiaowei Zhao Junyu Li Gang Ye Fengwei Huo Li Qiu Yanxi Zhang Wei Huang Institute of Flexible Electronics(IFE Future Technologies)Xiamen UniversityXiamen 361005China Yunnan Key Laboratory of Electromagnetic Materials and Devices National Center for International Research on Photoelectric and Energy MaterialsSchool of Materials and EnergyYunnan UniversityKunming 650091China Sinopec Shanghai Research Institute of Petrochemical Technology Shanghai 201028China Key Laboratory for the Green Preparation and Application of Functional Materials Hubei Key Laboratory of Polymer MaterialsSchool of Materials Science and EngineeringHubei UniversityWuhan 430062China Key Laboratory of Flexible Electronics(KLOFE)&Institute of Advanced Materials(IAM) Jiangsu National Synergetic Innovation Center for Advanced Materials(SICAM)Nanjing Tech University(NanjingTech)Nanjing 211800China Frontiers Science Center for Flexible Electronics MIIT Key Laboratory of Flexible Electronics(KLoFE)Northwestern Polytechnical UniversityXi'an 710072China

The performance of organic electrochemical transistors(OECTs)relies on the interaction between organic semiconductors and ***,hydrophilic ethylene glycol(EG)side chains are incorporated into organic semiconductors to improve the channel’s capacity to absorb ***,the EG substituted organic semiconductors tend to swell when immersed in aqueous electrolytes and exhibit microstructural changes induced by dopant *** our research,we introduce an alkyl spacer to create distance between the fullerene and EG *** approach is designed to reduce the negative effects of swelling and balance the ion and electron *** conducted an analysis of OECTs using four fullerene derivatives:no alkyl spacer,butyl,hexyl,and octyl *** OECTs based on fullerene derivatives with butyl and hexyl spacers exhibit enhanced transconductance(g_(m)=11.8 and 19.4 mS)compared to the ones without alkyl *** has also been observed that the butyl and hexyl spacers lead to a more than tenfold increase in volumetric *** increasing the alkyl spacer(octyl group)leads to no transistor *** study uncovers the relationship between alkyl spacers and the performance of OECTs based on fullerene *** will serve as a guideline for designing n-type small molecules for ***,we showcased the potential of utilizing OECTs based on these fullerene derivatives in cation sensing,which is promising for developing sweat sensors.

关键词： organic electrochemical transistors fullerene derivatives ethylene glycol side chains ion and electron conduction

来源：评论

学校读者我要写书评

暂无评论

Communication Countermeasure Strategy Decision-Making Based on Incomplete Information Game 27

Communication Countermeasure Strategy Decision-Making Based ...

引用

27th International Conference on Advanced Communications technology, ICACT 2025

作者： Liu, Jinyue Gao, Xiang Yang, Haowei Zhang, Jihao Liu, Yuhan Gong, Peng National Key Laboratory of Mechatronic Engineering and Control School of Mechatronical Engineering Beijing Institute of Technology Beijing China Institute of Computer Application Technology Norinco Group Beijing China

ISBN: (纸本)9791188428137

In modern battlefields, the stability of wireless communications is crucial for intelligence transmission, command coordination, and maintaining strategic advantage. However, with the rapid advancement of communication technologies, the electromagnetic environment has become increasingly complex, making intelligent decision-making in communication countermeasures a prominent research focus. However, most existing studies adopt deep learning and reinforcement learning methods, which require extensive data samples and computational resources. To address these limitations, this paper proposes a game-theoretic model for intelligent radio communication countermeasures under incomplete information. It quantitatively evaluates common attack and defense tactcis used in communication countermeasures and explores the mixed-strategy equilibrium of the game when both the attackers and defenders consist of multiple types. Furthermore, simulation-based comparative analyses are conducted to assess the factors influencing the utility of both the attacker and defender. The findings offer theoretical insights and decision-making support for the deployment of communication countermeasure strategies in practical military operations, contributing to significant strategic value. © 2025 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

StoryLLaVA: Enhancing Visual Storytelling with Multi-Modal Large Language Models 31

StoryLLaVA: Enhancing Visual Storytelling with Multi-Modal L...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Yang, Li Xiao, Zhiding Huang, Wenxin Zhong, Xian Hubei Key Laboratory of Big Data Intelligent Analysis and Application School of Computer Science and Information Engineering Hubei University China Hubei Key Laboratory of Transportation Internet of Things School of Computer Science and Artificial Intelligence Wuhan University of Technology China

ISBN: (纸本)9798891761964

The rapid development of multi-modal large language models (MLLMs) has positioned visual storytelling as a crucial area in content creation. However, existing models often struggle to maintain temporal, spatial, and narrative coherence across image sequences and frequently lack the depth and engagement of human-authored stories. To address these challenges, we propose Story with Large Language and Vision Assistant (StoryLLaVA), a novel framework for enhancing visual storytelling. Our approach introduces a Topic-Driven Narrative Optimizer (TDNO) that improves both the training data and MLLM models by integrating image descriptions, topic generation, and GPT-4-based refinements. Furthermore, we employ a preference-based ranked story sampling method that aligns model outputs with human storytelling preferences through positive-negative pairing. These two phases of the framework differ in their training methods: the former uses supervised fine-tuning, while the latter incorporates reinforcement learning with positive and negative sample pairs. Experimental results demonstrate that StoryLLaVA outperforms current models in visual relevance, coherence, and fluency, with LLM-based evaluations confirming the generation of richer and more engaging narratives. The enhanced dataset and model are available at https://***/XxxZzD/StoryLLaVA. © 2025 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EPRFL:An Efficient Privacy-Preserving and Robust Federated Learning Scheme for Fog Computing

引用

China Communications 2025年第4期22卷 202-222页

作者： Ke Zhijie Xie Yong Syed Hamad Shirazi Li Haifeng School of Computer Technology and Application Qinghai UniversityXining 810016China School of Computer and Information Science Qinghai Institute of TechnologyXining 810016China Guangdong Key Laboratory of Blockchain Security Guangzhou UniversityGuangzhou 510006China Department of Information Technology Hazara UniversityBaffa 21110Pakistan Qinghai Provincial Key Laboratory of Big Data in Finance and Artificial Intelligence Application Technology Xining 810016China

Federated learning(FL)is a distributed machine learning paradigm that excels at preserving data privacy when using data from multiple *** combined with Fog Computing,FL offers enhanced capabilities for machine learning applications in the Internet of Things(IoT).However,implementing FL across large-scale distributed fog networks presents significant challenges in maintaining privacy,preventing collusion attacks,and ensuring robust data *** address these challenges,we propose an Efficient Privacy-preserving and Robust Federated Learning(EPRFL)scheme for fog computing ***,we first propose an efficient secure aggregation strategy based on the improved threshold homomorphic encryption algorithm,which is not only resistant to model inference and collusion attacks,but also robust to fog node ***,we design a dynamic gradient filtering method based on cosine similarity to further reduce the communication *** minimize training delays,we develop a dynamic task scheduling strategy based on comprehensive *** analysis demonstrates that EPRFL offers robust security and low *** experimental results indicate that EPRFL outperforms similar strategies in terms of privacy preserving,model performance,and resource efficiency.

关键词： federated learning fog computing internet of things privacy-preserving robustness

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：