检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Wang, Yunfei Liu, Shixuan Wang, Wenhao Zhou, Changling Zhang, Chao Jin, Jiandong Zhu, Cheng National Key Laboratory of Information Systems Engineering National University of Defense Technology Hunan China Department of Intelligent Data Science College of Computer Science and Technology National University of Defense Technology Hunan China National University of Defense Technology Hunan China Tsinghua University Beijing China Computer Center Peking University Beijing China

The integration of artificial intelligence into automated penetration testing (AutoPT) has highlighted the necessity of simulation modeling for the training of intelligent agents, due to its cost-efficiency and swift feedback capabilities. Despite the proliferation of AutoPT research, there is a recognized gap in the availability of a unified framework for simulation modeling methods. This paper presents a systematic review and synthesis of existing techniques, introducing MDCPM to categorize studies based on literature objectives, network simulation complexity, dependency of technical and tactical operations, and scenario feedback and variation. To bridge the gap in unified method for multi-dimensional and multi-level simulation modeling, dynamic environment modeling, and the scarcity of public datasets, we introduce AutoPT-Sim, a novel modeling framework that based on policy automation and encompasses the combination of all sub dimensions. AutoPT-Sim offers a comprehensive approach to modeling network environments, attackers, and defenders, transcending the constraints of static modeling and accommodating networks of diverse scales. We publicly release a generated standard network environment dataset and the code of Network Generator. By integrating publicly available datasets flexibly, support is offered for various simulation modeling levels focused on policy automation in MDCPM and the network generator help researchers output customized target network data by adjusting parameters or fine-tuning the network generator. Copyright © 2025, The Authors. All rights reserved.

关键词： Intelligent agents

来源：评论

学校读者我要写书评

暂无评论

Modeling the Label Distributions for Weakly-Supervised Semantic Segmentation

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年 PP卷 PP页

作者： Wu, Linshan Zhong, Zhun Ma, Jiayi Wei, Yunchao Chen, Hao Fang, Leyuan Li, Shutao Hunan University College of Electrical and Information Engineering Changsha410082 China Hefei University of Technology School of Computer Science and Information Engineering China Wuhan University Electronic Information School Wuhan430072 China Beijing Jiaotong University Institute of Information Science Beijing10044 China The Hong Kong University of Science and Technology Department of Computer Science and Engineering Clear Water Bay Hong Kong Hong Kong

Weakly-Supervised Semantic Segmentation (WSSS) aims to train segmentation models by weak labels, which is receiving significant attention due to its low annotation cost. Existing approaches focus on generating pseudo labels for supervision while largely ignoring to leverage the inherent semantic correlation among different pseudo labels. We observe that pseudo-labeled pixels that are close to each other in the feature space are more likely to share the same class, and those closer to the distribution centers tend to have higher confidence. Motivated by this, we propose to model the underlying label distributions and employ cross-label constraints to generate more accurate pseudo labels. In this paper, we develop a unified WSSS framework named Adaptive Gaussian Mixtures Model, which leverages a GMM to model the label distributions. Specifically, we calculate the feature distribution centers of pseudo-labeled pixels and build the GMM by measuring the distance between the centers and each pseudo-labeled pixel. Then, we introduce an Online Expectation-Maximization (OEM) algorithm and a novel maximization loss to optimize the GMM adaptively, aiming to learn more discriminative decision boundaries between different class- wise Gaussian mixtures. Based on the label distributions, we leverage the GMM to generate high-quality pseudo labels for more reliable supervision. Our framework is capable of solving different forms of weak labels: image-level labels, points, scribbles, blocks, and bounding-boxes. Extensive experiments on PASCAL, COCO, Cityscapes, and ADE20 K datasets demonstrate that our framework can effectively provide more reliable supervision and outperform the state-of-the-art methods under all settings. Code will be available at https://***/Luffy03/AGMM-SASS. © 1979-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Novel Load Balancing Mechanism Based on Deep Reinforcement Learning for Human-Centric Applications in Data Centers

引用

Human-centric Computing and Information sciences 2025年 15卷

作者： Hu, Jinbin Luo, Wangqing He, Yi Rao, Shuying Alqahtani, Fayez Tolba, Amr Zhu, Min Wang, Jin School of Computer and Communication Engineering Changsha University of Science and Technology Changsha China Software Engineering Department College of Computer and Information Sciences King Saud University Riyadh Saudi Arabia Department of Computer Science Community College King Saud University Riyadh Saudi Arabia College of Information Science and Technology Zhejiang Shuren University Zhejiang China

Human-computer interaction applications require ultra-low response delays to achieve a better user experience. With the rapid growth of data center network (DCN) topologies, the number of equal-cost paths has increased dramatically. It is imperative to use load balancing between parallel paths to improve link utilization. However, the existing load balancing mechanisms cannot make appropriate forwarding decisions for reacting to the dynamic traffic and path congestion status in large-scale DCNs, resulting in poor network performance. In this paper, we have proposed a dynamic load balancing (DLB) mechanism that uses deep reinforcement learning (DRL) to monitor the status of parallel paths in real time and uses the depth deterministic policy gradient algorithm to make the path state weight (PSW) automatically adapt to different network load scenarios. It then automatically configures the PSW through the DRL agent to guide the switch to select the best forwarding path to balance the load. The experimental results show that DLB significantly reduces the average flow completion by up to 36% compared to state-of-the-art load balancing schemes such as DRILL, LetFlow, and RPS under the asymmetric topology scenario, the result of which significantly enhances the efficiency of human-centric interaction. © (2024), (Korea Information Processing Society). All Rights Reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Interface-driven D-band modulation for dual-function anchoring and catalytic conversion of polysulfides in lithium-sulfur batteries

引用

Journal of Energy Chemistry 2025年 107卷 919-928页

作者： Wenlong Xia Hengzhi Liu Hong Liu Qianqian Liang Lanhua Yi Manfang Chen Xianyou Wang Xingqiao Wu Hongbo Shu National Local Joint Engineering Laboratory for Key Materials of New Energy Storage Battery Hunan Province Key Laboratory for Electrochemical Energy Storage and Conversion School of Chemistry Xiangtan University Xiangtan Hunan 411105 China Department of Chemistry Southern University of Science and Technology Shenzhen Guangdong 518055 China College of Chemistry and Materials Engineering Wenzhou University Wenzhou Zhejiang 325035 China

The polysulfide shuttle effect critically hinders lithium-sulfur (Li S) battery development, therefore, the design of heterogeneous interface engineering with “adsorption-catalysis” functions for polysulfide conversion has garnered considerable attention. However, the exploration of the intricate relationship between key electronic properties and catalytic activity at such interfaces remains a challenge. Additionally, a comprehensive understanding of the thermodynamic growth mechanisms for heterostructure materials is lacking. Herein, a Ni-based homologous structure was precisely constructed via thermodynamic control, with a specific focus on optimizing the interface design. The theoretical results show that the heterostructures with adjustable composition realize the appropriate upward shift to the D-band, improving the affinity towards polysulfide, and further reducing the reaction energy barrier. On this basis, the relationship between interface design and the D-band center, as well as catalytic performance, was established. Specifically, M-Ni 3 Fe/Ni 3 ZnC 0.7 accomplishes the electron enrichment at the interface, supporting the further diffusion of polysulfides, and lowering the Li S bond energy, performing the bidirectional catalytic transformation of polysulfides. As a result, the Li S batteries with the cathode of M-Ni 3 Fe/Ni 3 ZnC 0.7 /S deliver rate performances of discharge capacity of 514 mA h g −1 at 5.0 C. This understanding of the D-band and interfacial design provides a framework for Li S catalyst optimization.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Seeing Through Dense Fog With an Intelligent Adaptive Dehazing System

引用

IEEE Sensors Journal 2025年第10期25卷 17696-17705页

作者： Chen, Pengyun Cao, Ning Xu, Ziqin Cui, Shuang Jin, Shaohui Liu, Hao Xu, Mingliang Zhengzhou University School of Computer Science and Artificial Intelligence Zhengzhou450001 China National University of Defense Technology College of Advanced Interdisciplinary Studies Changsha410073 China Engineering Research Center of Intelligent Swarm Systems Ministry of Education Zhengzhou450001 China National Supercomputing Center Zhengzhou450001 China

Most existing image dehazing methods are mainly suitable for synthetic datasets and often perform poorly in real-world, complex hazy scenarios. To address this issue, this article proposes an intelligent adaptive dehazing system (IADS) that integrates range-gated imaging with deep learning, combining image acquisition and restoration for enhanced dehazing performance. The range-gated imaging system reduces scattered light interference. However, our approach primarily focuses on enhancing image quality through advanced dehazing methods. Specifically, we introduce the MSCENAFormer dehazing network, which achieves high-quality reconstruction of target scenes in dense fog by effectively removing fog and improving visibility. The core modules of MSCENAFormer include the multiscale enhanced neighborhood attention (MSENA) module and the comprehensive attention refinement module (CARM). MSENA is designed to capture rich local information in harsh environment, improving the dehazing effect and enhancing image details. CARM integrates the local and global information to optimize the visual effect further. In addition, the adaptive feature mixing (AFM) module is used to fuse multiscale features for better performance. To validate the performance of our method, we utilize our lab-collected nonhomogeneous haze real dataset, O-ITDF, along with the public datasets NH-HAZE, NTIRE2021, and NTIRE2023. Experimental results demonstrate that our proposed MSCENAFormer outperforms many methods. © 2001-2012 IEEE.

关键词： Light interference

来源：评论

学校读者我要写书评

暂无评论

An Efficient Multi-Core DSP Power Management Controller

Engineering Reports

引用

engineering Reports 2025年第4期7卷

作者： Huang, Jian Wang, Huili Gong, Guohui Wang, Lei Chen, Xiaowen R&D Department Hunan Great Wall Galaxy Technology Co. Ltd. Hunan Changsha China College of Computer Science and Technology National University of Defense Technology Hunan Changsha China

Today's society has entered a digital era, and the use of DSP is becoming increasingly frequent and important. In order to achieve the market targets of high energy efficiency, it is necessary to integrate low-power design from the chip design stage. Based on FT-xDSP chip architecture, this work designs a power management controller for DSP suitable for multi-core and multi-integrated peripherals from the perspective of power control in the chip design stage. This controller can precisely control the power supply, clock, and memory of each module in the DSP and introduces a clamp control unit in the power management controller to solve the problem of possible glitches during asynchronous reset and ensures that the system has no overflow of redundant requests. Additionally, a configurable state transition counter is also set up to avoid the problem of insufficient state transition time for low-speed peripherals or long waiting time for high-speed peripherals. After the pre-tapeout experiment and post-tapeout testing data analysis, the above new power control manager has excellent power management performance. In the low power consumption state of the chip, the overall power consumption of the core is reduced by over 95%, which is of great significance for achieving high-efficiency processor chips. © 2025 The Author(s). engineering Reports published by John Wiley & Sons Ltd.

关键词： Integrated circuit design

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Wireless Information and Power Transfer for STAR-RIS Assisted UAV Networks

引用

IEEE Internet of Things Journal 2025年

作者： Xie, Wenwu Qin, Lijuan Wang, Ji Wu, Weimin Li, Xingwang Xu, Hongbo Yang, Liang Hunan Institute of Science and Technology School of Information Science and Engineering Yueyang414006 China Central China Normal University Department of Electronics and Information Engineering Wuhan430079 China Huazhong University of Science and Technology School of Electronic Information and Communications Wuhan430074 China Henan Polytechnic University School of Physics and Electronic Information Engineering Jiaozuo454003 China Hunan University College of Computer Science and Electronic Engineering Changsha410082 China

This paper explores the benefits of deploying simultaneously transmitting and reflecting reconfigurable intelligence surfaces (STAR-RIS) in unmanned aerial vehicle (UAV) networks with simultaneous wireless information and power transfer. In the proposed system, the UAV utilizes STAR-RIS to radiate energy-carrying information signals (ECISs) to multiple outdoor energy receivers and multiple indoor information receivers without flying over indoor no-fly zone. Based on the UAV propulsion power formula, we successively introduce fly-hover-broadcast (FHB) and path discretization (PD) protocols to minimize the total UAV energy consumption by jointly using the extended penalty function and optimization algorithm based on the expected value of channel status information, where the UAV flight constraints, no-fly constraint, minimized energy or information threshold constraints, and STAR-RIS phase-shift constraints are met. The FHB protocol, which requires the UAV to radiate the ECISs to the users at only a few hovering positions, provides a lower-bound performance of UAV energy consumption, while the PD protocol is used to discuss the general situation of the ECISs during UAV flight. Simulation results demonstrate that the utilization of the STAR-RIS in UAV networks outperforms the traditional RIS in improving energy efficiency and extending UAV flight time. © 2014 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Solid solution reaction enhanced rapid sodium ion Migration for superior Low-Temperature performance

引用

Journal of Colloid and Interface science 2025年 696卷 137851页

作者： Li, Jiao Ban, Jianfeng Zeng, Zhuoyan Lu, Feng Qin, Mulan Ma, Zhongyun Wang, Xianyou Luo, Zhigao College of Chemistry Xiangtan University Xiangtan411105 China School of materials science and engineering Guangdong University of Petrochemical Technology Maoming525000 China College of Materials and Chemical Engineering Hunan Institute of Engineering Xiangtan411104 China National Local Joint Engineering Laboratory for Key Materials of New Energy Storage Battery National Base for International Science & Technology Cooperation Key Laboratory of Environmentally Friendly Chemistry and Application of Ministry of Education Xiangtan411105 China

Owing to the natural abundance of sodium resources, sodium-ion battery (SIBs) systems have emerged as highly promising alternatives for next-generation energy storage applications, particularly for large-scale grid storage and cost-sensitive implementations. The electrochemical performance exhibit pronounced temperature dependence, especially for capacity retention, cycling stability, and operational safety. Both elevated and sub-ambient temperature conditions can induce various detrimental effects that markedly compromise cell performance and longevity. Considerable difficulties of sodium-ion batteries (SIBs) behavior in subzero environments have become a critical challenge in pursuit of more reliable and versatile energy storage solutions. In this study, we fabricated layer cathode materials via a facile sol–gel method, incorporating a synergistic Cu/Co/Mg multi-doping strategy to optimize electrochemical performance, resulting in a high capacity and structurally stable Na0.7Ni0.25Cu0.1Co0.05Mg0.05Mn0.55O2 (NNCCMM) at 2.0–4.0 V. NNCCMM exhibits extraordinary cycle stability and fast charging capability at low temperatures as well as normal temperature. The capacity at −20°C remains as high as 81.7 % (0.2C) of its room-temperature value. This study significantly expands the potential applications of sodium-ion battery technology while providing critical insights for developing advanced cathode materials with enhanced low-temperature performance. © 2025 Elsevier Inc.

关键词： Sodium-ion batteries

来源：评论

学校读者我要写书评

暂无评论

Hyper-IIoT: A Smart Contract-inspired Access Control Scheme for Resource-constrained Industrial Internet of Things

IEEE Transactions on Sustainable Computing

引用

IEEE Transactions on Sustainable Computing 2025年

作者： Li, Dun Li, Hongzhi Crespi, Noel Minerva, Roberto Li, Ming Liang, Wei Li, Kuan-Ching Tsinghua University Department of Industrial Engineering China Institut Polytechnique de Paris Samovar Telecom SudParis Palaiseau91120 France Chizhou University College of Big Data and Artificial Intelligence Chizhou247100 China The Hong Kong Polytechnic University Research Institute for Advanced Manufacturing Hung Hom Hong Kong Hunan University of Science and Technology School of Computer Science and Engineering Hunan University of Science and Technology Sanya Research Institute Hunan Key Laboratory for Service Computing and Novel Software Technology China Providence University Dept. of Computer Science and Information Engineering Taiwan

In recent years, the refinements in industrial processes and the increasing complexity of managing privacy-sensitive data in Industrial Internet of Things (IIoT) devices have highlighted the need for secure, robust, and adaptive data management solutions. In this work, we propose a smart contract-assisted access control scheme for IIoT, which employs the Attribute-Based Access Control (ABAC) model to set access permissions for different industrial components. Besides, we defined a storage model and data format for private data by designing and deploying smart contracts to manage system operations and access policies. In addition, the bloom filter component is deployed to optimize the efficiency of contract management and system performance. Experimental results show that in real-world simulations, Hyper-IIoT demonstrates excellent contract execution time control, stable system throughput, and rapid consensus processes that are capable of handling high throughput and efficient consensus in distributed systems, even in large-scale request scenarios. © 2016 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Memristor-Based Brain Emotional Learning Neural Network With Attention Mechanism and its Application

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年

作者： Deng, Quanli Wang, Chunhua Sun, Yichuang Cong, Xu Lin, Hairong Deng, Zekun Hunan University College of Computer Science and Electronic Engineering Changsha410082 China Hunan University Greater Bay Area Institute for Innovation Guangzhou511300 China University of Hertfordshire School of Engineering and Computer Science HatfieldAL10 9AB United Kingdom Changsha University of Science and Technology School of Computer and Communication Engineering Changsha410082 China Central South University School of Electronic Information Changsha410083 China

The brain emotional learning network offers several advantages when compared to traditional neural networks. It features a simpler structure, low computational complexity, and fast training speed. These characteristics make it ideal for applications like pattern recognition, data classification, and intelligent control. However, current brain emotional learning networks, including their modified networks, are not capable of recognizing or classifying data in complex environments. To address this issue, this paper proposes a brain emotional learning network with an attention mechanism that strengthens the processing of key information while suppressing interfering information, thereby enabling the network to recognize data within complex environments. Furthermore, software implementation of neural networks often experiences slow computing speeds due to the separation of storage and computation in traditional von Neumann computers. To combat this issue, the paper presents a hardware circuit implementation of the attention mechanism-based brain emotional learning network using memristors. Finally, the designed in-memory computing neural network has been successfully applied to the recognition of traffic signs within complex environments, and has achieved accurate and rapid recognition. © 1982-2012 IEEE.

关键词： Feature extraction

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：