检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Yang, Shangshang Chen, Mingyang Wang, Ziwen Yu, Xiaoshan Zhang, Panpan Ma, Haiping Zhang, Xingyi Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Anhui Hefei230601 China Anhui Province Key Laboratory of Intelligent Computing and Applications China Department of Information Materials Intelligent Sensing Laboratory of Anhui Province China

Existing graph learning-based cognitive diagnosis (CD) methods have made relatively good results, but their student, exercise, and concept representations are learned and exchanged in an implicit unified graph, which makes the interaction-agnostic exercise and concept representations be learned poorly, failing to provide high robustness against noise in students’ interactions. Besides, lower-order exercise latent representations obtained in shallow layers are not well explored when learning the student representation. To tackle the issues, this paper suggests a meta multigraph-assisted disentangled graph learning framework for CD (DisenGCD), which learns three types of representations on three disentangled graphs: student-exercise-concept interaction, exercise-concept relation, and concept dependency graphs, respectively. Specifically, the latter two graphs are first disentangled from the interaction graph. Then, the student representation is learned from the interaction graph by a devised meta multigraph learning module;multiple learnable propagation paths in this module enable current student latent representation to access lower-order exercise latent representations, which can lead to more effective nad robust student representations learned;the exercise and concept representations are learned on the relation and dependency graphs by graph attention modules. Finally, a novel diagnostic function is devised to handle three disentangled representations for prediction. Experiments show better performance and robustness of DisenGCD than state-of-the-art CD methods and demonstrate the effectiveness of the disentangled learning framework and meta multigraph module. The source code is available at https://***/BIMK/intelligent-Education/tree/main/DisenGCD. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

2023 7th International Conference on Communication and Information Systems An Improved IOTA Protocol Based on Optimal Midway Walk 7

2023 7th International Conference on Communication and Infor...

引用

7th International Conference on Communication and Information Systems, ICCIS 2023

作者： Wu, Hongcheng Zhi, Hui Liu, Yangyang Anhui University School of Electronic and Information Engineering Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Hefei230601 China Hefei Zhilian Technology Industry Investment Co. Ltd Hefei230601 China

ISBN: (纸本)9798350330540

IOTA (Internet of Things Applications) protocol aims to provide a secure and trustworthy protocol for realizing data-value interactions between IoT devices, and it has become the next possible direction for the development of Blockchain applications. IOTA protocol has the problem that the time-consuming cumulative weight update grows too fast with the increase of the number of transactions, this paper proposed an improved IOTA protocol based on optimal midway walk, the improved protocol uses cutting-edge transaction selection algorithm of weighted Monte Carlo Markov random walk to reduce cumulative weight update delay. Firstly, this improved IOTA protocol mainly ensures the efficiency of transaction confirmation without losing the security of consensus by introducing the optimal midway walk method, i.e., the starting point of each walk is chosen to depart at an optimal location. Secondly, this paper designs the indirect verification identity record algorithm and the layer degree of confirmation principle are designed to realize the improved IOTA protocol's resilience and resistance to Parasite chain attack. The experimental results show that the improved IOTA using random function to select the midway walk starting point from i-50λ, to i-75λsubstantially solves the system computational burden problem and greatly reduces the cumulative weight update delay. © 2023 IEEE.

关键词： cumulative weight IOTA midway walk Parasite chain attack

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Object Detection in SAR images via Gaussian Flow Class-Balanced Differential Aggregation

Few-Shot Object Detection in SAR images via Gaussian Flow Cl...

引用

signal, Information and Data processing (ICSIDP), IEEE International Conference on

作者： Po Zhao Jie Chen Chaochen Zhang Ke Ma Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Electronics and Information Engineering Anhui University Hefei China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

Currently, few-shot object detection (FSOD) methods for synthetic aperture radar (SAR) images are severely understudied. The high confidentiality and scarcity of SAR data, coupled with the susceptibility of targets in SAR images to significant changes in orientation, make existing models sensitive to variations in novel class examples. This sensitivity leads to challenges in extracting class prototypes and accurately estimating class centers for novel classes. To solve the above issues, we propose a few-shot object detection algorithm for SAR images via Gaussian Flow Class-Balanced Differential Aggregation. Specifically, we first design a class-balanced difference feature aggregation module to solve the problems of difficult class distribution estimation and inaccurate class center estimation of novel classes in SAR images. Second, the contextual information perception module is designed to extract the most representative support features into fine-grained prototypes and aggregate them with the query features using the matching paradigm to solve the imbalance between foreground targets and background in SAR images. Finally, experimental results on MSAR-AIR dataset indicate that our model realizes the best detection properties on SAR images compared to existing models.

关键词： Representation learning Sensitivity Prototypes Estimation Object detection Interference Feature extraction Radar polarimetry Data models Synthetic aperture radar

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 3

Research on patent classification based on hierarchical labe...

引用

3rd International Conference on Education, Knowledge and Information Management, ICEKIM 2022

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

ISBN: (纸本)9781665416665

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. © 2022 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Electrochemical protein biosensors for disease marker detection:progress and opportunities

引用

Microsystems & Nanoengineering 2024年第3期10卷 1-20页

作者： Lanpeng Guo Yunong Zhao Qing Huang Jing Huang Yanbing Tao Jianjun Chen Hua-Yao Li Huan Liu School of Integrated Circuits Wuhan National Laboratory for OptoelectronicsOptics Valley LaboratoryHuazhong University of Science and TechnologyWuhan 430074China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Integrated CircuitsAnhui UniversityHefei 230601China School of Optoelectronic Materials and Technology Jianghan UniversityWuhan 430056China Department of Otorhinolaryngology Union HospitalTongji Medical CollegeHuazhong University of Science and Technology1277 Jiefang AvenueWuhan 430022China Wenzhou Institute of Advanced Manufacturing Technology Huazhong University of Science and TechnologyWenzhou 325000China

The development of artificial intelligence-enabled medical health care has created both opportunities and challenges for next-generation biosensor *** are extensively used as biological macromolecular markers in disease diagnosis and the analysis of therapeutic *** protein biosensors have achieved desirable specificity by using the specific antibody–antigen binding principle in ***,the active centers of protein biomarkers are surrounded by a peptide matrix,which hinders charge transfer and results in insufficient sensor ***,electrode-modified materials and transducer devices have been designed to increase the sensitivity and improve the practical application prospects of electrochemical protein *** this review,we summarize recent reports of electrochemical biosensors for protein biomarker *** highlight the latest research on electrochemical protein biosensors for the detection of cancer,viral infectious diseases,inflammation,and other *** corresponding sensitive materials,transducer structures,and detection principles associated with such biosensors are also addressed ***,we present an outlook on the use of electrochemical protein biosensors for disease marker detection for the next few years.

关键词： diagnosis specificity Electrochemical

来源：评论

学校读者我要写书评

暂无评论

Enhanced Breakdown Voltage of p-GaN HEMT with a Lateral Gradient in Barrier Layer Component

Enhanced Breakdown Voltage of p-GaN HEMT with a Lateral Grad...

引用

IEEE International Workshop on Radio-Frequency Integration Technology (RFIT)

作者： Wei Zhi Xingang Ren Hui Wang Shubin Zhao Gang Wang Shuping He Zhixiang Huang Xianliang Wu Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui University Hefei China Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei China Anhui Province Key Laboratory of Simulation and Design for Electronic Information System Hefei Normal University Hefei China Key Laboratory of Intelligent Computing & Signal Processing Anhui University Hefei China

ISBN: (数字)9798331541095

ISBN: (纸本)9798331541101

In this paper, an optimized enhanced-mode p-GaN high electron mobility transistor (p-GaN HEMT) is proposed, in which the barrier layer is set into a composite structure with a lateral gradient of Aluminum component (LGC) from the drain edge under the gate towards both source and drain, respectively. By leveraging the polarization effects from different heterojunctions, a two-dimensional electron gas (2DEG) with gradually changing density is formed laterally in the channel layer, which more precisely modulates the electric field distribution in the gate-drain region, enhances the voltage resistance of it, and reduces leakage current, thereby enhancing the breakdown voltage of the device and improving the output performance. The breakdown voltage of the proposed optimized LGC-HEMT under simulation is 716.73V, which is 13.1 % higher than that of the conventional p-GaN HEMT (633.64V), while the specific on-resistance $(\mathrm{R}_{\mathrm{o}\mathrm{n},\mathrm{s}\mathrm{p}})$ is only 1.34 $m\Omega\cdot cm^{2}$ , and the Baliga's figure of merit (BFOM) changes from 216.42 to 382.68 $MW/cm^2$ , which is 76.82% higher, hinting at the promising potential of the proposed HEMT.

关键词： Resistance Radio frequency Performance evaluation Breakdown voltage HEMTs Logic gates Impact ionization Leakage currents MODFETs Electric fields

来源：评论

学校读者我要写书评

暂无评论

RETRACTED ARTICLE: ZpZp2 -linear codes: rank and kernel

引用

Designs, Codes, and Cryptography 2023年第2期91卷 693-693页

作者： Shi, Minjia Wang, Shukai Li, Xiaoxiao Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Mathematical Sciences Anhui University Anhui Hefei China

来源：评论

学校读者我要写书评

暂无评论

Efficient CDI-FDTD Method for Modelling Graphene-Based Structures

Efficient CDI-FDTD Method for Modelling Graphene-Based Struc...

引用

2023 International Applied Computational Electromagnetics Society Symposium, ACES-China 2023

作者： Liu, Jiale Xie, Guoda Huang, Zhixiang Education of Anhui Province Anhui Province Key Laboratory of Target Recognition and Feature Extraction Anhui Luan237000 China Ministry of Education The Key Laboratory of Intelligent Computing and Signal Processing Hefei China Anhui Province Anhui University Key Laboratory of Electromagnetic Environmental Sensing Hefei230601 China Anhui University Hefei China

ISBN: (纸本)9781733509657

This paper presents a novel approach for calculating graphene-based structures in the complying divergence implicit finite-difference time-domain (CDI-FDTD) method. To begin, the differential iteration formula of graphene structure in the CDI-FDTD method is derived utilizing the auxiliary-differential-equation (ADE) method. Next, the transmission characteristics of an infinite graphene sheet in an open space are investigated by conducting simulation analyses within the CDI-FDTD framework, considering various magnetostatic or electrostatic biases. Finally, the simulation results were compared with analytical solutions and the results obtained from traditional FDTD methods, confirming the unconditional stability and reliability of the proposed method. © 2023 Applied Computational Electromagnetics Society (ACES).

关键词： Graphene

来源：评论

学校读者我要写书评

暂无评论

A Wideband Millimeter-wave Bidirectional OAM Antenna using sequential rotation feeding 4

A Wideband Millimeter-wave Bidirectional OAM Antenna using s...

引用

4th International Applied Computational Electromagnetics Society Symposium in China, ACES-China 2021

作者： Wu, Jie Feng, Jian Huang, Zhixiang Wu, Xianliang Key Laboratory of Intelligent Computing Signal Processing Anhui University Ministry of Education Hefei China

ISBN: (纸本)9781733509619

A wideband bidirectional circularly polarized (CP) orbital angular momentum (OAM) antenna array is proposed for millimeter-wave frequency. The designed antenna array is composed of four bidirectional radiating dual-CP antenna units that rotate 90 degrees sequentially to each other in the clockwise direction. Results indicate that the left-hand circular polarization (LHCP) with a mode l-{OAM}=-1 in +z direction and right-hand circular polarization (RHCP) with a mode l-{OAM}=+1 in -z direction, over a wide impedance and 3-dB axial ratio (AR) relative bandwidth of 32.3% from 26 to 36 GHz. © 2021 Applied Computational Electromagnetics Society (ACES).

关键词： Antenna arrays

来源：评论

学校读者我要写书评

暂无评论

ZTrans: A new Transformer for Speech Enhancement 4

ZTrans: A new Transformer for Speech Enhancement

引用

4th International Conference on Information Communication and signal processing, ICICSP 2021

作者： Guo, Yucheng Yu, Weiwei Zhou, Jian Key Laboratory of Intelligent Computing and Signal Processing Anhui University Anhui University HeFei China

ISBN: (纸本)9781665407571

At present, Transformer architectures based on the self-attention mechanism have attracted wide attention due to their excellent performance in many fields, such as natural language processing and computer vision. However, in the field of speech processing, the potential of Transformer architectures has not been fully utilized. The main reason is that the position embedding mechanism in the Transformer cannot effectively perform sequence modeling in speech tasks, and the Transformer itself is challenging to train and converge. Inspired by recent research, we propose a new speech enhancement in this paper. Specifically, a recurrent neural network is used to replace the position embedding in Transformer, and the fully connected layer in the Transformer feed forward layer is replaced with one-dimensional convolution. In addition, the model also introduces a weighted residual connection mechanism. Experiment results show that compared with baseline models, the new model performs better in speech quality and speech intelligibility. At the same time, the convergence and inference speed are also much improved. Compared with the baseline model, the processing speed of the proposed method is increased by 4.27 times. © 2021 IEEE.

关键词： Recurrent neural networks

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：