检索结果-内蒙古大学图书馆

Broadband low-frequency sound absorption of multifunctional composite metastructure

science China(Technological sciences) 2025年第2期68卷 114-124页

作者： Yilong YANG Shanshan LIU Yan LI Tong GAO Yongdong PAN Yong LI Yabin JIN School of Aerospace Engineering and Applied Mechanics Tongji UniversityShanghai 200092China State International Joint Research Center of Aerospace Design and Additive Manufacturing Northwestern Polytechnical UniversityXi’an 710072China Institute of Acoustics School of Physics Science and EngineeringTongji UniversityShanghai 200092China Shanghai Key Laboratory of Intelligent Sensing and Detection Technology School of Mechanical and Power EngineeringEast China University of Science and TechnologyShanghai 200237China Shanghai Institute of Aircraft Mechanics and Control Shanghai 200092China

In this study,we fabricated multifunctional metastructures from carbon fiber-reinforced plastic composites using additive manufacturing *** metastructures are characterized by their lightweight,load-bearing capacity,and broadband low-frequency sound absorption *** metastructure consists of 36 unit cells,and non-local coupling mechanism was considered for designing the sound absorption *** developed an acoustic impedance theory tailored for the metastructure,facilitating an analysis of thermal and viscous dissipation *** is proven theoretically and experimentally that the proposed composite metastructure can achieve a noise reduction with an average sound absorption coefficient greater than 0.9 across frequencies in the rage of 330-1500 *** also studied the metastructure’s quasi-static and cyclic compression performance,confirming its efficient absorption capabilities after cyclic *** proposed design and additive manufacturing method for composite metastructures provides a novel pathway for creating lightweight,multifunctional structures with diverse applications,such as aerospace engineering.

关键词： composite metastructure broadband sound absorption additive manufacturing

来源：评论

学校读者我要写书评

暂无评论

Dynamic Regret for Distributed Online Composite Optimization

引用

IEEE Transactions on Automatic control 2025年第5期70卷 3056-3071页

作者： Hou, Ruijie Yu, Yang Li, Xiuxian Tongji University Department of Control Science and Engineering College of Electronics and Information Engineering Shanghai201800 China Tongji University Shanghai Research Institute for Intelligent Autonomous Systems National Key Laboratory of Autonomous Intelligent Unmanned Systems Frontiers Science Center for Intelligent Autonomous Systems Ministry of Education Shanghai Institute of Intelligent Science and Technology Shanghai201210 China

This article focuses on online composite optimization over multiagent networks. In the distributed setting, each agent has its own local loss function, which consists of a convex, strongly convex or strongly convex and smooth function, and a time-varying nonsmooth regularizer. Two distributed online algorithms are proposed and corresponding dynamic regrets are analyzed. Two proposed algorithms are based on signs of relative states. The first algorithm obtains (Formula presented) dynamic regret bound when each local loss is a general convex composite function, where CT is the path variation. If CT can be estimated in advance for convex or strongly convex local loss with a time-varying nonsmooth regularizer, then dynamic regret bounds are, respectively, in the order of (Formula presented) and o (log T(1 + CT)). The second algorithm is based on the first one, especially for handling the local loss composed of a strongly convex and smooth function with a nonsmooth regularizer, and then obtains o (1 + CT) dynamic regret bound. In the end, numerical results are given to support the theoretical findings. © 1963-2012 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Aggressive and robust low-level control and trajectory tracking for quadrotors with deep reinforcement learning

引用

Neural Computing and Applications 2025年第3期37卷 1223-1240页

作者： Chen, Shiyu Li, Yanjie Lou, Yunjiang Lin, Ke Department of Control Science and Engineering Harbin Institute of Technology Shenzhen Shenzhen518055 China Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics Shenzhen518055 China

Executing accurate trajectory tracking tasks using a high-performance low-level controller is crucial for quadrotors to be applied in various scenarios, especially those involving uncertain disturbances. However, due to the uncertainties in disturbed environments, developing effective low-level controllers with traditional model-based control schemes is challenging. This paper presents an aggressive and robust reinforcement learning (RL)-based low-level control policy for quadrotors. The policy maps the observed quadrotor state directly to motor thrust commands, without requiring the quadrotor dynamics. Additionally, a trajectory generation pipeline is developed to improve the accuracy of trajectory tracking tasks based on differential flatness. With the learned low-level control policy, extensive simulations and real-world experiments are implemented to validate the performance of the policy. The results indicate that our RL-based low-level control policy outperforms traditional proportional–integral–derivative (PID) control methods and related learning-based policies in terms of accuracy and robustness, particularly in environments with uncertain disturbances. Furthermore, the proposed RL-based control policy exhibits an aggressive response in trajectory tracking, even when the speed of the desired trajectory is increased to 6 m/s. Moreover, the learned policy demonstrates strong vibration suppression capabilities and enables the quadrotor to recover to a hovering state from random initial conditions with shorter response time. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Trust-Based Identity Privacy for Edge Computing 24

Trust-Based Identity Privacy for Edge Computing

引用

14th International Conference on Communication and Network Security, ICCNS 2024

作者： Dong, Jie Wen Kang, Xi Nai Peng, Jin Jiang, Xuan Ming Zhu, Tao Jun Information Technology Department National Key Laboratory of Seience and Technology on Aerospace Intelligence Control Beijing Aerospace Automatic Control Institute BeiJing China School of Computer Science Beijing University of Technology BeiJing China

ISBN: (纸本)9798400717994

College of Computer science Beijing University of technology, Beijing 100124, China, 1374622525@*** This paper proposes a trust collaboration technology for edge computing, addressing trust isolation and security issues through a unified trust value calculation method and blockchain technology. The designed trust management model evaluates the identity, capability, and behavior of terminal nodes using static and dynamic trust measurements. A consortium blockchain stores trust information to ensure immutability and efficient sharing. Simulation experiments validate the scheme's effectiveness in countering malicious node attacks, improving task completion rates, and reducing system risks. This solution offers an efficient and secure approach to trust management in edge computing environments. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Trust Collaboration for Edge Computing 24

Trust Collaboration for Edge Computing

引用

14th International Conference on Communication and Network Security, ICCNS 2024

ISBN: (纸本)9798400717994

As edge computing becomes an increasingly important computing model, trust management and security issues are becoming more severe. Problems such as malicious node attacks and trust isolation pose threats to the security and stability of edge computing environments. Therefore, designing an efficient and secure trust management mechanism is imperative. This paper proposes a trust collaboration technology for edge computing, addressing trust isolation and security issues through a unified trust value calculation method and blockchain technology. The designed trust management model evaluates the identity, capability, and behavior of terminal nodes using static and dynamic trust measurements. A consortium blockchain stores trust information to ensure immutability and efficient sharing. Simulation experiments validate the scheme's effectiveness in countering malicious node attacks, improving task completion rates, and reducing system risks. This solution offers an efficient and secure approach to trust management in edge computing environments. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

FPGA-based Real-Time High-resolution Image Processing for rocket on-board processing 17

FPGA-based Real-Time High-resolution Image Processing for ro...

引用

17th IEEE International Conference on Computer Research and Development, ICCRD 2025

作者： Zhou, Hui Wang, Xiaofeng Xie, Yujia Cao, Yongxiang Tang, Yu Huo, Yongchun Wen, Huan Zhao, Xiongbo Li, Chaoran National Key Laboratory of Science and Technology on Aerospace Intelligent Control Beijing Aerospace Automatic Control Institute Beijing China Beihang University Computer Science and Engineering Beijing China Beihang University National Superior College for Engineers Beijing China

ISBN: (纸本)9798331531881

The structure of the rocket-borne model is inherently complex, with processed images exhibiting high resolution and generating substantial amounts of data and calculations. Achieving robust real-Time computing on an embedded platform poses significant challenges due to strictly limited resources, power consumption constraints, and size limitations. Our review of rocket-borne applications reveals considerable variability in the design resources of different devices, indicating a need for expanded design approaches. Upon evaluating existing methods, we identified two primary drawbacks. First, certain operators within the high-resolution target detection model are difficult to parallelize, resulting in significant inference delays that hinder the ability to meet task requirements. Although existing methods have been extended, there remains significant potential for performance enhancement in core scheduling for poor acceleration. This paper proposes an optimized architecture for the target detection algorithm accelerator designed for high-resolution images, along with a novel highly parallel data pre-processing and post-processing module implemented on FPGA to address these issues. Compared to the ARM implementation, this architecture demonstrates an improved performance of 24.64x. Furthermore, to ensure flexible application across various rocket launch scenarios, we introduce an optimization structure for convolution, pooling, and fusion operators and a multi-core expansion optimization method. This approach yields a 1.29x improvement in computing unit utilization compared to state-of-The-Art multi-core scaling efforts. Finally, we assessed the accelerator architecture across multiple FPGA platforms, achieving a peak processing element utilization rate of 99.71% for a single core and layer. The overall computing efficiency, excluding the first layer, exceeded 90%. The peak computing power for the four cores reached 1638.4 GOPS, and the end-To-end computation time for

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation and Transmitter Optimization for AN-Aided FH Communication Against Time Misalignment

引用

China Communications 2025年第3期22卷 86-103页

作者： Song Changqing Lin Lang Qin Lizhi Xiao Fei Zhao Hongzhi Shao Shihai National Key Laboratory of Wireless Communications University of Electronic Science and Technology of ChinaChengdu 611731China The Laboratory of Electromagnetic Space Cognition and Intelligent Control Beijing 100089China The Thirtieth Research Institude of China Electronic Science and Technology Group Corporation Chengdu 610093China

To guarantee secure communication against eavesdropping and malicious attack,an artificial noise(AN)-aided frequency-hopping(FH)architecture is adopted in this *** the inevitable time misalignment between the received signal and locally reconstructed AN will deteriorate the AN cancellation performance,yielding significant secrecy degradation at the FH *** view of this,first,the AN cancellation performance under time misalignment is evaluated via signal to AN-plus-noise ratio,and the system secrecy is analyzed via secrecy ***,to mitigate the performance degradation raised by time misalignment,the transmitting power allocation scheme for AN and confidential signal(CS)is optimized,and the optimal hopping period is ***,the obtained conclusions in both the performance evaluation and transmitter optimization sections hold no matter whether the eavesdropper can realize FH synchronization or *** verify that time misalignment will raise non-negligible performance ***,the power ratio of AN to CS should decrease as time misalignment increases,and for perfect time synchronization,the transmitting power of AN and CS should be *** addition,a longer hopping period is preferred for secrecy enhancement when time misalignment gets exacerbated.

关键词： artificial noise(AN)cancellation hopping period design power allocation time misalignment

来源：评论

学校读者我要写书评

暂无评论

Infrared Dim Small Target Detection Algorithm Based on Adaptive Attention Transformer Network

引用

Journal of Shanghai Jiaotong University (science) 2025年 1-13页

作者： Ding, Leqi Xia, Yilin Wang, Biyun Cai, Yunze Department of Automation Shanghai Jiao Tong UniversityKey Laboratory of System Control and Information Processing of Ministry of Education Shanghai200240 China National Key Laboratory of Air-based Information Perception and Fusion Henan Luoyang471009 China Shanghai Institute of Aerospace Control Technology Infrared Detection Technology R & D Center of China Aerospace Science and Technology Corporation Shanghai201109 China

This paper presents a novel algorithm for detecting infrared dim small targets in complex backgrounds by integrating both global and local feature information. The proposed method employs an adaptive attention transformer network which addresses challenges associated with computational complexity and information redundancy in traditional self-attention mechanisms. A global context aggregation module is designed to address the loss of small target features in high-level feature maps. This module compensates for spatial distribution information during the multi-scale feature fusion process, ensuring the preservation of target features. Comparison experiments were conducted on two datasets, NUAA-SIRST and IRSTD-1k. The proposed algorithm achieved 0.784 for mIoU and 0.878 for F-measure on NUAA-SIRST, 0.632 for mIoU and 0.807 for F-measure on IRST-1k, all of which are the highest values. The proposed algorithm shows a significant improvement over other existing detection algorithms, demonstrating its capability to accurately extract both local and global features of targets with high recall rates and low false alarm rates across various scenarios. The ablation study results highlight the significant improvements contributed by the key modules to the proposed algorithm. (Figure presented.) © Shanghai Jiao Tong University 2025.

关键词： A adaptive attention global context aggregation module infrared dim small target detection TP391.4 Transformer network

来源：评论

学校读者我要写书评

暂无评论

Kolmogorov-Arnold Networks for Enhancing Gravitational Wave Glitch Classification Performance 24

Kolmogorov-Arnold Networks for Enhancing Gravitational Wave ...

引用

4th Asia-Pacific Artificial Intelligence and Big Data Forum, AIBDF 2024

作者： Cai, Yiting Ma, Cunliang Xiao, Wanhai Jiangxi Provincial Key Laboratory of Multidimensional Intelligent Perception and Control Jiangxi University of Science and Technology Jiangxi Ganzhou China

ISBN: (纸本)9798400710865

Detecting gravitational waves is essential for the success of the LIGO and Virgo experiments, requiring thorough comprehension of how these instruments are affected by environmental and instrumental noise. In particular, the data recorded by the LIGO/Virgo detectors frequently include transient noise events, referred to as"glitches". These glitches can interfere with real gravitational wave signals and, in some cases, their characteristics may resemble those of actual gravitational wave signals, leading to misidentification. Identifying and differentiating these glitches plays a vital role in improving the precision and dependability of gravitational wave observations. LIGO’s initial observation of gravitational waves marked a transformative achievement in expanding our comprehension of the universe. However, because of the detectors’ exceptional sensitivity, they also pick up many other noise sources that can interfere with the observation of gravitational waves. To address this challenge, numerous classification methods have been proposed;however, as model complexity increases, so does the risk of overfitting, requiring more computational resources and resulting in significantly longer training and inference times. The Kolmogorov-Arnold Network (KAN), with its unique high-dimensional mapping and powerful feature extraction capabilities, demonstrates greater robustness and accuracy than traditional methods, thus improving classification performance. In this paper, we explore multi-view classification of gravitational wave glitches using KAN networks, where the linear and convolutional layers of conventional neural networks are replaced with KAN-based structures, and residual connections are incorporated within the KAN modules. © 2024 Copyright held by the owner/author(s).

关键词： Gravitational effects

来源：评论

学校读者我要写书评

暂无评论

Edge Gradient Exploration Attack based on Graph Neural Networks 24

Edge Gradient Exploration Attack based on Graph Neural Netwo...

引用

4th Asia-Pacific Artificial Intelligence and Big Data Forum, AIBDF 2024

作者： Yang, Shuxin Ge, Ran Jiangxi Province Key Laboratory of Multidimensional Intelligent Perception and Control Jiangxi University of Science and Technology Jiangxi Ganzhou China

ISBN: (纸本)9798400710865

Graph Neural Networks (GNNs) have achieved remarkable success in various graph-structured tasks due to their powerful graph representation learning capabilities. By aggregating and transforming information from the neighboring nodes, GNNs explore the structure of the graph and the features of the nodes. However, recent theoretical and empirical analyses have revealed that GNNs are particularly vulnerable to adversarial attacks. Among these, gradient-based attacks have been widely studied for their inherent efficiency and effectiveness. Nevertheless, due to the discrete nature of graph data, gradient-based attacks often result in suboptimal outcomes. Furthermore, the portability of some previously proposed attack algorithms requires further improvement. To address these two issues, we propose a novel Multi-Network Exploratory Attack (MNEA) aimed at enhancing gradient-based graph perturbations and improving their transferability. MNEA consists of two phases: the generation phase and the reconstruction phase. In the generation phase, multiple networks are utilized to generate a variety of candidate edges, preventing the generated perturbed edges from being too targeted toward a single model, which could lead to decreased transferability. The reconstruction phase introduces multiple edges for recombination, with the objective of avoiding misleading information potentially provided by the maximum gradient. Experimental results that are conducted on three publicly available benchmark datasets demonstrate that MNEA significantly outperforms baseline methods in terms of performance. © 2024 Copyright held by the owner/author(s).

关键词： Generative adversarial networks

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：