检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Fu, Maixia Liu, Zhonghao Duan, Yule Zhou, Fei Li, Yinsheng Key Laboratory of Grain Information Processing and Control Ministry of Education Henan University of Technology Zhengzhou450001 China College of Information Science and Engineering Henan University of Technology Zhengzhou450001 China

The rapid advancement of terahertz(THz) technology has sparked significant interest in exploring tunable broadband functionaldevices. In this study, we propose an antisymmetric graphene skeletonized structure to achieve a terahertz double-perfect broadbandabsorber. This absorber consists of a gold (Au) substrate, a TOPAS dielectric layer, and C4 regular antisymmetric-patternedgraphene embedded in the polymer. It exhibits two unpolarized perfect absorbing broadbands through the resonance mechanisms oflocalized surface-isolated exciton resonance and electromagnetic dipole resonance. The results indicate high absorbance exceeding90% across two distinct frequency ranges of 0.93-2.03 THz and 4.16-5.3 THz. The dual-broadband absorption feature stems fromthe pronounced aggregation effect of the "Hollow-out corner" on the electric field, enabling modulation of the second Harmonicwhile leaving the first Harmonic largely unaffected. The absorber’s response can be dynamically tuned through adjusting the Fermienergy level and structural parameters of graphene. Our design opens up possibilities for diverse applications, in photodetectors,THz modulation, and stealth technologies. © 2024, The Authors. All rights reserved.

关键词： Graphene

来源：评论

学校读者我要写书评

暂无评论

Modality Unified Attack for Omni-Modality Person Re-Identification

引用

IEEE Transactions on information Forensics and Security 2025年 20卷 5577-5587页

作者： Bian, Yuan Liu, Min Yi, Yunqi Wang, Xueping Ma, Yunfeng Wang, Yaonan Hunan University National Engineering Research Center of Robot Visual Perception and Control Technology College of Electrical and Information Engineering Hunan Changsha China Hunan Normal University Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing College of Information Science and Engineering Hunan Changsha China

Deep learning based person re-identification (re-id) models have been widely employed in surveillance systems. Recent studies have demonstrated that black-box single-modality and cross-modality re-id models are vulnerable to adversarial examples (AEs), leaving the robustness of multi-modality re-id models unexplored. Due to the lack of knowledge about the specific type of model deployed in the target black-box surveillance system, we aim to generate modality unified AEs for omni-modality (single-, cross- and multi-modality) re-id models. Specifically, we propose a novel Modality Unified Attack method to train modality-specific adversarial generators to generate AEs that effectively attack different omni-modality models. A multi-modality model is adopted as the surrogate model, wherein the features of each modality are perturbed by metric disruption loss before fusion. To collapse the common features of omnimodality models, Cross Modality Simulated Disruption approach is introduced to mimic the cross-modality feature embeddings by intentionally feeding images to non-corresponding modality-specific subnetworks of the surrogate model. Moreover, Multi Modality Collaborative Disruption strategy is devised to facilitate the attacker to comprehensively corrupt the informative content of person images by leveraging a multi modality feature collaborative metric disruption loss. Extensive experiments show that our MUA method can effectively attack the omni-modality re-id models, achieving 55.9%, 24.4%, 49.0% and 62.7% mean mAP Drop Rate, respectively. © 2005-2012 IEEE.

关键词： Feature extraction Perturbation methods Measurement Generators Collaboration Robustness Identification of persons Data mining Closed box Training

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis for Small Samples Based on VMR

Fault Diagnosis for Small Samples Based on VMR

引用

Chinese Automation Congress (CAC)

作者： Xuejin Wu Yanghu Hu Yali Wu Department of Information and Control Engineering Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an University of Technology Xi'an China State Key Laboratory of Metal Extrusion and Forging Equipment Technology China National Heavy Machinery Research Institute Co. Ltd Xi'an China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

The scarcity of fault samples presents a significant challenge for fault diagnosis in industrial processes. Conventional methods often fail to deliver satisfactory results when dealing with small sample sizes. In addressing the issue of small sample fault diagnosis in industrial processes, this paper utilizes the Variational Mode Reconstruction(VMR) algorithm to screen the best components decomposed by the Variational Mode Decomposition(VMD) through the envelope entropy then random weighting them and signal reconstruction to achieve data enhancement, to enrich the sample size and to prevent the model overfitting phenomenon due to the scarcity of samples. Meanwhile, this paper integrates Convolutional Neural Network (CNN) and Long Short-term Memory Neural Network (LSTM) to propose a network model of spatio-temporal feature fusion for feature extraction and classification. The experiments demonstrate that this model not only enhances data diversity but also ensures consistency before and after enhancement, effectively mitigating overfitting. Furthermore, it guarantees high recognition and generalization rates in fault diagnosis.

关键词： Fault diagnosis Training Neural networks Rolling bearings Feature extraction Data models Signal reconstruction Convolutional neural networks Long short term memory Overfitting

来源：评论

学校读者我要写书评

暂无评论

On the Generalization of Machine-Learning-aided QoT Estimation in Optical Networks 32

On the Generalization of Machine-Learning-aided QoT Estimati...

引用

32nd Wireless and Optical Communications Conference, WOCC 2023

作者： Gao, Hanyu Zhang, Liang Zhang, Bin Chen, Xiaoliang Li, Zhaohui School of Electronics and Information Technology Sun Yat-sen University Guangdong Provincial Key Labratory of Optoelectronic Information Processing Chips and Systems Guangzhou China Southern Marine Science and Engineering Guangdong Laboratory Zhuhai China George Mason University Department of Electrical and Computer Engineering FairfaxVA22030 United States

ISBN: (纸本)9798350337150

This paper presents a composable machine learning method for generalizing the quality-of-transmission (QoT) metric estimation in optical networks. The composable machine learning approach characterizes this metric for lightpaths of arbitrary lengths by compositions of launch, propagation and readout modules. Results verify the feasibility of the design and show its successful application in facilitating autonomous lightpath provisioning. © 2023 IEEE.

关键词： Fiber optic networks

来源：评论

学校读者我要写书评

暂无评论

control of chaos in Frenkel-Kontorova model using reinforcement learning

引用

Chinese Physics B 2021年第5期30卷 247-254页

作者： You-Ming Lei Yan-Yan Han School of Mathematics and Statistics Northwestern Polytechnical UniversityXi'an 710072China Ministry of Industry and Information Technology(MIIT)Key Laboratory of Dynamics and Control of Complex Systems Northwestern Polytechnical UniversityXi'an 710072China

It is shown that we can control spatiotemporal chaos in the Frenkel-Kontorova(FK)model by a model-free control method based on reinforcement *** method uses Q-learning to find optimal control strategies based on the reward feedback from the environment that maximizes its *** optimal control strategies are recorded in a Q-table and then employed to implement *** advantage of the method is that it does not require an explicit knowledge of the system,target states,and unstable periodic *** that we need is the parameters that we are trying to control and an unknown simulation model that represents the interactive *** control the FK model,we employ the perturbation policy on two different kinds of parameters,i.e.,the pendulum lengths and the phase *** show that both of the two perturbation techniques,i.e.,changing the lengths and changing their phase angles,can suppress chaos in the system and make it create the periodic *** form of patterns depends on the initial values of the angular displacements and *** particular,we show that the pinning control strategy,which only changes a small number of lengths or phase angles,can be put into effect.

关键词： chaos control Frenkel-Kontorova model reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Fengyun-4 Geostationary Satellite-Based Solar Energy Nowcasting System and Its Application in North China

引用

Advances in Atmospheric Sciences 2022年第8期39卷 1316-1328页

作者： Chunlin HUANG Hongrong SHI Ling GAO Mengqi LIU Qixiang CHEN Disong FU Shu WANG Yuan YUAN Xiang′ao XIA Key Laboratory of Aerospace Thermophysics Ministry of Industry and Information TechnologyHarbin Institute of TechnologyHarbin 150001China Key Laboratory of Middle Atmosphere and Global Environment Observation Institute of Atmospheric PhysicsChinese Academy of SciencesBeijing 100029China Collaborative Innovation Center on Forecast and Evaluation of Meteorological Disasters Nanjing University of Information Science&TechnologyNanjing 210044China National Satellite Meteorological Center China Meteorological AdministrationBeijing 100192China Key Laboratory of Atmospheric Sounding Chengdu University of Information TechnologyChengdu 610225China State Key Laboratory of Operation and Control of Renewable Energy&Storage Systems China Electric Power Research Institute(CEPRI)Beijing 100192China Key Laboratory of Cloud-Precipitation Physics and Severe Storms Institute of Atmospheric PhysicsChinese Academy of SciencesBeijing 100029China

Surface solar irradiance(SSI)nowcasting(0-3 h)is an effective way to overcome the intermittency of solar energy and to ensure the safe operation of grid-connected solar power *** this study,an SSI estimate and nowcasting system was established using the near-infrared channel of Fengyun-4A(FY-4A)geostationary *** system is composed of two key components:The first is a hybrid SSI estimation method combining a physical clear-sky model and an empirical cloudy-sky *** second component is the SSI nowcasting model,the core of which is the derivation of the cloud motion vector(CMV)using the block-matching *** goal of simultaneous estimation and nowcasting of global horizontal irradiance(GHI)and direct normal irradiance(DNI)is *** system was evaluated under different sky conditions using SSI measurements at Xianghe,a radiation station in the North China *** results show that the accuracy of GHI estimation is higher than that of DNI estimation,with a normalized root-mean-square error(nRMSE)of 22.4%relative to 45.4%.The nRMSE of forecasting GHI and DNI at 30-180 min ahead varied within 25.1%-30.8%and 48.1%-53.4%,*** discrepancy of SSI estimation depends on cloud occurrence frequency and shows a seasonal pattern,being lower in spring-summer and higher in *** FY-4A has great potential in supporting SSI nowcasting,which promotes the development of photovoltaic energy and the reduction of carbon emissions in *** system can be improved further if calibration of the empirical method is improved.

关键词： Fengyun-4A surface solar irradiance estimates and forecasting cloud motion block-matching

来源：评论

学校读者我要写书评

暂无评论

Transfer learning with a spatiotemporal graph convolution network for city flowprediction

引用

Frontiers of information Technology & Electronic Engineering 2025年第1期26卷 79-92页

作者： Binkun LIU Yu KANG Yang CAO Yunbo ZHAO Zhenyi XU Department of Automation University of Science and Technology of ChinaHefei 230026China Key Laboratory of System Control and Information Processing Ministry of EducationShanghai 200240China Institute of Artificial Intelligence Hefei Comprehensive National Science CenterHefei 230088China Institute of Advanced Technology University of Science and Technology of ChinaHefei 230088China

Recently,deep learning based city flow prediction has been extensively used in the establishment of *** methods are data-hungry,making them unscalable to areas lacking *** transfer learningcan use data-rich source domains to assist target domain cities in city flow prediction,the performance of existingmethods cannot meet the needs of actual use,because the long-distance road network connectivity is *** this problem,we propose a transfer learning method based on spatiotemporal graph convolution,in which weconstruct a co-occurrence space between the source and target domains,and then align the mapping of the sourceand target domains’data in this space,to achieve the transfer learning of the source city flow prediction modelon the target ***,a dynamic spatiotemporal graph convolution module along with a temporalencoder is devised to simultaneously capture the concurrent spatiotemporal features,which implies the inherentrelationship among the road network structures,human travel habits,and city bike ***,these concurrentfeatures are leveraged as cross-city invariant representations and nonlinearly spanned to a co-occurrence *** domain features are thereby aligned with the source domain features in the co-occurrence space by using aMahalanobis distance loss,to achieve cross-city bike flow *** proposed method is evaluated on the publicbike flow datasets in Chicago,New York,and Washington in 2015,and significantly outperforms state-of-the-arttechniques.

关键词： Transfer learning City flow prediction Spatiotemporal graph convolution

来源：评论

学校读者我要写书评

暂无评论

LSU-NET: Lightweight Automatic Organs Segmentation Network for Medical Images

LSU-NET: Lightweight Automatic Organs Segmentation Network f...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Yujie Ding Shenghua Teng Zuoyong Li Xiao Chen College of Electronic and Information Engineering Shandong University of Science and Technology Qingdao China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control School of Computer and Big Data Minjiang University Fuzhou China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

UNet and its variants have widespread applications in medical image segmentation. However, the substantial number of parameters and computational complexity of these models make them less suitable for use in clinical settings with limited computational resources. To address this limitation, we propose a novel Lightweight Shift U-Net (LSU-Net). We integrate the Light Conv Block and the Tokenized Shift Block in a lightweight manner, combining them with a dynamic weight multi-loss design for efficient dynamic weight allocation. The Light Conv Block effectively captures features with a low parameter count by combining standard convolutions with depthwise separable convolutions. The Tokenized Shift Block optimizes feature representation by shifting and capturing deep features through a combination of the Spatial Shift Block and depthwise separable convolutions. Dynamic adjustment of the loss weights at each layer approaches the optimal solution and enhances training stability. We validated LSU-Net on the UWMGI and MSD Colon datasets, and experimental results demonstrate that LSU-Net outperforms most state-of-the-art segmentation architectures.

关键词： Training Image segmentation Convolution Dynamic scheduling Stability analysis Resource management Speech processing Standards Monitoring Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

A Sub-array MIMO Radar Waveform Design with Wide Pulse Compression Main-lobe

A Sub-array MIMO Radar Waveform Design with Wide Pulse Compr...

引用

IEEE International Conference on Radar

作者： Xiaohe Du Shenghua Zhou Mengchen Zhang National Key Laboratory of Radar Signal Processing Xidian University Xi’an China Academy of Space Information Systems Xi’an China

Existing multiple-input multiple-output radar wave-form optimization works focus on full-digital radar, which is only a small part of existing radar system. Sub-array MIMO radar, in which sub-array antennas operate in the phased-array mode and different sub-array transmit differen waveforms, is more practical in some real applications. This paper studies a sub-array MIMO radar waveform optimization method. A waveform optimization criterion is presented to suppresses range compression sidelobes, mutual correlation sidelobes for differernt spatial regions, and the mismatch from a desired transmit beampattern. The sequential quadratic programming (SQP) algorithm is used to solve the optimization problem. Numerical results indicate that this method can efficiently control the distribution of signal energy in space and to suppress auto and mutual correlation sidelobes of angular waveforms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Aβ-Aggregation-Generated Blue Autofluorescence Illuminates Senile Plaques as well as Complex Blood and Vascular Pathologies in Alzheimer’s Disease

引用

Neuroscience Bulletin 2024年第8期40卷 1115-1126页

作者： Hualin Fu Jilong Li Chunlei Zhang Peng Du Guo Gao Qiqi Ge Xinping Guan Daxiang Cui Institute of Nano Biomedicine and Engineering School of Sensing Science and EngineeringSchool of Electronic Information and Electrical EngineeringShanghai Jiao Tong UniversityShanghai 200240China Institute of Marine Equipment Shanghai Jiao Tong UniversityShanghai 200240China National Center for Translational Medicine Shanghai Jiao Tong UniversityShanghai 200240China Department of Colorectal Surgery School of MedicineXinhua HospitalShanghai Jiao Tong UniversityShanghai 200092China Department of Automation Shanghai Jiao Tong UniversityShanghai 200240China The Key Laboratory of System Control and Information Processing Ministry of EducationShanghai 200240China

Senile plaque blue autofluorescence was discovered around 40 years ago,however,its impact on Alzheimer’s disease(AD)pathology has not been fully *** analyzed senile plaques with immunohistochemistry and fluorescence imaging on AD brain sections and also Aβ aggregation in *** DAPI or Hoechst staining,the nuclear blue fluorescence could only be correctly assigned after subtracting the blue plaque *** flower-like structures wrapping dense-core blue fluorescence formed by cathepsin D staining could not be considered central-nucleated neurons with defective lysosomes since there was no nuclear staining in the plaque core when the blue autofluorescence was *** Aβ self-oligomers and Aβ/hemoglobin heterocomplexes generated blue *** Aβ amyloid blue autofluorescence not only labels senile plaques but also illustrates red cell aggregation,hemolysis,cerebral amyloid angiopathy,vascular plaques,vascular adhesions,and *** summary,we conclude that Aβ-aggregation-generated blue autofluorescence is an excellent multi-amyloidosis marker in Alzheimer’s disease.

关键词： Senile plaque Blue autofluorescence Aβ Amyloid aggregation Hemoglobin Cathepsin D.Microaneurysm Alzheimer's disease

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：