检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Rathgeb, Christian Kolberg, Jascha Uhl, Andreas Busch, Christoph Da/sec – Biometrics and Internet Security Research Group Hochschule Darmstadt Germany WaveLab – Multimedia Signal Processing and Security Lab Universität Salzburg Austria Norwegian Biometrics Laboratory Norwegian University of Science and Technology Norway

Today, deep learning represents the most popular and successful form of machine learning. Deep learning has revolutionised the field of pattern recognition, including biometric recognition. Biometric systems utilising deep learning have been shown to achieve auspicious recognition accuracy, surpassing human performance. Apart from said breakthrough advances in terms of biometric performance, the use of deep learning was reported to impact different covariates of biometrics such as algorithmic fairness, vulnerability to attacks, or template protection. Technologies of biometric template protection are designed to enable a secure and privacy-preserving deployment of biometrics. In the recent past, deep learning techniques have been frequently applied in biometric template protection systems for various purposes. This work provides an overview of how advances in deep learning take influence on the field of biometric template protection. The interrelation between improved biometric performance rates and security in biometric template protection is elaborated. Further, the use of deep learning for obtaining feature representations that are suitable for biometric template protection is discussed. Novel methods that apply deep learning to achieve various goals of biometric template protection are surveyed along with deep learning-based attacks. Copyright © 2023, The Authors. All rights reserved.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

An Overview of Organs-on-Chips Based on Deep Learning

引用

Research 2022年第2期2022卷 141-160页

作者： Jintao Li Jie Chen Hua Bai Haiwei Wang Shiping Hao Yang Ding Bo Peng Jing Zhang Lin Li Wei Huang Frontiers Science Center for Flexible Eletronrics Xi'an Institu te of Flexible Electronics(IFE)and Xr'an Institute of Biomedical Materials EngineeringNorthwesterm Polytechnical UniversityXi'an 710072China Key Laboratory of Ietlieant Computing and Signal Processing of Minsry of Educaton School of Electronics and Information EngineeringAnhui UriversityHefei 230601China 38th Research Institute of China Eilectronics Technology Grouep Corporation Hiefei 230088 China Collge of Biomedical Engimeering Sichuan UntiversityChengdu 610065China Key Laboratory of Flexible Elecronics(KLOFE)and Institute of Advanced Materials(IAM)Nanjing Tech University(NanjingTech)J Nanjing 211800 China

Microfluidic-based organs-on-chips(OoCs)are a rapidly developing technology in biomedical and chemical research and have emerged as one of the most advanced and promising in vitro *** miniaturization,stimulated tissue mechanical *** microenvironment of OoCs offer unique properties for biomedical ***,the large amount of data generated by the high parallelization of OoC systems has grown far beyond the scope of manual analysis by researchers with biomedical *** learning,an emerging area of research in the field of machine learning,can automatically mine the inherent characteristics and laws of"big data"and has achieved remarkable applications in computer vision,speech recognition,and natural language *** integration of deep learning in OoCs is an emerging field that holds enormous potential for drug development,disease modeling,and personalized *** review bricfly describes the basic concepts and mechanisms of microfluidics and deep learning and summarizes their successful *** then analyze thecombination of OoCs and deep learning for image digitization,data analysis,and ***,the problems faced in current applications are discussed,and future perspectives and suggestions are provided to further strengthen this integration.

关键词： Deep holds beyond

来源：评论

学校读者我要写书评

暂无评论

Research on patent classification based on hierarchical label semantics

Research on patent classification based on hierarchical labe...

引用

Education, Knowledge and Information Management (ICEKIM), International Conference on

作者： Jie Chen Shu Zhao Fan Lu Feng Liu Yangping Zhang Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei China School of Computer Science and Technology Anhui University Hefei China

ISBN: (纸本)9781665416672

Patent classification is an essential task in patent information management and knowledge mining. Most existing studies are based on the textual content of individual patent texts (e.g., titles and abstracts) for classification, but the patent also has label information with hierarchical structure and semantic description. However, the semantics correlation of patent texts and their labels have been largely ignored. In this paper, we propose a novel framework called HLSPC for patent classification by leveraging the hierarchical semantics correlation of patent texts and their labels. Specifically, we first apply a patent representation learning module for capturing the semantics representation of patent texts and hierarchical labels. Then, we design a label attention learning module to build the semantics correlation between patent texts and hierarchical labels, which enhances patent representation. Finally, we deploy a multi-level fusion module to get the refined category prediction for each patent which can preserve both local and global hierarchical prediction information. Extensive experimental results on two English patent datasets demonstrate the effective power of the HLSPC model.

关键词： Representation learning Patents Correlation Semantics Text categorization Education Information management

来源：评论

学校读者我要写书评

暂无评论

Cross-Polarization suppression by Comb-Shaped slots in Microstrip Patch 13

Cross-Polarization suppression by Comb-Shaped slots in Micro...

引用

13th International Conference on Microwave and Millimeter Wave technology, ICMMT 2021

作者： Ma, Jing Tan, Shi-Li Ni, Si-Yuan Wang, Chen Sun, Kai Luo, Yong-Yuan Peng, Lin Beijing Simulation Center Science And Technology On Special System Simulation Laboratory Beijing100854 China 95972 Troops Of PLA Jiuquan735018 China Guilin University Of Electronic Technology Guangxi Key Laboratory Of Wireless Wideband Communication And Signal Processing Guangxi Guilin541004 China

ISBN: (纸本)9781665434379

Cross-polarization (XP) of the microstrip antenna was suppressed by etching comb-shaped slots in the patch. By cutting longitudinal comb-shaped slots on the rectangular patch, the transverse current at the patch edges that lead to cross-polarization was dammed up. Then, the co-to cross-polarization (CP-XP) ratio over entire angular range around the broadside direction was increased from 20 dB of the rectangular microstrip antenna (RMA) to 35 dB of the defected patch structure (DPS). Moreover, as the longitudinal current was little affected by the slots, the proposed structure has little effect on the other performances of the antenna (including gain, directivity, radiant principle and impedance bandwidth). As the presented structure is achieved by simple adding slots to the rectangular patch, it is very easy to be fabricated. © 2021 IEEE.

关键词： Etching

来源：评论

学校读者我要写书评

暂无评论

Range-Velocity Tracking of Dynamic Finger Gestures Using 120GHz radar With LFM-MFSK Waveform

Range-Velocity Tracking of Dynamic Finger Gestures Using 120...

引用

IEEE International Conference on radar

作者： Ling Hong Fengzhou Dai School of Computer Science Shaanxi Normal University Xi'an China National Laboratory of Radar Signal Processing Xidian University Xi'an China

ISBN: (纸本)9781665468893

Hand and finger gesture sensing with millimeter wave (MMW) radar is an emerging technology. In this paper, we propose a novel linear frequency modulation and multiple frequency shift key (LFM-MFSK) combined waveform to sense the finger gesture and a new 1D searching phase unwrapping algorithm for the unambiguous range estimation of the significant scatterers on the hand of interest. By utilizing the new waveform, the hand is resolved from other objects in the range domain, and the different fingers can be resolved in the Doppler domain with high Doppler resolution. Besides, the unambiguous high accurate range estimation of the fingers can be obtained from the phase differences of the returns via a 1D searching phase unwrapping algorithm based on the Chinese remainder theorem (CRT). The 120GHz millimeter wave radar with the LFM-MFSK waveform is designed, and the proposed method is verified with the returns of two common finger gestures.

关键词： radar measurements Heuristic algorithms signal processing algorithms Estimation Millimeter wave radar radar tracking radar signal processing

来源：评论

学校读者我要写书评

暂无评论

Optically transparent transmissive orbital angular momentum (OAM) metasurface with high transmittance and broadband characteristics

引用

Optics Express 2025年第12期33卷 24385-24395页

作者： Yong Cai Yuying Dai Yue Ma Gang Wang Guanghui Xu Xingang Ren Hui Wang Xiaohu Zhao Xianliang Wu Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui University Hefei 230039 China Key Laboratory of Electromagnetic Environmental Sensing of Anhui Higher Education Institutes Anhui University Hefei 230039 China wang_toward@*** ghxu86@*** Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Institute of Physical Science and Information Technology Anhui University Hefei 230039 China xgren@*** Hefei Normal University Hefei 230009 China

This work proposes a high-performance broadband orbital angular momentum (OAM) beam-generating metasurface based on optically transparent media. A broadband polarization-converting transmissive metasurface, which operates in the 18 - 24 (28.57% fractional bandwidth) GHz range, has been realized by collaboratively designing dual C-split ring resonator structures and bidirectional lattice-patterned surface networks. The array structure demonstrates typical helical phase distribution features in the K-band, and experimental results verify simulation design. Innovatively employing a composite structure of quartz glass substrate and patterned conductive thin films, the design achieves compatible optimization of 77% visible-light transmittance and microwave broadband performance. This approach breaks through the mutually exclusive limitations of traditional metasurfaces’ optical/electromagnetic properties, providing a highly integrated solution for transparent antenna radomes in satellite communication systems and multi-mode beam multiplexing applications.

关键词： Orbital angular momentum multiplexing Phase plates Ring resonators Spatial light modulators Spiral phase Thin films

来源：评论

学校读者我要写书评

暂无评论

A Range Ambiguity Resolution Method for High-Resolution and Wide-Swath SAR Imaging Based on Continuous Pulse Coding

A Range Ambiguity Resolution Method for High-Resolution and ...

引用

IEEE International Conference on radar

作者： Jingyi Wei Yachao Li Ziyue Sun National Laboratory of Radar Signal Processing Xidian University Xi'an China School of Engineering and Computer Science University of Exeter Exeter UK

ISBN: (纸本)9781665468893

In synthetic aperture radar (SAR), high-resolution and wide-swath (HRWS) imaging is a challenging problem due to the contradiction between azimuth Doppler ambiguity and range ambiguity. In order to break the limitation of the pulse repetition frequency (PRF) on the radar imaging width, a HRWS SAR imaging method based on continuous pulse coding (CPC) to solve the range ambiguity is proposed in this paper. CPC method requires the radar to transmit multi-pulse signals with varying high PRF in the original pulse repetition period. Because of the small distance between each pulse, the echo will be aliased and blocked. In order to recover the unambiguous echo, we first use the form of CPC signal and the swath width of the radar to construct a linear equation set to mathematically model the aliased echo signal of each receiving window. Next, the established linear equations are split according to the distribution law of the receiving window, and the range ambiguity of the echo is performed by solving the split sub-linear equations. Finally, imaging processing is performed on the decoded unambiguous echo to achieve HRWS SAR imaging. The experimental results have confirmed the effectiveness of the method proposed in this paper.

关键词： Image resolution Imaging radar radar imaging Encoding Mathematical models radar polarimetry

来源：评论

学校读者我要写书评

暂无评论

Micro-Doppler Analysis of Target Based on the Clustering Prior to Solve the Block Sparse Forward and Backward TVAR Model

Micro-Doppler Analysis of Target Based on the Clustering Pri...

引用

IEEE International Conference on radar

作者： Shuojing Jin Ling Hong Fengzhou Dai National Laboratory of Radar Signal Processing Xidian University Xi'an China Key Laboratory of Modern Teaching Technology Ministry of Education School of Computer Science Shaanxi Normal University Xi'an China

ISBN: (纸本)9781665468893

Micro-Doppler features generated by target micromotion are usually unique and can be used as an important basis for target recognition, which reflects the fine features of target. In this paper, we propose an algorithm based on cluster-structured prior to solve block sparse forward and backward time-varying autoregressive (TVAR) model to perform Micro-Doppler analysis of the target. Firstly, convert the time-varying coefficients into the form of time-invariant coefficients. Then, an improved algorithm based on extended block sparse Bayesian learning (EBSBL) is used to solve the time-invariant block sparse coefficients by adopting a cluster-structured prior. At the same time, the priori information with known boundary is applied. Finally, the electromagnetic simulation results show that the proposed algorithm has advantages in Micro-Doppler analysis, which can not only give a clearer TF diagram than traditional methods, but also has a strong anti-noise performance.

关键词： Analytical models Target recognition Simulation Clustering algorithms radar Bayes methods Electromagnetics

来源：评论

学校读者我要写书评

暂无评论

Speech Topic Classification Based on Pre-trained and Graph Networks

Speech Topic Classification Based on Pre-trained and Graph N...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Fangjing Niu Tengfei Cao Ying Hu Hao Huang Liang He School of Information Science and Engineering Xinjiang University Urumqi China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi China Department of Electronic Engineering Tsinghua University Beijing China Beijing National Research Center for Information Science and Technology Beijing China

Speech Topic Classification (STC) automatically classifies audio clips into predefined categories, which is widely used in short video, personalized recommendation and other fields. At present, the common system is composed of two parts: first, the speech is converted into text by automatic speech recognition (ASR), and then the text topic is classified by natural language processing (NLP). Most of them have problems such as error propagation and lack of global structure. So in this paper, we propose a new end-to-end framework based on a pre-trained model and graph network. The pre-trained model is used to extract the semantic features with sequential structure instead of acoustic features, and the combination with the global features of conversational context constructed by graph network has achieved good results on the Fisher dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Joint Trajectory Design and Power Allocation for Target Tracking in Airborne radar Network

Joint Trajectory Design and Power Allocation for Target Trac...

引用

IEEE International Conference on radar

作者： Tao He Xiuci Mo Peng Zhang Hao Jiao Junkun Yan Hongwei Liu National Laboratory of Radar Signal Processing Xidian University Xi'an China AVIC Leihua Electronic Technology Research Institution Wuxi China

ISBN: (纸本)9781665468893

In this paper, a performance driven joint trajectory design and power allocation (JTDPA) scheme is developed for target tracking application in airborne radar network (ARN). The key idea of this scheme is to collaboratively exploit the maneuverability of aircraft and the adaptable transmit power of radar network to maximize the target tracking performance. The practical constraints including the threat zone, as well as the aircraft's maneuverability and the total transmit power budget are considered. By building the JTDPA scheme as a mathematical optimization problem, we can utilize the heuristic algorithm to solve the problem. Simulation results demonstrate that the proposed JTDPA scheme can greatly improve the target tracking performance.

关键词： Target tracking Simulation Heuristic algorithms Airborne radar radar tracking Trajectory Resource management

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：