检索结果-内蒙古大学图书馆

Dynamic Spectrum Anti-Jamming with Distributed Learning and Transfer Learning

China Communications 2023年第12期20卷 52-65页

作者： Xinyu Zhu Yang Huang Delong Liu Qihui Wu Xiaohu Ge Yuan Liu Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space Ministry of Industry and Information TechnologyNanjing University of Aeronautics and AstronauticsNanjing 210016China The 723 Institute of CSSC Yangzhou 225001China School of Electronic Information and Communications Huazhong University of Science and TechnologyWuhan 430074China School of Electronic and Information Engineering South China University of TechnologyGuangzhou 510641China

Physical-layer security issues in wireless systems have attracted great *** this paper,we investigate the spectrum anti-jamming(AJ)problem for data transmissions between *** fast-changing physical-layer jamming attacks in the time/frequency domain,frequency resources have to be configured for devices in advance with unknown jamming patterns(*** time-frequency distribution of the jamming signals)to avoid jamming signals emitted by malicious *** process can be formulated as a Markov decision process and solved by reinforcement learning(RL).Unfortunately,stateof-the-art RL methods may put pressure on the system which has limited computing *** a result,we propose a novel RL,by integrating the asynchronous advantage actor-critic(A3C)approach with the kernel method to learn a flexible frequency pre-configuration ***,in the presence of time-varying jamming patterns,the traditional AJ strategy can not adapt to the dynamic interference *** handle this issue,we design a kernelbased feature transfer learning method to adjust the structure of the policy function *** results reveal that our proposed approach can significantly outperform various baselines,in terms of the average normalized throughput and the convergence speed of policy learning.

关键词： A3C anti-jamming reinforcement learning spectrum transfer learning wireless system

来源：评论

学校读者我要写书评

暂无评论

Acronym Identification Based on SpanBERT-CRF 3

Acronym Identification Based on SpanBERT-CRF

引用

3rd International Conference on Artificial Intelligence and Electromechanical Automation, AIEA 2022

作者： Ou, Lizhen Luo, Xueshan Li, Xinmeng Chen, Peipei Science and Technology on Information System Engineering Laboratory National University of Defense Technology Changsha China

ISBN: (纸本)9781510657281

Acronym Identification means to recognizing acronyms and their definitions in a given paragraph by an algorithm. Existing studies have shown that the pre-training model has significant performance advantages in acronyms recognition. However, the vanilla Bert measures randomly masking tokens in the pre-training, which may also abbreviate the token of acronyms in sentence. The continuous masking method will be more helpful to the recognition and interpretation of acronyms. In this paper, we propose to use the SpanBERT model for acronym recognition and obtaining the transfer relationship between indicators with the help of a conditional random field (CRF). Through experimental comparison, the results demonstrate that our method increases the F1 value compared with the Bert and BERT-CRF models. © 2022 SPIE.

关键词： Random processes

来源：评论

学校读者我要写书评

暂无评论

Lensless imaging through the Fourier-ADMM network with a cost-effective and easily fabricated phase mask

引用

Optics Letters 2025年第3期50卷 758-761页

作者： Xiong, Zhencong He, Wenjun Chen, Yijie Xu, Yifei Wang, Wenbo Fu, Yuegang School of Opto-Electronic Engineering Changchun University of Science and Technology Changchun130022 China Changchun University of Science and Technology Key Laboratory of Opto-Electric Measurement and Optical Information Transmission Technology Ministry of Education Changchun130012 China

In this Letter, we introduce the Fourier-ADMM (alternating direction method of multipliers) network, improving the Fourier-ADMM algorithm by integrating it with an additional backpropagation process. Simultaneously, we develop a cost-effective and easily fabricated phase mask for lensless imaging systems. While the simplified phase mask may challenge the image quality for its faults such as low contrast and a suboptimal signal-to-noise ratio, the capabilities of the Fourier-ADMM network effectively mitigate these issues. The fabrication of the phase mask requires inexpensive and readily available raw materials and tools, and the process itself does not necessitate any highly specialized or precision operations. Our experimental results demonstrate that, with the backing of this advanced decoding network, the camera equipped with the simplified phase mask is capable of delivering high-quality imaging and rapid response times. © 2025 Optica Publishing Group. All rights, including for text and data mining (TDM), Artificial Intelligence (AI) training, and similar technologies, are reserved.

关键词： Masks

来源：评论

学校读者我要写书评

暂无评论

Anti-corrosive and highly reversible zinc metal anode enabled by the phenolic resin coating

引用

Rare Metals 2024年第5期43卷 2115-2124页

作者： Ya-Ping Wang Ya-Di Yang Shu-Qi Duan Li Wang Jia-Shuo Guo An-Qiang Pan School of Materials Science and Engineering Hebei University of TechnologyTianjin 300130China Key Laboratory of Special Functional Materials for Ecological Environment and Information(Hebei University of Technology).Ministry of Education Tianjin 300130China Key Laboratory for New Type of Functional Materials in Hebei Province Hebei University of TechnologyTianjin 300130China School of Materials Science and Engineering Central South UniversityChangsha 410083China

Aqueous zinc-ion batteries have attracted much attention due to their high theoretical capacity,low cost high safety,and ***,challenges such as dendrite growth and side reactions severely hinder the electrochemical performance of the Zn anode,leading to low Coulombic efficiency(CE)or even short circuits Herein,phenolic resin(PF)is used as a protective coating on the surface of the zinc metal *** PF layer can greatly improve the corrosion resistance of the Zn electrode in the ***,this artificial electrode/electrolyte interphase also elevates the nucleation barrier and restrains Zn^(2+)2D diffusion,regulating the zinc deposition/dissolution *** a result,PF@Zn symmetric cells exhibit superior performance than that of bare Zn symmetric cells,achieving a stable and dendrite-free cycle of 1400 ***,the carbon nanotube MnO_(2)||PF@Zn(CNT/MnO_(2)||PF@Zn)full cell also delivers a long cycle life with a high-capacity retention of about 180.0 m Ah·g^(-1)after 1400 cycles,far exceeding that of bare Zn *** work provides a facile strategy for achieving a dendrite-free and rechargeable zinc anode.

关键词： Rechargeable aqueous batteries Zn metal anode Phenolic resin Anti-corrosion

来源：评论

学校读者我要写书评

暂无评论

Template synthesis of copper azide primary explosive through Cu2O@HKUST-1 core-shell composite prepared by “bottle around ship” method

引用

Defence technology（防务技术） 2023年第7期25卷 99-111页

作者： Xu-wen Liu Yan Hu Jia-heng Hu Jia-xin Su Cai-min Yang Ying-hua Ye Rui-qi Shen School of Chemistry and Chemical Engineering Nanjing University of Science and TechnologyNanjing210094China Micro-Nano Energetic Devices Key Laboratory Ministry of Industry and Information TechnologyNanjing210094China

Copper azide(CA), as a primary explosive with high energy density, has not been practically used so far because of its high electrostatic sensitivity. The Cu2O@HKUST-1 core-shell structure hybrid material was synthesized by the “bottle around ship” methodology in this research by regulating the dissolution rate of Cu2O and the generation rate of metal-organic framework(MOF) materials. Cu2O@HKUST-1 was carbonized to form a Cu O@porous carbon(CuO@PC) composite material. CuO@PC was synthesized into a copper azide(CA) @PC composite energetic material through a gas-solid phase in-situ azidation *** is encapsulated in PC framework, which acts as a nanoscale Faraday cage, and its excellent electrical conductivity prevents electrostatic charges from accumulating on the energetic material’s surface. The CA@PC composite energetic material has a CA content of 89.6%, and its electrostatic safety is nearly 30times that of pure CA(1.47 mJ compared to 0.05 mJ). CA@PC delivers an outstanding balance of safety and energy density compared to similar materials.

关键词： Composite energetic materials Copper azide Carbonization Template method Core-shell composite Electrostatic safety

来源：评论

学校读者我要写书评

暂无评论

Multivariable identification of membrane fouling based on compacted cascade neural network

引用

Chinese Journal of Chemical engineering 2023年第1期53卷 37-45页

作者： Kun Ren Zheng Jiao Xiaolong Wu Honggui Han Faculty of Information Technology Beijing University of TechnologyBeijing 100124China Engineering Research Center of Digital Community Ministry of EducationBeijing 100124China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing 100124China

The membrane fouling phenomenon,reflected with various fouling characterization in the membrane bioreactor(MBR)process,is so complicated to *** paper proposes a multivariable identification model(MIM)based on a compacted cascade neural network to identify membrane fouling ***,a multivariable model is proposed to calculate multiple indicators of membrane fouling using a cascade neural network,which could avoid the interference of the overlap ***,an unsupervised pretraining algorithm was developed with periodic information of membrane fouling to obtain the compact structure of ***,a hierarchical learning algorithm was proposed to update the parameters of MIM for improving the identification accuracy ***,the proposed model was tested in real plants to evaluate its efficiency and *** results have verified the benefits of the proposed method.

关键词： Membrane fouling Permeability Cascade neural networks Model Prediction

来源：评论

学校读者我要写书评

暂无评论

Anti-Jamming Null Space Projection Beamforming Based on Symbiotic Radio

引用

Computer Modeling in engineering & sciences 2024年第1期138卷 679-689页

作者： Baofeng Ji Yifan Liu Tingpeng Li Ling Xing Weixing Wang Shahid Mumtaz Xiaolong Shang Wanying Liu Congzheng Han State Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System(CEMEE) Luoyang471000China Research and Innovation Center of Intelligent System Longmen LaboratoryLuoyang471000China College of Information Engineering Henan University of Science and TechnologyLuoyang471000China Institute of Atmospheric Physics Chinese Academy of Sciences(LAGEO)Beijing100000China Instituto de Telecomunicaes Aveiro3800-005Portugal Chinese Academy of Agricultural Mechanization Sciences Beijing100000China

With the development of information technology,more and more devices are connected to the Internet through wireless communication to complete data *** to the broadcast characteristics ofwireless channels,wireless networks have suffered more and more malicious *** layer security has received extensive attention from industry and *** is considered to be one of the most important technologies related to physical layer *** beamforming technology,messages can be transmitted to legitimate users in an offset direction that is as orthogonal as possible to the interference channel to ensure the reception SINR by legitimate *** the symbiotic radio(SR)technology,this paper considers a symbiotic radio antijamming MIMO system equipped with a multi-antenna system at the main base *** order to avoid the interference signal and improve the SINR of the signal received by the *** base station is equipped with a uniform rectangular antenna array,and using Null Space Projection(NSP)Beamforming,Intelligent Reflecting Surface(IRS)can assist in changing the beam’s *** simulation results show that NSP Beamforming could make a better use of the null space of interference,which can effectively improve the received SINR of users under directional interference,and improve the utilization efficiency of signal energy.

关键词： Symbiotic radio anti-jamming MIMO NSP Beamforming physical layer security

来源：评论

学校读者我要写书评

暂无评论

Interval analysis for neural networks with application to fault detection

引用

science China(information sciences) 2024年第11期67卷 222-237页

作者： Zhenhua WANG Youdao MA Song ZHU Thach Ngoc DINH Yi SHEN Department of Control Science and Engineering Harbin Institute of Technology National Key Laboratory of Complex System Control and Intelligent Agent Cooperation School of Mathematics China University of Mining and Technology The CEDRIC-Lab Conservatoire National des Arts et Métiers (CNAM)

This paper investigates an interval analysis method for neural networks and applies it to fault detection for systems with unknown but bounded measurement noise. First, a novel interval analysis method is presented, which can compute the bounds of the output of a feedforward neural network subject to a bounded input. By applying the proposed interval analysis method to a network trained with fault-free system data, adaptive thresholds for fault detection are computed. Finally, one can acquire fault detection results via a fault detection strategy. The proposed method can achieve tight bounds of the network output and employ simple operations, which leads to accurate fault detection results and a low computational burden.A numerical simulation and an experiment on an AC servo motor are given to illustrate the effectiveness and superiority of the proposed method.

关键词： interval analysis feedforward neural network fault detection adaptive thresholds

来源：评论

学校读者我要写书评

暂无评论

RESEARCH ON GAIT RECOGNITION BY USING 1DCNN BASED ON LOWER LIMB KINEMATIC POSTURE DATA 10

RESEARCH ON GAIT RECOGNITION BY USING 1DCNN BASED ON LOWER L...

引用

10th International Symposium on Test Automation and Instrumentation, ISTAI 2024

作者： Li, Mu Ma, Chao Wang, Shaohong Key Laboratory of Modern Measurement and Control Technology Ministry of Edu. Beijing Information Science and Technology University Beijing China Beijing Key Laboratory of Measurement and Control of Mechanical and Electrical System Beijing Information Science and Technology University Beijing China

ISBN: (纸本)9781837242672

Gait recognition refers to the process of realizing the detection of human identity or health status and other information according to the characteristics of human plantar pressure, video images or human dynamics indicators. With the advantages of non-contact, non-aggression, no need for cooperation and easy to collect, gait recognition technology has been widely used in recent years in the field of public security criminal investigation, medical care, intelligent transportation and other fields. In this study, to meet the needs of gait recognition, IMU sensors are used to acquire human lower limb motion posture data and wavelet transform is used to decompose several components. Then the components were determined and the optimized 1DCNN model is used to carry out gait recognition research. The results showed that the optimized 1DCNN model for gait recognition task exhibits excellent performance with up to 95% accuracy, 96% recall and Fl value, as well as good computational efficiency, which is valuable for clinical automatic gait recognition analysis, rehabilitation engineering and criminal investigation work. Although there are some errors in some gait classifications, our study provides directions for further optimization of the algorithm to improve the accuracy and robustness of gait recognition. © The Institution of engineering & technology 2024.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

ADA: An Acronym-Based Data Augmentation Method for Low-Resource Text Classification 10th

ADA: An Acronym-Based Data Augmentation Method for Low-Resou...

引用

10th China Conference on Command and Control, C2 2022

作者： Ou, Lizhen Chen, Honghui Luo, Xueshan Li, Xinmeng Chen, Siya Science and Technology on Information System Engineering Laboratory National University of Defence Technology Changsha China

ISBN: (纸本)9789811960512

Text classification is an essential part of natural language processing. With the development of deep learning technology, using deep learning for text classification has become mainstream. However, deep learning methods often require a considerable quantity of data, and collecting and processing data sets is cumbersome and expensive. This paper presents a data enhancement method simulating the generation of acronyms, quickly expanding the text classification datasets. We show the performance of our method on three classical data sets and compare it with two classical text data enhancement methods. The results show that this method can effectively improve the effect of text classification. Meanwhile, by comparing the similarity with the original sentence, it is found that our method has very little change in sentence semantics and is more robust than the baseline method. © 2022, Chinese Institute of Command and Control.

关键词： Semantics

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：