检索结果-内蒙古大学图书馆

41st Computer Graphics International Conference, CGI 2024

作者： Peng, Jiaxin Li, Tao Jiang, Qin Liu, Jie Wang, Ruibo Laboratory of Software Engineering for Complex Systems School of Computer Science National University of Defense Technology Hunan Changsha410073 China Parallel and Distributed Processing Laboratory School of Computer Science National University of Defense Technology Hunan Changsha410073 China

ISBN: (纸本)9783031820205

The conventional Levenberg-Marquardt (LM) algorithm is a state-of-the-art trust-region optimization method for solving bundle adjustment problems in the Structure-from-Motion community, which not only takes advantage of the fast convergence of the Gauss-Newton method, but also the stability of the gradient descent method when approaching optimal solutions. However, the damping ratio of LM is simply provided by trial-and-error, which causes slow convergence rate for large-scale problems. This paper proposes the Yamashita-Fukushima LM (YFLM) algorithm to reduce the time complexity for global bundle adjustment, where the damping factor is determined by Yamashita and Fukushima’s method. YFLM dynamically calculates a more reasonable and optimal damping ratio according to the newest reprojection error. The experimental results show that the YFLM algorithm outperforms the conventional LM algorithm for most public bundle adjustment datasets. Besides this, the convergence of the YFLM algorithm is also evaluated with different σ∈(0,2]. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Damping

来源：评论

学校读者我要写书评

暂无评论

Wideband 3-D Bandpass Frequency Selective Surface With High Selectivity and Angular Stability

引用

IEEE Microwave and Wireless Technology Letters 2025年

作者： Yan, Yuchen Wu, Weiwei Ma, Yuhong Huang, Jingjian Yuan, Naichang National University of Defense Technology State Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System Changsha410073 China National University of Defense Technology College of Electronic Engineering Hefei230037 China

This letter introduces a novel wideband bandpass frequency selective surface (FSS) based on 3-D slotline structures, which exhibits excellent selectivity and angular stability. The proposed FSS comprises orthogonally arranged 3-D periodic printed circuit boards (PCBs) etched with slotline structures. By simultaneously loading an inductive strip and a series LC structure based on interdigital capacitors at the center of the open-circuit slotline, a third-order filtering response with a controllable high-frequency transmission zero (TZ) is formed. In addition, a stepped-impedance short-circuited slotline is introduced to generate a controllable low-frequency TZ to further improve the passband selectivity. The working principle is elucidated through a detailed analysis employing equivalent circuit models (ECMs). Furthermore, to confirm the design concept, an FSS prototype is manufactured and measured. © 2023 IEEE.

关键词： Frequency selective surfaces

来源：评论

学校读者我要写书评

暂无评论

An Encoder-Decoder Model Based On Spiking Neural Networks For Address Event Representation Object Recognition

引用

IEEE Transactions on Cognitive and Developmental systems 2025年

作者： Du, Sichun Zhu, Haodi Zhang, Yang Hong, Qinghui Hunan University College of Computer Science and Electronic Engineering Changsha418002 China Shenzhen University Computer Vision Institute School of Computer Science and Software Engineering National Engineering Laboratory for Big Data System Computing Technology Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China

Address event representation (AER) object recognition task has attracted extensive attention in neuromorphic vision processing. The spike-based and event-driven computation inherent in the spiking neural network (SNN) provides an energy-saving solution for AER object recognition. However, SNN with spike timing dependent plasticity (STDP) learning rule has not achieved satisfying AER object recognition performance. This work proposes an SNN-based encoder-decoder model to improve the recognition performance of AER objects. An STDP-based locally connected spiking neural network (LC-SNN) is proposed as an encoder to extract rich spatiotemporal features from AER event flows more flexibly. After the encoder extracts and learns primary features, we propose a fully connected spiking neural network (FC-SNN) based on the reward-modulated spike-timing-dependent plasticity (R-STDP) learning rule as a decoder to learn higher-level features for classification. In addition, we improved the winner-take-all (WTA) mechanisms and R-STDP learning rule in the decoder based on the reward and punish decision, enabling the network to perform better. The experiments are performed on the N-MNIST, MNIST-DVS, and the DVS Gesture datasets, improving the accuracy of the best existing plasticity-based SNN by 0.19%, 0.27% and 1.35%, respectively. © 2016 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Design of High-efficiency Transmitarray with Beam Steering and Low Scattering Characteristic

引用

IEEE Transactions on Antennas and Propagation 2025年

作者： Shaozhi, Wang Zihao, Zheng Weiwei, Wu Yuhong, Ma Jingjian, Huang Qingzhan, Shi Naichang, Yuan National University of Defense Technology State Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System Hunan Changsha410000 China National University of Defense Technology College of Electronic Engineering Hefei230037 China

This article introduces a hybrid design method for high-efficiency absorbing Reconfigurable Transmitarray (ARTA). By cascading an absorbing layer with a 2-bit reconfigurable layer, the transmission unitcells can realize the frequency response characteristic of an Absorbing-Transmissive-Absorbing (A-T-A). Specifically, the frequencies with an absorption rate exceeding 80% are within the ranges of 3.3GHz-5.1GHz and 7.8GHz-9.4GHz, while the frequency range with transmission exceeding -3dB spans from 5.69GHz to 5.92GHz. Meanwhile, the transmission phase can be adjusted among four states: 0°, 90°, 180°, and 270°, enabling beam steering of ARTA. Compared to designs for non-reconfigurable transmissive arrays, our design methodology necessitates the satisfaction of absorbing performance under different phase states. For validation, A prototype sample, comprising a 12x12 array structured with 5 metallic layers and 4 dielectric layers, sandwiching an air layer in between, has been fabricated and tested. Measurement results demonstrated high radiation performance with a peak gain of 21.6 dB and aperture efficiency of 33.3% at 5.85 GHz. The BW-1 dB and BW-3 dB were 0.2 GHz and 0.6 GHz, respectively. ±60° 2D-scanning was achievable and when the beam is directed at 0°, the sidelobe levels in the E-plane and H-plane are -17.3 dB and -18 dB, respectively. Under normal incidence of an x-polarized wave, the -8 dB Monostatic RCS reduction bandwidths covered 32.1% (3.4-4.7 GHz) for lower band and 10% (8.5-9.4 GHz) for upper band. The ARTA by this hybrid design methodology represents an attractive solution for addressing electromagnetic compatibility issues and for low-detectability applications. © 1963-2012 IEEE.

关键词： Integrated circuit design

来源：评论

学校读者我要写书评

暂无评论

Exploring Communication-efficient Federated Learning via Stateless In-network Aggregation

引用

IEEE Transactions on Mobile Computing 2025年

作者： Xia, Junxu Cheng, Geyao Wu, Wenfei Luo, Lailong Guo, Deke National University of Defense Technology National Key Laboratory of Information Systems Engineering Changsha Hunan410073 China National University of Defense Technology State Key Laboratory of Complex & Critical Software Environment College of Information and Communication Changsha Hunan410073 China Peking University School of Computer Science Beijing100091 China

As an ambitious training paradigm, federated learning has garnered increasing attention in recent years, which enables collaborative training of a global model without accessing users' private data. However, due to the simultaneous and constant model updates gathering from massive distributed clients, the central server generally becomes a performance bottleneck. Additionally, the stateful aggregation (retaining all the updates from each client) conducted by the central server further poses potential threats to privacy, since it may recover the raw data based on such model updates inversely. The state-of-the-art methodologies, however, fail to address these two problems concurrently and efficiently. To this end, we propose GAIN, a secure aggregation acceleration service for federated learning. At its core, GAIN leverages programmable switches deployed at the edge network to aggregate model updates in a stateless manner before transmitting them to the central server. Consequently, GAIN can accelerate the transmission and aggregation of model updates while eliminating the chance of recovering private data. We evaluate the performance of GAIN through FPGA-based experiments and large-scale simulations. The results show that GAIN can effectively reduce bandwidth overhead and achieve up to 4.11× training throughput acceleration while prioritizing privacy protection. © 2025 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

DiffDual-AD: Diffusion-Based Dual-Stage Adversarial Defense Framework in Remote Sensing with Denoiser Constraint

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Lu, Zihao Sun, Hao Lei, Lin Xu, Yanjie Sun, Yuli Kuang, Gangyao National University of Defense Technology State Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System the College of Electronic Science and Technology Changsha410073 China National University of Defense Technology College of Aerospace Science and Engineering Changsha410073 China

Deep neural networks (DNNs), though highly effective in various Earth observation tasks with remote sensing images (RSIs), are vulnerable to adversarial attacks, threatening their reliability. Each maliciously attacked RSI potentially contains unique and critical information, but current defenses lack a unified framework for rapidly detecting adversarial RSIs and accurately restoring them to their natural state. To bridge this research gap, we propose a diffusion-based dual-stage adversarial defense (DiffDual-AD) framework. In the first stage, we propose a novel adversarial detection method based on the score expectation (AD-SE), which is integrated into the forward process of diffusion model with an improved denoiser constrained for adversarial defense. During the reverse process, the second stage introduces the distance and label-guided adversarial purification (DL-GAP) to restore adversarial RSIs to natural ones. With the help of two proposed guidelines and the specific denoiser, the DL-GAP effectively smooths out the adversarial perturbations from the detected adversarial RSIs while preserving semantic information and local key features. Finally, DL-GAP yields nonadversarial purified RSIs based on the results of AD-SE. Both stages are integrated within the diffusion models, complementing each other to form a pipelined operational mode. Extensive experiments across three RSI scene classification datasets have proven its efficacy in resisting adversarial RSIs in both whitebox and black-box scenarios, achieving an average adversarial detection accuracy of 87.02% with AD-SE and an average final classification accuracy of 81.50% with the entire DiffDual-AD. The performances of our proposed AD-SE and DL-GAP have surpassed other advanced adversarial detection and purification methods when applied to RSIs. Therefore, DiffDual-AD provides a unified and universal solution to preserve the utility and security of processing the adversarial RSIs, which advances the adversari

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Harnessing Multiple Large Language Models: A Survey on LLM Ensemble

arXiv

引用

arXiv 2025年

作者： Chen, Zhijun Li, Jingzheng Chen, Pengpeng Li, Zhuoran Sun, Kai Luo, Yuankai Mao, Qianren Yang, Dingqi Sun, Hailong Yu, Philip S. State Key Laboratory of Complex & Critical Software Environment Beihang University Beijing China Zhongguancun Laboratory Beijing China Aviation System Engineering Institute of China Beijing China Xi’an Jiaotong University Xi’an China University of Macau China University of Illinois at Chicago Chicago United States

LLM Ensemble—which involves the comprehensive use of multiple large language models (LLMs), each aimed at handling user queries during downstream inference, to benefit from their individual strengths—has gained substantial attention recently. The widespread availability of LLMs, coupled with their varying strengths and out-of-the-box usability, has profoundly advanced the field of LLM Ensemble. This paper presents the first systematic review of recent developments in LLM Ensemble. First, we introduce our taxonomy of LLM Ensemble and discuss several related research problems. Then, we provide a more in-depth classification of the methods under the broad categories of "ensemble-before-inference, ensemble-during-inference, ensemble-after-inference", and review all relevant methods. Finally, we introduce related benchmarks and applications, summarize existing studies, and suggest several future research directions. A curated list of papers on LLM Ensemble is available at https://***/junchenzhi/ Awesome-LLM-Ensemble. Copyright © 2025, The Authors. All rights reserved.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

PATCH: Empowering Large Language Model with Programmer-Intent Guidance and Collaborative-Behavior Simulation for Automatic Bug Fixing

arXiv

引用

arXiv 2025年

作者： Zhang, Yuwei Jin, Zhi Xing, Ying Li, Ge Liu, Fang Zhu, Jiaxin Dou, Wensheng Wei, Jun Affiliated with Nanjing Institute of Software Technology University of Chinese Academy of Sciences Nanjing China Key Laboratory of System Software Chinese Academy of Sciences Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China Key Laboratory of High Confidence Software Technologies Peking University Ministry of Education School of Computer Science Peking University Beijing China School of Computer Science Wuhan University Wuhan China School of Intelligent Engineering and Automation Beijing University of Posts and Telecommunications Beijing China State Key Laboratory of Complex & Critical Software Environment School of Computer Science and Engineering Beihang University Beijing China

Bug fixing holds significant importance in software development and maintenance. Recent research has made substantial strides in exploring the potential of large language models (LLMs) for automatically resolving software bugs. However, a noticeable gap in existing approaches lies in the oversight of collaborative facets intrinsic to bug resolution, treating the process as a single-stage endeavor. Moreover, most approaches solely take the buggy code snippet as input for LLMs during the patch generation stage. To mitigate the aforementioned limitations, we introduce a novel stage-wise framework named PATCH. Specifically, we first augment the buggy code snippet with corresponding dependence context and intent information to better guide LLMs in generating the correct candidate patches. Additionally, by taking inspiration from bug management practices, we decompose the bug-fixing task into four distinct stages: bug reporting, bug diagnosis, patch generation, and patch verification. These stages are performed interactively by LLMs, aiming to simulate the collaborative behavior of programmers during the resolution of software bugs. By harnessing these collective contributions, PATCH effectively enhances the bug-fixing capability of LLMs. We implement PATCH by employing the powerful dialogue-based LLM ChatGPT. Our evaluation on the widely used bug-fixing benchmark BFP demonstrates that PATCH has achieved better performance than state-of-the-art LLMs. Copyright © 2025, The Authors. All rights reserved.

关键词： Computer software maintenance

来源：评论

学校读者我要写书评

暂无评论

ForkXplorer:an approach of fork summary generation

引用

Frontiers of Computer Science 2022年第2期16卷 1-15页

作者： Zhang ZHANG Xinjun MAO Chao ZHANG Yao LU Key Laboratory of Software Engineering for Complex Systems College of ComputerNational University of Defense TechnologyChangsha 410073China

Pull-based development has become an important paradigm for distributed software *** this model,each developer independently works on a copied repository(i.e.,a fork)from the central *** is essential for developers to maintain awareness of the state of other forks to improve collaboration *** this paper,we propose a method to automatically generate a summary of a *** first use the random forest method to generate the label of a fork,i.e.,feature implementation or a bug *** on the information of the fork-related commits,we then use the TextRank algorithm to generate detailed activity information of the ***,we apply a set of rules to integrate all related information to construct a complete fork *** validate the effectiveness of our method,we conduct 30 groups of manual experiment and 77 groups of case studies on *** propose Fea_(avg)to evaluate the performance of Fea_(avg)the generated fork summary,considering the content accuracy,content integrity,sentence fluency,and label extraction *** results show that the average of of the fork summary generated by this method is *** than 63%of project maintainers and the contributors believe that the fork summary can improve development efficiency.

关键词： open source software pull-based development fork summary distributed cooperative development

来源：评论

学校读者我要写书评

暂无评论

AMCheX: Accurate Analysis of Missing-Check Bugs for Linux Kernel

引用

Journal of Computer Science & Technology 2021年第6期36卷 1325-1341页

作者： Ying-Jie Wang Liang-Ze Yin Wei Dong Key Laboratory of Software Engineering for Complex Systems College of Computer Science National University of Defense TechnologyChangsha 410073China

The Linux kernel adopts a large number of security checks to prevent security-sensitive operations from being executed under unsafe *** a security-sensitive operation is unchecked,a missing-check issue *** check is a class of severe bugs in software programs especially in operating system kernels,which may cause a variety of security issues,such as out-of-bound accesses,permission bypasses,and privilege *** to the lack of security specifications,how to automatically identify security-sensitive operations and their required security checks in the Linux kernel becomes a challenge for missing-check *** this paper,we present an accurate missing-check analysis method for Linux kernel,which can automatically infer possible security-sensitive ***,we first automatically identify all possible security check functions of *** according to their callsites,a two-direction analysis method is leveraged to identify possible security-sensitive operations.A missing-check bug is reported when the security-sensitive operation is not protected by its corresponding security *** have implemented our method as a tool,named AMCheX,on top of the LLVM(Low Level Virtual Machine)framework and evaluated it on the Linux *** reported 12 new missing-check bugs which can cause security *** of them have been confirmed by Linux maintainers.

关键词： security check function security-sensitive operation program analysis missing-check

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：