检索结果-内蒙古大学图书馆

2022 3rd International Conference on Computer Information and Big Data Applications, CIBDA 2022

作者： Xie, Jingsheng Chen, Xi Zhang, Yanping Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Anhui Hefei China School of Computer Science and Technology Anhui University HefeiAH551 China

ISBN: (纸本)9783800758760

Network representation learning is to learn low dimensional vectors for nodes. It plays a critical role in network analysis. However, most existing network embedding methods focus on embedding the nodes that already exist in the network, and cannot be generalized to newly-added nodes without retraining the learning model. To deal with this problem, the most common idea is to directly aggregate neighbor embeddings as the representation of new nodes, but this may lead to ignoring the particularity of node neighbors themselves. To fill this gap, we present INRL-NA, an innovative method of Inductive Network Representation Learning based on Neighbor Aggregation, which uses the hierarchical information to selectively aggregate neighbor node embeddings, preserving both the structural information and feature information of network. First we build a hierarchical network, then train a refinement model on the hierarchical network, finally after a new node joins the network, we use the hierarchical information and feature information to selectively aggregate neighbor embeddings. The experimental results show that compared with direct aggregation of all neighbor representations, INRLNA has higher representation quality. © VDE VERLAG GMBH - Berlin - Offenbach.

关键词： Aggregates

来源：评论

学校读者我要写书评

暂无评论

Practical Frequency-Hopping MIMO Joint radar Communications: Design and Experiment

arXiv

引用

arXiv 2023年

作者： Liu, Jiangtao Wu, Kai Su, Tao Zhang, J. Andrew National Laboratory of Radar Signal Processing Xidian University Shaanxi Xi’an710071 China The Global Big Data Technologies Centre University of Technology SydneyNSW2007 Australia

Joint radar and communications (JRC) can realize two radio frequency (RF) functions using one set of resources, greatly saving hardware, energy and spectrum for wireless systems needing both functions. Frequency-hopping (FH) MIMO radar is a popular candidate for JRC, as the achieved communication symbol rate can greatly exceed radar pulse repetition frequency. However, practical transceiver imperfections can fail many existing theoretical designs. In this work, we unveil for the first time the non-trivial impact of hardware imperfections on FH-MIMO JRC and analytically model the impact. We also design new waveforms and, accordingly, develop a low-complexity algorithm to jointly estimate the hardware imperfections of unsynchronized receiver. Moreover, employing low-cost software-defined radios and commercial off-the-shelf (COTS) products, we build the first FH-MIMO JRC experiment platform with radar and communications simultaneously validated over the air. Corroborated by simulation and experiment results, the proposed designs achieves high performances for both radar and communications. © 2023, CC BY-NC-ND.

关键词： MIMO radar

来源：评论

学校读者我要写书评

暂无评论

A method for passive sonar broadband target detection based on peak filtering in frequency-wavenumber domain

引用

Chinese Journal of Acoustics 2023年第3期42卷 270-287页

作者： NING Jiangbo LI Yu WU Yongsheng CHI Cheng LI Zigao LI Shuqiu Institute of Acoustics Chinese Academy of SciencesBejing 100190 Key Laboratory of Science and Technology on Advanced Underwater Acoustic Signal Processing Chinese Academy of SciencesBeijing 100190 University of Chinese Academy of Sciences Beijing 100049 Unit 92682PLA Zhanjiang 524000

Traditional detection of broadband targets in passive sonars has low output signalto-noise ratio and poor performance in a complex situation with multiple targets and strong interferences. To solve this problem, this paper proposes a target detection method based on the characteristic of the energy distribution of broadband signals in the frequency-wavenumber domain by using uniform linear array. The proposed method converts the array signal into the frequency-wavenumber domain and uses the characteristics of the width and the spatial distribution of the main lobes and the side lobes to discriminate the main lobes in the wavenumber domain. After discriminating the main lobes of the same target at different frequencies, the accumulation of main lobe energy and the number of main lobes are used as the azimuth spectra for target detection. The theoretical analysis and simulations show the proposed method only utilizes the main lobes which have prominent contributions to target detection, thereby reducing the influence of the side lobes dramatically and improving the detection performance significantly. The results of trial data processing show that the output signal-to-noise ratio of the proposed method can be increased by 5.58 dB compared to SPED and 8.73 dB compared to CED. In addition, the computing time is decreased by 46% compared to CED, which validates the superiority of the proposed method.

关键词： passive wave number

来源：评论

学校读者我要写书评

暂无评论

Tensor-Based Source Localization Method with EVS Array

引用

Journal of Beijing Institute of technology 2021年第4期30卷 352-362页

作者： Guanjun Huang Yongquan Li Zijing Zhang Junpeng Shi Fangqing Wen Department of Electronic and Information Yangtze UniversityJingzhou 434200HubeiChina Department of National Laboratory of Radar Signal Processing Xidian UniversityXi’an 710071China. Department of Electronic Countermeasure National University of Defense TechnologyHefei 230037China

In many wireless scenarios,e.g.,wireless communications,radars,remote sensing,direc-tion-of-arrival(DOA)is of great *** this paper,by making use of electromagnetic vec-tor sensors(EVS)array,we settle the issue of two-dimensional(2D)DOA,and propose a covari-ance tensor-based *** of all,a fourth-order covariance tensor is used to formulate the array covariance *** an enhanced signal subspace is obtained by utilizing the high-er-order singular value decomposition(HOSVD).Afterwards,by exploiting the rotation invariant property of the uniform array,we can acquire the elevation ***,we can take ad-vantage of vector cross-product technique to estimate the azimuth ***,the polarization parameters estimation can be easily completed via least squares,which may make contributions to identifying polarization state of the weak *** tensor covariance algorithm can be adapted to spatially colored noise scenes,suggesting that it is more flexible than the most advanced *** experiments can prove the superiority and effectiveness of the proposed approach.

关键词： 2D-DOA estimation vector sensors tensor decomposition colored noise

来源：评论

学校读者我要写书评

暂无评论

A Mode Switching q-noise Constrained LMS-based Generalized Sidelobe Canceller

A Mode Switching q-noise Constrained LMS-based Generalized S...

引用

IEEE MTT-S International Microwave Workshop Series on Advanced Materials and Processes for RF and THz Applications (IMWS-AMP)

作者： Wenjing Hao Weixing Sheng Array Antenna and Array Signal Processing Laboratory Nanjing University of Science and Technology

The traditional q-derivative method has the advantage of fast convergence, it also has a wide optimization space for various beamforming algorithms. In this paper, based on the generalized sidelobe canceller (GSC) beamforming algorithm, the q-derivative method is optimized by mode transformation, which further improves the convergence speed of the algorithm. Meanwhile, the stability of the algorithm is guaranteed. Therefore, the algorithm can greatly reduce the computation amount by reducing the number of iterations, which provides the possibility for application in practice. The simulation results show that the algorithm has excellent convergence speed and good stability.

关键词： Radio frequency Array signal processing Simulation Switches Microwave theory and techniques Stability analysis Steady-state

来源：评论

学校读者我要写书评

暂无评论

COT2DNet: Contextual 2D Attention for Scene Text Recognition

COT2DNet: Contextual 2D Attention for Scene Text Recognition

引用

Artificial Intelligence, Human-Computer Interaction and Robotics (AIHCIR), International Conference on

作者： Yefei Qian Mayire Ibrayim Askar Hamdulla Chunhu Zhang Xinjiang Key Laboratory of Signal Detection and Processing Urumqi China School of Computer Science and Technology Xinjiang University Xinjiang China

Although scene text recognition (STR) methods have made great progress, reading the text of irregularly shaped scenes remains a challenge. The current conversion of two-dimensional (2D) images to one-dimensional (1D) feature maps for sequence recognition may lose a large amount of spatial information and cannot recognize text with a large degree of curvature. In this paper, we propose an network infrastructure to recognize texts of arbitrary shapes, named COT2D Attention Text Recognition Network (COT2Net). Firstly, deformable convolution is added to the feature extraction module, which can perform feature extraction according to the shape of the character and expand the receptive field of feature extraction; Finally, in the Transformer encoding stage, the multi-head attention is changed to Contextual 2D Multi-head Attention (COT2D), which can make full use of the relationship between the input keys Q, K, and V to guide the learning of dynamic attention, thereby enhancing the visual expression ability of text images. The COT2DNet uses COT2D to learn the relevance of each character in a scene text image and achieves excellent results on public datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Introducing Multilingual Phonetic Information to Speaker Embedding for Speaker Verification

Introducing Multilingual Phonetic Information to Speaker Emb...

引用

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

作者： Zhida Song Liang He Penghao Wang Ying Hu Hao Huang School of Computer Science and Technology Xinjiang University China Xinjiang Key Laboratory of Signal Detection and Processing China Department of Electronic Engineering Tsinghua University China

Incorporating frame-level phonetic information during the extraction of speaker embeddings has been shown to enhance the performance of speaker verification systems. However, previous studies have primarily relied on phonetic information obtained from pre-trained models of monolingual automatic speech recognition (ASR). Considering that speaker verification datasets typically consist of multiple languages, there are instances where speakers are proficient in multiple languages, resulting in discrepancies between the languages used in the enrolled and test utterances. To address these challenges, we employ a pre-trained multilingual ASR Conformer encoder to initialize the MFA-Conformer network for speaker verification. Experimental results on the VoxCeleb dataset demonstrate a significant improvement in the performance of the system that incorporates multilingual phonetic information across different evaluation sets, including VoxCeleb1-O, E, and H, as well as the VoxSRC21 validation set, which focuses on multilingual verification. The source code is released at https://***/zds-potato/multilingual-phonetic-sv.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SAR Image Feature Selection and Change Detection Based on Sparse Coefficient Correlation

SAR Image Feature Selection and Change Detection Based on Sp...

引用

International Conference on Control, Automation, Robotics and Vision (ICARCV)

作者： Wanying Song Huan Quan Yuang Chen Peng Zhang Xi'an Key Laboratory of Heterogeneous Network Convergence Communication Xi'an University of Science and Technology Xian China National Laboratory of Radar Signal Processing Xidian University Xian China

ISBN: (纸本)9781665476881

High-dimensional features extraction and selection is of great significance for synthetic aperture radar (SAR) image change detection. In this paper, a feature selection based on sparse coefficient correlation, abbreviated as SR-PCC, is proposed to realize the local reconstruction of known samples, so as to improve the accuracy of change detection. Firstly, high-dimensional texture features are extracted from real SAR images and then fused by stacking. Secondly, for the known samples, the sparse representation is performed and then the sparse coefficients are obtained. Then, the Pearson correlation coefficient method is used to select sparse coefficients related to the image itself, thus realizing local optimal reconstruction. Finally, the selected features are inputted into the support vector machine (SVM) to realize change detection. Experiments on real SAR images demonstrate the effectiveness of the proposed SR-PCC in high-dimensional feature selection and illustrate that it can provide better change detection maps.

关键词： Support vector machines Correlation coefficient Correlation Stacking Feature extraction radar polarimetry Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Detection of interference in main lobe for two-dimensional monopulse antenna

Detection of interference in main lobe for two-dimensional m...

引用

IEEE MTT-S International Microwave Workshop Series on Advanced Materials and Processes for RF and THz Applications (IMWS-AMP)

作者： Yujiao Wang Weixing Sheng Array Antenna and Array Signal Processing Laboratory Nanjing University of Science and Technology

In this paper, an interference detection and angle estimation algorithm for two-dimensional monopulse antenna is proposed to solve the problem that the interference in the main lobe is difficult to be detected. Only the sum signal, difference signal and noise variance are required in this algorithm. We use the generalized likelihood ratio criterion (GLRT) to obtain a detection statistic, compare this statistic with the set threshold, and then realize the detection of interference according to the comparison result. The angle estimation formula is further derived. Simulation results show that the performance of interference detection and angle estimation is well achieved.

关键词： Microwave antennas Radio frequency Azimuth Simulation Conferences Estimation Interference

来源：评论

学校读者我要写书评

暂无评论

Multi model fusion based prediction of human joint angles using sEMG and historical angles

Multi model fusion based prediction of human joint angles us...

引用

第42届中国控制会议

作者： Jiandong Han Haoping Wang Yang Tian Sino-French International Joint Laboratory of Automatic Control and Signal Processing (LaFCAS) School of AutomationNanjing University of Science and Technology

Active rehabilitation training for patients with lower limb motor dysfunction mainly depends on exoskeleton robots that can accurately and timely identify human motion intentions,which can be implemented by continues estimation of human joint *** this paper,a multi model fusion based ridge regression named as 'MMF-RR' for the prediction of human joint angles is ***,four selected basic learners are first end-to-end trained for the subsequent analysis from the data set composed of surface electromyography signals(sEMG) and historical *** the results are spliced into ridge regression with penalty terms for joint angle *** proposed MMF-RR was evaluated on publicly available dataset for 22 participants,where half of them were healthy participants,while the other half had various knee joint *** the results show that the proposed MMF-RR can significantly improve the predicting *** particular,the average mean absolute error(MAE) and average mean square error(MSE) of knee joint angle prediction of healthy participants and participants with knee joint lesions were 6.73%,2.36% and 8.97%,3.26%,respectively,which indicate that MMF-RR can provide more precise human motion intention information for lower limb motor under rehabilitation training than five comparison methods.

关键词：

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：