检索结果-南通市图书馆

Contrastive Clustering for Unsupervised Recognition of Interference Signals

在线全文

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2023年第8期46卷 1385-1400页

作者： Xiangwei Chen Zhijin Zhao Xueyi Ye Shilian Zheng caiyi lou Xiaoniu Yang The School of Communication Engineering Hangzhou Dianzi UniversityHangzhou310018China The Science and Technology on Communication Information Security Control Laboratory Jiaxing314001China

Interference signals recognition plays an important role in anti-jamming *** the development of deep learning,many supervised interference signals recognition algorithms based on deep learning have emerged recently and show better performance than traditional recognition ***,there is no unsupervised interference signals recognition algorithm at *** this paper,an unsupervised interference signals recognition method called double phases and double dimensions contrastive clustering(DDCC)is ***,in the first phase,four data augmentation strategies for interference signals are used in data-augmentation-based(DA-based)contrastive *** the second phase,the original dataset’s k-nearest neighbor set(KNNset)is designed in double dimensions contrastive *** addition,a dynamic entropy parameter strategy is *** simulation experiments of 9 types of interference signals show that random cropping is the best one of the four data augmentation strategies;the feature dimensional contrastive learning in the second phase can improve the clustering purity;the dynamic entropy parameter strategy can improve the stability of DDCC *** unsupervised interference signals recognition results of DDCC and five other deep clustering algorithms show that the clustering performance of DDCC is superior to other *** particular,the clustering purity of our method is above 92%,SCAN’s is 81%,and the other three methods’are below 71%when jammingnoise-ratio(JNR)is−5 *** addition,our method is close to the supervised learning algorithm.

关键词： Interference signals recognition unsupervised clustering contrastive learning deep learning k-nearest neighbor

Primary User Adversarial Attacks on Deep Learning-Based Spectrum Sensing and the Defense Method

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

China Communications 2021年第12期18卷 94-107页

作者： Shilian Zheng Linhui Ye Xuanye Wang Jinyin Chen Huaji Zhou caiyi lou Zhijin Zhao Xiaoniu Yang Science and Technology on Communication Information Security Control Laboratory Jiaxing314000China College of Information Engineering Zhejiang University of TechnologyHangzhou310012China Institute of Cyberspace Security Zhejiang University of TechnologyHangzhou310012China School of Communication Engineering Hangzhou Dianzi UniversityHangzhou310018China

The spectrum sensing model based on deep learning has achieved satisfying detection per-formence,but its robustness has not been *** this paper,we propose primary user adversarial attack(PUAA)to verify the robustness of the deep learning based spectrum sensing *** adds a care-fully manufactured perturbation to the benign primary user signal,which greatly reduces the probability of detection of the spectrum sensing *** design three PUAA methods in black box *** or-der to defend against PUAA,we propose a defense method based on autoencoder named *** apply the long short-term memory network and the convolutional neural network together to DeepFilter,so that it can extract the temporal and local features of the input signal at the same time to achieve effective *** experiments are conducted to eval-uate the attack effect of the designed PUAA method and the defense effect of *** show that the three PUAA methods designed can greatly reduce the probability of detection of the deep learning-based spectrum sensing *** addition,the experimen-tal results of the defense effect of DeepFilter show that DeepFilter can effectively defend against PUAA with-out affecting the detection performance of the model.

关键词： spectrum sensing cognitive radio deep learning adversarial attack autoencoder defense

Insight into the Dual Cycle Mechanism of Methanol-to-OIefins Reaction over SAPO-34 Molecular Sieve by Isotopic Tracer Studies

在线全文

学校读者我要写书评

暂无评论

Chemical Research in Chinese Universities 2020年第6期36卷 1203-1208页

作者： YU Bowen lou caiyi ZHANG Wenna XU Shutao HAN Jingfeng YU Zhengxi WEI Yingxu LIU Zhongmin National Engineering Laboratory for Methanol to Olefins Dalian National Laboratory for Clean EnergyiChEM(Collaborative Innovation Center of Chemistry for Energy Materials)Dalian Institute of Chemical PhysicsChinese Academy of SciencesDalian 116023P.R.China University of Chinese Academy of Sciences Beijing 100039P.R.China

Methanol-to-olefins(MTO)reaction is one of the important non-petroleum routes to produce light olefinsover acidic molecular *** this study,the complete reaction course of MTO on SAPO-34 molecular sieve with retained organics evolution from induction period to deactivation period was investigated systematically at different weight hourly space velocities(WHSV)of *** the aid of 12C/3C-methanol isotopic switch experiment,the dual cycle mechanism involving aromatics-based cycle and alkenes-based cycle was evaluated during the whole reac-tion *** detailed reaction route varied with the evolution of the retained organics in the catalyst at different reaction *** aromatics-based cycle and alkenes-based cycle alternately dominate the reaction *** the efficient reaction period,aromatics-based cvcle is the main reaction mechanism,while in the induction and deactiva-tion *** contribution of alkenes-based cvcle mechanism will become more important.

关键词： SAPO-34 Methanol-to-olefin(MTO) Polymethy Ibenzene Dual-cycle mechanism Isotopic tracer

Benzene alkylation with methanol over phosphate modified hierarchical porous ZSM-5 with tailored acidity

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Chemical Engineering 2017年第9期25卷 1187-1194页

作者： Jinghui Lyu Hualei Hu Carolyn Tait Jiayao Rui caiyi lou Qingtao Wang Wenwen Han Qunfeng Zhang Zhiyan Pan Xiaonian Li Industrial Catalysis Institute of Zhejiang University of Technology State Key Laboratory Breeding Base of Green Chemistry Synthesis Technology Department of Environmental Engineering Zhejiang University of Technology Department of Chemical and Biochemical Engineering University of Western Ontario

The acidity and acid distribution of hierarchical porous ZSM-5 were tailored via phosphate modification. The catalytic results showed that both benzene conversion and selectivity of toluene and xylene increased with the presence of appropriate amount of phosphorus. Meanwhile, side reactions such as methanol to olefins related with the formation of by-product ethylbenzene formation and isomerization of xylene to meta-xylene were suppressed efficiently. The acid strength and sites amount of Br?nsted acid of the catalyst were crucial for improving benzene conversion and yield of xylene, whereas passivation of external surface acid sites played an important role in breaking thermodynamic equilibrium distribution of xylene isomers.

关键词： Hierarchical porous ZSM-5 Phosphate modification Benzene alkylation with methanol Xylene

星载测向系统的测向误差及其定位误差计算方法

在线全文

学校读者我要写书评

暂无评论

宇航学报 2024年第9期45卷 1488-1497页

作者：黄凯尤明懿陆安南楼财义电磁空间安全全国重点实验室嘉兴314033 中国电子科技集团公司第三十六研究所嘉兴314033

针对星载测向系统可通过单次测向实现对地面/海面辐射源瞬时定位的特点,基于星载测向系统的定位模型,推导任意二维阵型的相位干涉仪测向误差表达式。分别从方位角与俯仰角以及空间夹角详细推导了单星测向定位误差公式,并结合球面约束推... 详细信息

针对星载测向系统可通过单次测向实现对地面/海面辐射源瞬时定位的特点,基于星载测向系统的定位模型,推导任意二维阵型的相位干涉仪测向误差表达式。分别从方位角与俯仰角以及空间夹角详细推导了单星测向定位误差公式,并结合球面约束推导单星直接定位的误差表达式。数值仿真表明,基于测向角度的定位误差计算方法结果逼近理论误差值,从而可基于任意二维测向阵型,快速评估卫星观测区域内的测向误差及其定位误差,而单星直接定位相较于测向定位,定位误差显著降低。

关键词：星载测向系统测向误差定位误差单星直接定位

面向通信信号调制识别的半监督生成对抗网络框架

在线全文

学校读者我要写书评

暂无评论

国防科技大学学报 2023年第6期45卷 78-83页

作者：周华吉徐杰郑仕链沈伟国王巍楼财义电磁空间安全全国重点实验室浙江嘉兴314033 西安电子科技大学人工智能学院陕西西安710071

针对只有少量标签数据的弱监督条件下现有调制信号识别模型准确率较低的问题,提出基于生成对抗网络的半监督学习框架。该方法通过对通信信号进行冗余空域变换,使其在适应生成对抗网络模型的同时保留丰富的信号相邻特征;通过梯度惩罚Wass... 详细信息

针对只有少量标签数据的弱监督条件下现有调制信号识别模型准确率较低的问题,提出基于生成对抗网络的半监督学习框架。该方法通过对通信信号进行冗余空域变换,使其在适应生成对抗网络模型的同时保留丰富的信号相邻特征;通过梯度惩罚Wasserstein生成对抗网络的引入,构建适宜电磁信号处理的半监督学习框架,实现对无标签信号样本的有效利用。为了验证所提算法的有效性,在RADIOML 2016.04C数据集上进行测试。实验结果表明,该方法在半监督条件下能训练出高效的分类器,获得优异的调制识别结果。

关键词：生成对抗网络半监督学习框架通信信号调制识别

Multi-component decompositions, linear superpositions, and new nonlinear integrable coupled KdV-type systems

在线全文

学校读者我要写书评

暂无评论

Communications in Theoretical Physics 2025年第2期77卷 3-14页

作者： Xiazhi Hao S Y lou School of Mathematical Science Zhejiang University of Technology School of Physical Science and Technology Ningbo University

In the realm of nonlinear integrable systems, the presence of decompositions facilitates the establishment of linear superposition solutions and the derivation of novel coupled systems exhibiting nonlinear integrability. By focusing on single-component decompositions within the potential BKP hierarchy, it has been observed that specific linear superpositions of decomposition solutions remain consistent with the underlying equations. Moreover, through the implementation of multi-component decompositions within the potential BKP hierarchy,successful endeavors have been undertaken to formulate linear superposition solutions and novel coupled Kd V-type systems that resist decoupling via alterations in dependent variables.

关键词： integrable system single-component decomposition multi-component decomposition linear superposition integrable coupled KdV-type system

Multi-interface structure design of bamboo-based carbon/Co/CoO composite electromagnetic wave absorber based on biomimetic honeycomb-shaped superstructure

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

International Journal of Minerals,Metallurgy and Materials 2025年第3期32卷 631-644页

作者： Yanting Wang He Han Huiyang Bian Yanjun Li Zhichao lou Jiangsu Co-Innovation Center of Efficient Processing and Utilization of Forest Resources College of Materials Science and EngineeringNanjing Forestry UniversityNanjing 210037China College of Light Industry and Food Engineering Nanjing Forestry UniversityNanjing 210037China

The rapid development of 5G communication technology and smart electronic and electrical equipment will inevitably lead to electromagnetic radiation *** heterointerface polarization relaxation through nanostructure design and interface modifica-tion has proven to be an effective strategy to obtain efficient electromagnetic wave ***,this work implements an innovative method that combines biomimetic honeycomb superstructure to constrain hierarchical porous heterostructure composed of Co/CoO nano-particles to improve the interfacial polarization *** method effectively controlled the absorption efficiency of Co^(2+)through de-lignification modification of bamboo,and combined with the bionic carbon-based natural hierarchical porous structure to achieve uniform dispersion of nanoparticles,which is conducive to the in-depth construction of heterogeneous *** addition,the multiphase struc-ture brought about by high-temperature pyrolysis provides the best dielectric loss and impedance matching for the ***,the obtained bamboo-based Co/CoO multiphase composite showed excellent electromagnetic wave absorption performance,achieving excel-lent reflection loss(RL)of-79 dB and effective absorption band width of 4.12 GHz(6.84-10.96 GHz)at low load of 15wt%.Among them,the material’s optimal radar cross-section(RCS)reduction value can reach 31.9 dB·m^(2).This work provides a new approach to the micro-control and comprehensive optimization of macro-design of microwave absorbers,and offers new ideas for the high-value utiliza-tion of biomass materials.

关键词： biomass honeycomb porous heterojunction structure interfacial polarization electromagnetic wave absorption

Study of the Transport Behavior of Multispherical Proppant in Intersecting Fracture Based on Discrete Element Method

在线全文

学校读者我要写书评

暂无评论

Energy Engineering 2025年第1期122卷 185-201页

作者： Chengyong Peng JianshuWu Mao Jiang Biao Yin Yishan lou CNOOC Research Institute Company Limited Beijing100028China School of Petroleum Engineering Yangtze UniversityWuhan430100China Hubei Key Laboratory of Oil and Gas Drilling and Production Engineering(Yangtze University) Wuhan430100China

To analyze the differences in the transport and distribution of different types of proppants and to address issues such as the short effective support of proppant and poor placement in hydraulically intersecting fractures,this study considered the combined impact of geological-engineering factors on *** reservoir production parameters and the discrete elementmethod,multispherical proppants were ***,a 3D fracture model,based on the specified conditions of the L block,employed coupled(Computational Fluid Dynamics)CFD-DEM(Discrete ElementMethod)for joint simulations to quantitatively analyze the transport and placement patterns of multispherical proppants in intersecting *** indicate that turbulent kinetic energy is an intrinsic factor affecting proppant ***,the efficiency of placement and migration distance of low-sphericity quartz sand constructed by the DEM in the main fracture are significantly reduced compared to spherical ceramic proppants,with a 27.7%decrease in the volume fraction of the fracture surface,subsequently affecting the placement concentration and damaging fracture *** to small-angle fractures,controlling artificial and natural fractures to expand at angles of 45°to 60°increases the effective support length by approximately 20.6%.During hydraulic fracturing of gas wells,ensuring the fracture support area and post-closure conductivity can be achieved by controlling the sphericity of proppants and adjusting the perforation direction to control the direction of artificial fractures.

关键词： Hydraulic fracturing discrete element method proppant sphericity CFD-DEM