检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Wu, Rongsheng Shi, Minjia Solé, Patrick Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education School of Mathematical Sciences Anhui University Hefei230601 China Lab I2M CNRS Aix-Marseille University Centrale Marseille Marseille France

Quasi-polycyclic (QP for short) codes over a finite chain ring R are a generalization of quasi-cyclic codes, and these codes can be viewed as an R[x]-submodule of Rm, where Rm := R[x]/hfi, and f is a monic polynomial of degree m over R. If f factors uniquely into monic and coprime basic irreducibles, then their algebraic structure allow us to characterize the generator polynomials and the minimal generating sets of 1-generator QP codes as R-modules. In addition, we also determine the parity check polynomials for these codes by using the strong Gröbner bases. In particular, via Magma system, some quaternary codes with new parameters are derived from these 1-generator QP codes. © 2021, CC0.

关键词： Polynomials

来源：评论

学校读者我要写书评

暂无评论

The Database and Benchmark For the Source Speaker Tracing Challenge 2024

The Database and Benchmark For the Source Speaker Tracing Ch...

引用

IEEE Spoken Language Technology Workshop

作者： Ze Li Yuke Lin Tian Yao Hongbin Suo Pengyuan Zhang Yanzhen Ren Zexin Cai Hiromitsu Nishizaki Ming Li School of Computer Science Wuhan University Wuhan China Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems Duke Kunshan University Kunshan China AI Center OPPO Beijing China Key Laboratory of Speech Acoustics and Content Understanding Institute of Acoustics CAS China Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University Center for Language and Speech Processing Johns Hopkins University USA Integrated Graduate School of Medicine Engineering and Agricultural Sciences University of Yamanashi 4-4-37 Takeda Kofu Yamanashi Japan

ISBN: (数字)9798350392258

ISBN: (纸本)9798350392265

Voice conversion (VC) systems can transform audio to mimic another speaker’s voice, thereby attacking speaker verification (SV) systems. However, ongoing studies on source speaker verification (SSV) are hindered by limited data availability and methodological constraints. This paper presents the Source Speaker Tracking Challenge (SSTC) on STL 2024, which aims to fill the gap in the database and benchmark for the SSV task. In this study, we generate a large-scale converted speech database with 16 common VC methods and train a batch of baseline systems based on the MFA-Conformer architecture. In addition, we introduced a related task called conversion method recognition, with the aim of assisting the SSV task. We expect SSTC to be a platform for advancing the development of the SSV task and provide further insights into the performance and limitations of current SV systems against VC attacks. Further details about SSTC can be found here 1 . 1 https://***/

关键词： Databases Conferences Transforms Contrastive learning Benchmark testing Multitasking Calibration

来源：评论

学校读者我要写书评

暂无评论

Ultra-Wideband MIMO Antenna with Double Notched Band

Ultra-Wideband MIMO Antenna with Double Notched Band

引用

Cross Strait Quad-Regional Radio Science and Wireless Technology Conference (CSQRWC)

作者： Xuefeng Wang Yufa Sun Key Lab of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei China

ISBN: (数字)9781728181813

ISBN: (纸本)9781728181820

This paper presents an ultra-wideband (UWB) multiple-input multiple-output (MIMO) antenna with a small size of 41×41×1.6mm 3 . Double notched bands are obtained by introducing C-shaped slot and L-shaped slot. The proposed antenna exhibits good UWB performance, it achieves impedance bandwidth from 3.1GHz to 10.8GHz, and better than -15dB of isolation over the entire operating band, with adaptable double band rejection to avoid interference caused by two narrow frequency bands WLAN (5.15-5.85 GHz) and X-band satellite communication systems (7.25-7.75 GHz).

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Broadband Ka-band Antenna with Asymmetric CPW Structure for package integration

A Broadband Ka-band Antenna with Asymmetric CPW Structure fo...

引用

International Conference on Microwave and Millimeter Wave Technology Proceedings

作者： Kun Li Hao-Ran Zhu Zhi-Xiang Huang Xian-Liang Wu Key Lab of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei China

ISBN: (数字)9781728157337

ISBN: (纸本)9781728157344

In this paper, a novel broadband Coplanar Waveguide(CPW)-fed slot antenna working at Ka-band is presented. A wideband performance is realized by slot coupling between the rectangular stub and the surrounding ground plane for millimeter wave applications. Meanwhile, an asymmetric CPW structure is introduced to improve the antenna bandwidth, by adjusting the width of the rectangular stub, two different resonance frequencies of the narrow slots around the stub are generated close to the center frequency to achieve a wider band-width. The designed CPW slot antenna exhibits a wide impedance bandwidth over 42.4% and an average gain of 3 dBi.

关键词： Microwave antennas Slot antennas Resonant frequency Broadband communication Coplanar waveguides Broadband antennas Antenna radiation patterns

来源：评论

学校读者我要写书评

暂无评论

Research on Denoising of Cryo-em Images Based on Deep Learning

引用

Journal of Information Hiding and Privacy Protection 2020年第1期2卷 1-9页

作者： Jianquan Ouyang Yi He Huanrong Tang Zhousong Fu Key Laboratory of Intelligent Computing&Information Processing Ministry of EducationXiangtan UniversityXiangtan411105China

Cryo-em(Cryogenic electron microscopy)is a technology this can build bio-macromolecule of three-dimensional *** the condition of now,the projection image of the biological macromolecule which is collected by the Cryo-em technology that the contrast is low,the signal to noise is low,image blurring,and not easy to distinguish single particle from background,the corresponding processing technology is lagging ***,make Cryo-em image denoising useful,and maintaining bio-macromolecule of contour or signal of function-construct improve Cryo-em image quality or resolution of Cryo-em three-dimensional structure have important *** paper researched a denoising function base on GANs(generative adversarial networks),purpose an improved discriminant model base on Wasserstein distance and an improved image denoising model by add gray *** model turn discriminant model’s training process from binary classification’s training process into regression task training process,it make GANs in training process more stable,more reasonable parameter ***,we also propose an improved generative model by add gray *** experimental results show that our model can increase the peak signal-to-noise ratio of the Cryo-em simulation image by 10.3 dB and improve SSIM(Structural Similarity Index)of the denoised image results by *** with traditional image denoising algorithms such as BM3D(Block Matching 3D),our model can better save the model structure and the vein signal in the original image and the operation speed is faster.

关键词： Deep learning Cryo-em GAN image denosing

来源：评论

学校读者我要写书评

暂无评论

A Deep Reinforcement Learning Framework for Vehicle Detection and Pose Estimation in 3D Point Clouds 6th

A Deep Reinforcement Learning Framework for Vehicle Detectio...

引用

6th International Conference on Artificial Intelligence and Security, ICAIS 2020

作者： Wang, Weipeng Luo, Huan Zheng, Quan Wang, Cheng Guo, Wenzhong Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350003 China Key Laboratory of Spatial Data Mining and Information Sharing Ministry of Education Fuzhou350003 China Fujian Key Laboratory of Sensing and Computing for Smart City Xiamen University XiamenFJ361005 China

ISBN: (纸本)9783030578800

As for autonomous driving in urban environments, it is of significance to accurately capture the position and pose of vehicles. Those information can assist self-driving system in making right decisions to avoid potential risks. Currently, 3D point clouds captured by laser scanners are widely used in self-driving systems to sense the real environment. Therefore, in this paper, we propose a deep reinforcement learning framework for vehicle detection and pose estimation by using 3D point clouds. Specifically, to estimate the pose of vehicles, we propose to design a rotation action in Deep Q Network (DQN). In addition, by considering the whole detection procedure as Markov Decision Process (MDP), our intermediate detected results can further improve the detection performance of our proposed method. The evaluations are carried on outdoor point cloud scenes captured by VMX450 laser scanning system. The experimental results demonstrate the satisfied performance on vehicle detection and pose estimation. © 2020, Springer Nature Switzerland AG.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

CycleGAN with dual adversarial loss for bone-conducted speech enhancement

arXiv

引用

arXiv 2021年

作者： Pan, Qing Gao, Teng Zhou, Jian Wang, Huabin Tao, Liang Kwan, Hon Keung Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei230601 China Department of Electrical and Computer Engineering University of Windsor WindsorONN9B 3P4 Canada

Compared with air-conducted speech, bone-conducted speech has the unique advantage of shielding background noise. Enhancement of bone-conducted speech helps to improve its quality and intelligibility. In this paper, a novel CycleGAN with dual adversarial loss (CycleGAN-DAL) is proposed for bone-conducted speech enhancement. The proposed method uses an adversarial loss and a cycle-consistent loss simultaneously to learn forward and cyclic mapping, in which the adversarial loss is replaced with the classification adversarial loss and the defect adversarial loss to consolidate the forward mapping. Compared with conventional baseline methods, it can learn feature mapping between bone-conducted speech and target speech without additional air-conducted speech assistance. Moreover, the proposed method also avoids the over-smooth problem which is occurred commonly in conventional statistical based models. Experimental results show that the proposed method outperforms baseline methods such as CycleGAN, GMM, and BLSTM. © 2021, CC BY.

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Resilient Collaborative Caching for Multi-Edge Systems with Robust Federated Deep Learning

引用

IEEE/ACM Transactions on Networking 2024年

作者： Chen, Zheyi Liang, Jie Yu, Zhengxin Cheng, Hongju Min, Geyong Li, Jie Fuzhou University College of Computer and Data Science Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou350116 China Ministry of Education Engineering Research Center of Big Data Intelligence Fuzhou350002 China Lancaster University School of Computing and Communications LancasterLA1 4YW United Kingdom University of Exeter Faculty of Environment Science and Economy Department of Computer Science ExeterEX4 4QF United Kingdom Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai200240 China

As a key technique for future networks, the performance of emerging multi-edge caching is often limited by inefficient collaboration among edge nodes and improper resource configuration. Meanwhile, achieving optimal cache hit rates poses substantive challenges without effectively capturing the potential relations between discrete user features and diverse content libraries. These challenges become further sophisticated when caching schemes are exposed to adversarial attacks that seriously impair cache performance. To address these challenges, we introduce RoCoCache, a resilient collaborative caching framework that uniquely integrates robust federated deep learning with proactive caching strategies, enhancing performance under adversarial conditions. First, we design a novel partitioning mechanism for multi-dimensional cache space, enabling precise content recommendations in user classification intervals. Next, we develop a new Discrete-Categorical Variational Auto-Encoder (DC-VAE) to accurately predict content popularity by overcoming posterior collapse. Finally, we create an original training mode and proactive cache replacement strategy based on robust federated deep learning. Notably, the residual-based detection for adversarial model updates and similarity-based federated aggregation are integrated to avoid the model destruction caused by adversarial updates, which enables the proactive cache replacement adapting to optimized cache resources and thus enhances cache performance. Using the real-world testbed and datasets, extensive experiments verify that the RoCoCache achieves higher cache hit rates and efficiency than state-of-the-art methods while ensuring better robustness. Moreover, we validate the effectiveness of the components designed in RoCoCache for improving cache performance via ablation studies. © 1993-2012 IEEE.

关键词： cache space partitioning content popularity prediction Multi-edge collaborative caching proactive cache replacement robust federated deep learning

来源：评论

学校读者我要写书评

暂无评论

A Biased Random key Heuristic Genetic Approach for the Payload Packing Design of A Satellite Module

A Biased Random Key Heuristic Genetic Approach for the Paylo...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Ziqiang Li Wenqian Ruan Yu Kang School of Computer Science Xiangtan University Xiangtan Hunan China Ministry Education Key Laboratory of Intelligent Computing & Information Processing Xiangtan University Xiangtan Hunan China

ISBN: (纸本)9781728165981

Existing heuristic evolutionary approaches are effective to solve the multi-module satellite packing problem. But for them, payload allocation and packing optimization are achieved in two different stages. And for their heuristics there are faults of weaker generality and less candidate location. So, a biased random key heuristic genetic approach is proposed for the collaborative payload allocation and packing for multi-module satellite (MSRKHGA). The firstly, by coding and decoding the random key individual and using GA operator, the organic combination of the payload allocation and packing optimization is achieved. Secondly, by region-positioning it can avoid the time-consuming overlapping calculation between individuals and dynamically generate more candidate regions for payloads to be packed. Numerical experiments show that all index of the proposed MSRKHGA approach are superior obviously to those of existing approaches.

关键词： Satellites Heuristic algorithms Genetics Encoding Decoding Resource management Optimization

来源：评论

学校读者我要写书评

暂无评论

Steady-state Analysis of Bipolar Transistor

Steady-state Analysis of Bipolar Transistor

引用

Progress in Electromagnetic Research Symposium (PIERS)

作者： Yeqiang Yan Xingang Ren Shuping He Xiaotao Huang Zhixiang Huang Anhui Province Key Laboratory of Target Recognition and Feature Extraction Luan China Information Materials and Intelligent Sensing Laboratory of Anhui Province Institute of Physical Science and Information Technology Anhui University Hefei China Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei China Lingnan Normal University Zhanjiang China

ISBN: (纸本)9781665409889

Numerical simulation of semiconductor devices enable the quick obtain of the device physical characteristics. However, the trial productions of the semiconductor devices have the disadvantages of long cycle and high cost. Therefore, it is necessary to carry out numerical simulation investigating semiconductor devices. We propose the coupling approach and the decoupling-Gummel method to solve the semiconductor equations. The results of the two methods are compared with the commercial software. Numerical experiment indicates that the results obtained by our method are accurate. When the transistor is at a low voltage bias, the decoupling method converges faster than the coupling method. In the case of high voltage bias, the decoupling method has a slower convergence speed than the coupling method, even difficult to converge for higher voltage bias. However, the coupling method has higher memory requirements than the Gummel method. Therefore, we need to balance the advantages of the coupling method and the Gummel method when conduct the numerical simulation.

关键词： Couplings Bipolar transistors Voltage Production Numerical simulation Mathematical models Software

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：