检索结果-内蒙古大学图书馆

6th International Conference on Intelligent Computing and signal processing (ICSP)

作者： Xin Jiang Peng Zhou Shu Zhao Yufeng Guo School of Computer Science and Technology Anhui University Hefei China Key Laboratory of Intelligent Computing and Signal Processing Anhui University Hefei China

Technological innovation is becoming one of the critical factors in promoting social development all over the world. The vigorous development of patent applications in recent years provides an opportunity to reveal the inherent laws of innovation, but it also puts forward higher requirements for patent mining technology. An essential step in patent text mining is to build a technical portrait for each patent, that is, to identify the technical phrases involved, which can summarize and represent the patent from a technical perspective. Previous technical phrase extraction methods thoroughly used technical phrases' characteristics and the relationship between technical phrases. Regarding our observations, the relationship between patent texts and technical phrases is also essential. Specifically, critical technical phrases are more relevant to the patent text and can be discovered by the attention mechanism. Motivated by this, we propose an unsupervised technical phrase extraction method based on the attention mechanism named UTESC. Self-attention captures the importance of technical phrases in sentences, and cross-attention captures the relevance between technical phrases and patents. Extensive experiments and algorithm comparisons on patent datasets have proven the effectiveness of our algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Modified Tracking Algorithm for NSHV Based on Aerodynamic Model

A Modified Tracking Algorithm for NSHV Based on Aerodynamic ...

引用

2021 CIE International Conference on radar, radar 2021

作者： Zhang, Jiaqi Zheng, Jibin Sun, Dianxing Liu, Hongwei Xidian University National Laboratory of Rader Signal Processing Xian China China Electronic Technology Group Corporation Science and Technology on Electronic Test and Measurement Laboratory Qingdao China

ISBN: (纸本)9781665498142

In order to track the near space hypersonic vehicle (NSHV), we propose a tracking model containing aerodynamic and kinematic information using interacting multiple model (IMM) algorithm with accruate speed prior information. Because traditional maneuver models are difficult to describe the complex movement characteristics, which involves large-scale high-speed mobile, large flight cover, etc., fault-acceleration model with surface damage model and external disturbance model are proposed. With the model, the state equations are constructed and the system dynamic error is deduced taking variable structure multiple model (VSMM) algorithm as the flitering algorithm. Moreover, an adaptive method for the change of control variables is proposed for setting parameters apporiately in the situations when a prior information is unknown. Simulation experiments are conducted to validate the superiorities among all tracking algorithms in this paper. © 2021 IEEE.

关键词： aerodynamic model interacting multiple model algorithm near space hypersonic vehicle tracking

来源：评论

学校读者我要写书评

暂无评论

LE-CAM++: A Lighter and More Efficient CAM++ for Speaker Verification

LE-CAM++: A Lighter and More Efficient CAM++ for Speaker Ver...

引用

International Symposium on Chinese Spoken Language processing

作者： Shuanghong Liu Zhida Song Zhihua Fang Liang He School of Computer Science and Technology Xinjiang University Urumqi Xinjiang Key Laboratory of Signal Detection and Processing Urumqi School of Intelligence Science and Technology Xinjiang University Urumqi Department of Electronic Engineering and Beijing National Research Center for Information Science and Technology Tsinghua University Beijing

ISBN: (数字)9798331516826

ISBN: (纸本)9798331516833

Due to its superior performance and fewer parameters, CAM++ has become the state-of-the-art model for speaker verification tasks. This model uses 2D convolutional blocks to extract front-end features, which are then fed into a densely connected time-delay neural network backbone to extract deep features. However, the simple stacking of 2D convolutions may lead to the generation of a significant amount of redundant features, which is detrimental to efficient feature extraction. Furthermore, although CAM++ already has a relatively small number of parameters, there is still room for further optimization. To address these issues, this paper first employs depthwise separable convolutions to replace the dilated convolutions in the back-end network of CAM++, making the model more lightweight. Next, we introduce spatial and channel reconstruction convolution (SCConv) in the ResBlock module of CAM++ to reduce redundant features and optimize the feature extraction process. Finally, after SCConv, we apply squeeze and excitation attention mechanism to model the interdependencies between channels and recalibrate each channel, further enhancing the model's representational capacity. We name the resulting model LE-CAM++. Our proposed model achieves an EER of 0.686 and a minDCF of 0.084 on the VoxCeleb1–O dataset. Compared to the baseline model CAM ++, the EER is reduced by 11%, and the minDCF is reduced by 28%. Additionally, the model parameters are reduced by 8%.

关键词： Attention mechanisms Stacking Neural networks Feature extraction Optimization

来源：评论

学校读者我要写书评

暂无评论

No-Reference Image Quality Assessment Based on Active Reasoning Module 6

No-Reference Image Quality Assessment Based on Active Reason...

引用

6th IEEE International Conference on Electronic Information and Communication technology, ICEICT 2023

作者： Qi, Junwei Deng, Yuhao Wang, Qingchun Yang, Zhen Li, Yingsong College of Information and Communication Engineering Harbin Engineering University Harbin150001 China Shanghai Yanding Information Technology Co. Ltd. Shanghai201210 China College of Computer Science and Technology Harbin Engineering University Harbin150001 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China

ISBN: (纸本)9798350399059

We present a no-reference image-quality - assessment algorithm based on active reasoning module. This algorithm has three modules: the feature extraction module, the active reasoning module, and the quality assessment module. The active reasoning module incorporates the generator component of the generative adversarial network and enhances its structure with the Res2Net architecture. By integrating this module into the backbone feature extraction network, we improve the receptive field of each convolutional layer, enabling the network to capture information at different scales of the image. To preserve the texture information of the image, we input the gradient map of the distorted image, the distorted image itself, and the image features generated by the generator into the quality assessment module, which has a multi-feature regression networks. This module establishes a mapping model from image-feature to image-quality scores. We conducted experimental analysis of this algorithm on three widely used public datasets, confirming the excellent performance and superiorities of the presented algorithm. The results validate the effectiveness of the designed algorithm and its ability to assess image quality accurately. © 2023 IEEE.

关键词： Image quality

来源：评论

学校读者我要写书评

暂无评论

Simplified Skip-Connected UNet for Robust Speaker Verification Under Noisy Environments

Simplified Skip-Connected UNet for Robust Speaker Verificati...

引用

International Symposium on Chinese Spoken Language processing

作者： Zonghui Wang Zhihua Fang Zhida Song Liang He School of Computer Science and Technology Xinjiang University Urumqi Xinjiang Key Laboratory of Signal Detection and Processing Urumqi School of Intelligence Science and Technology Xinjiang University Urumqi Department of Electronic Engineering Beijing National Research Center for Information Science and Technology Tsinghua University Beijing

ISBN: (数字)9798331516826

ISBN: (纸本)9798331516833

In recent years, deep neural network based methods for speaker verification have made remarkable progress in clean environments. However, background noise significantly reduces the accuracy and reliability of speaker verification systems by masking or changing the voice characteristics of the speaker. In this paper, we propose a cascaded framework optimized with multiobjective loss to mitigate the interference of different levels and types of noise on the speaker verification task. The proposed architecture consists of two components: a speech enhancement module based on improved 2D-UNet, which reduces the structural limitations of directly using classical UNet for noise reduction, and a back-end speaker embedding extraction module. We carry our experiments on the VoxCeleb1 and VOiCES datasets, as well as in the presence of out-of-domain noise conditions. The evaluations have demonstrated this method shows great potential for speaker verification in noisy environments.

关键词： Training Semantics Noise reduction Interference Speech enhancement Complexity theory Noise measurement Reliability Optimization signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Formulation of Optimization Problems with Radiation Field Phases as Design Variables for Pattern Synthesis of Linear Antenna Arrays

引用

China Communications 2022年第12期19卷 86-100页

作者： Fei Zhao Jun He Sanyou Zeng Changhe Li Qinghui Xu Zhigao Zeng School of Mechanical Engineering and Electronic Information China University of GeosciencesWuhan 430074China Science and Technology on Blind Signal Processing Laboratory Southwest Electronics and Telecommunication Technology Research InstituteChengdu 610041China School of Automation China University of GeosciencesWuhan 430074China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan 430074China College of Computer Hunan University of TechnologyZhuzhou CityHunan Province412007China

Pattern synthesise of antenna arrays is usually complicated optimization problems,while evolutionary algorithms(EAs)are promising in solving these *** paper does not propose a new EA,but does construct a new form of optimization *** new optimization formulation has two differences from the common *** is the objective function is the field error between the desired and the designed,not the usual amplitude error between the desired and the *** difference is beneficial to decrease complexity in some *** second difference is that the design variables are changed as phases of desired radiation field within shaped-region,instead of excitation *** difference leads to the reduction of the number of design variables.A series of synthesis experiments including equally and unequally spaced linear arrays with different pattern shape requirements are applied,and the effectiveness and advantages of the proposed new optimization problems are *** results show that the proposing a new optimization formulation with less complexity is as significant as proposing a new algorithm.

关键词： pattern synthesis evolutionary algorithms linear antenna arrays

来源：评论

学校读者我要写书评

暂无评论

Calibration and Estimation for FDA-MIMO radar with Random Amplitude and Phase Errors

Calibration and Estimation for FDA-MIMO Radar with Random Am...

引用

IEEE International Conference on radar

作者： Feilong Liu Shengqi Zhu Jingwei Xu Ximin Li Yanhong Xu Wenwen Si National Key Laboratory of Radar Signal Processing Xidian University Xi’an Shannxi China the School of Communication and Information Engineering Xi’an University of Science and Technology Xi’an Shannxi China Beijing Institute of Space Long March Vehicle Xi’an Beijing China

The combination of frequency diverse array (FDA) with range-angle-time dependent beampattern and waveform diversity in multiple input multiple output (MIMO) radar, namely, FDA-MIMO radar, offers additional degrees-of-freedom to enhance the overall system performance. The existing parameter estimation algorithms for FDA-MIMO radar are difficult to achieve effective target estimation when there is amplitude-phase error in the array antenna. In this paper, the proposed method can achieve the calibration and estimation for FDA-MIMO radar with random amplitude and phase errors. First, the signal model for FDA-MIMO radar signal model with random amplitude and phase errors is established. Second, the angle and range estimation is obtained by the spectral peak search method with reduced dimension. Then, the amplitude and phase error of each array element are estimated by the singular value decomposition and eigenvalue decomposition. Finally, the multiple simulation experiments show that in the presence of amplitude and phase errors, the existing algorithms have completely failed, but the proposed algorithm still has the ability to estimate the target with high precision.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On the Structure Property of PCR’s Adjacency Graph with a Prime Order and Its Application of Constructing M-Sequences 16th

On the Structure Property of PCR’s Adjacency Graph with a P...

引用

16th International Conference on Information Security and Cryptology, Inscrypt 2020

作者： Zhou, Congwei Guan, Jie Hu, Bin He, Kuan PLA SSF Information Engineering University Zhengzhou China National Key Laboratory of Science and Technology on Blind Signal Processing Chengdu China

ISBN: (纸本)9783030718510

In this paper we find a deterministic structure respecting the adjacency graph of a pure circulating shift register (PCR) with a prime order, and give a theoretical method for constructing all floor weight class of M-sequences. As a special case of this method, we calculate a lower bound of the number of floor weight class of M-sequences and give their corresponding feedback functions. © 2021, Springer Nature Switzerland AG.

关键词： Shift registers

来源：评论

学校读者我要写书评

暂无评论

Shared Aperture K- and Ka-Band Antenna Array for Satellite Communications

Shared Aperture K- and Ka-Band Antenna Array for Satellite C...

引用

International Symposium on Antennas, Propagation and EM Theory (ISAPE)

作者： Yiwei Geng Yuqi Cong Yan Zhang State Key Laboratory of Millimeter Waves School of Information Science and Engineering Southeast University Nanjing China Guangxi Wireless Broadband Communication and Signal Processing Key Laboratory Guilin University of Electronic Technology Guilin China

ISBN: (数字)9798350353129

ISBN: (纸本)9798350353136

The design of a shared aperture dual-band and dualpolarized antenna array is presented for the K- and Ka-band satellite communications. The antenna operating at either band shares similar geometries, consisting of four small square patches fed by two orthogonally deployed inverted-F shaped antennas (IFAs) and an L-shaped metal strip to enhance inter-port isolation. By optimizing the geometrical sizes, two types of antenna elements are adjusted to operate in the K- and Ka-band, respectively. A novel topology for intersectional arranging of low-band and highband antenna elements is proposed, using a nested configuration of triangular and rectangular layouts. The proposed antenna array, verified through simulations, can generate dual orthogonal linearly polarized waves over 18.6-21.1 GHz and 25.5-32.5 GHz, with inter-band isolations better than 17 dB and 15 dB, respectively. The typical realized gain is 13.2 dBi at 19 GHz and 16.2 dBi at 29 GHz, respectively.

关键词： Satellite antennas Antenna theory Layout Dual band Metals Aperture antennas Topology Ka-band Satellite communications Antenna arrays

来源：评论

学校读者我要写书评

暂无评论

Millimeter-Wave Broadband Dual-Polarized Shorted Patch-Loaded Magnetoelectric-Dipole Antenna and Its Array

引用

IEEE Transactions on Antennas and Propagation 2025年

作者： Wang, Gan Zhang, Yan Southeast University State Key Laboratory of Millimeter Waves School of Information Science and Engineering Nanjing210096 China Southeast University School of Information Science and Engineering State Key Laboratory of Millimeter Waves Nanjing210096 China Guilin University of Electronic Technology Guangxi Wireless Broadband Communication and Signal Processing Key Laboratory Guilin541004 China

A broadband dual-polarized antenna is proposed for millimeter-wave (mmW) application, which is composed of two pairs of magnetoelectric (ME) dipoles and a shorted patch. The ME dipoles are arranged into a square ring shape to enclose the shorted patch to generate multiple resonances, and they are fed through a cross-shaped slot by two orthogonally placed feeding strip lines for dual-polarization. The proposed antenna is fabricated and measured, which achieves an impedance bandwidth of 65.4% (21.3-42 GHz) for dual-polarization, with an in-band gain variation of less than 1 dB. A 1 × 8 array is further designed and implemented using two substrate-integrated coaxial line (SICL) feeding networks to excite eight uniformly distributed elements. The measured results show that an impedance bandwidth of 58.75 % (22.1-40.48 GHz) is achieved for dual-polarization, accompanying a peak gain of 15 dBi and gain fluctuation smaller than 3 dB. To break through the beam scanning limitation over the achieved octave bandwidth, an offset feeding scheme is introduced to the proposed antenna, and a smallscale 2×2 non-uniformly arranged array is proposed and numerically analyzed. The measured results indicate that a beam scanning range of ±30° can be achieved over the entire operating bandwidth, and the side-lobe levels (SLLs) remain below -10.46 dB, -11.5 dB, and -10.16 dB at 22, 30, and 38 GHz, respectively. The proposed antenna and its array have features of broad bandwidth, flat gain, stable radiation pattern, and wide-angle scanning, which are promising for mmW communication systems. © 1963-2012 IEEE.

关键词： Dipole antennas

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：