检索结果-内蒙古大学图书馆

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Pu, Xinyan Zhang, Ke Shu, Huazhong Coatrieux, Jean Louis Kong, Youyong Southeast University Ministry of Education Key Laboratory of Computer Network and Information Integration Nanjing China Southeast University Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing School of Computer Science and Engineering Nanjing China Universit de Rennes 1 Ltsi Rennes France Centre de Recherche en Information BioMdicale Sino-Franais Rennes France

ISBN: (纸本)9781728163277

Graph contrastive learning has gained popularity due to its success in self-supervised graph representation learning. Augmented views in contrastive learning greatly determine the quality of the learned representations. Handcrafted data augmentations in previous work require tedious trial-and- errors per dataset, which is time-consuming and resource-intensive. Here, we propose a Graph Contrastive learning framework with Learnable graph Augmentation called GraphCLA. Specifically, learnable graph augmentation trains augmented views by minimizing the mutual information (MI) between the input graphs and their augmented graphs. This paper designs a kernel contrastive loss function based on an end-to-end differentiable graph kernel to learn augmented views. In addition, this paper utilizes a min-max optimization strategy to learn challenging augmented graphs and to learn discriminative representations adversarially. Finally, we compared GraphCLA with state-of-the-art self-supervised learning baselines and experimentally validate the effectiveness of GraphCLA. © 2023 IEEE.

关键词： Contrastive learning data augmentation graph representation learning

来源：评论

学校读者我要写书评

暂无评论

Graph Contrastive Learning with Learnable Graph Augmentation

Graph Contrastive Learning with Learnable Graph Augmentation

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Xinyan Pu Ke Zhang Huazhong Shu Jean Louis Coatrieux Youyong Kong Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing China LTSI Universit de Rennes 1 Rennes France Centre de Recherche en Information BioMdicale Sino-Franais Rennes France

关键词： Representation learning Self-supervised learning Signal processing Benchmark testing Acoustics Kernel Speech processing

来源：评论

学校读者我要写书评

暂无评论

TSUnet-CC: Temporal Spectrogram Unet embedding Cross Channel-wise attention mechanism for MDD identification

TSUnet-CC: Temporal Spectrogram Unet embedding Cross Channel...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： C. Yang Z. Sun F. Zhang H. Shu J. Li W. Xiang Key Laboratory of Computer Network and Information Integration of Ministry of Education Southeast University China Jiangsu Provincal Joint International Research Laboratory of Medical Information Processing Southeast University China Centre de Recherche en Information Biomédicale Sino-français Southeast University China Université de Rennes 1 France Jiangsu Province Engineering Research Center for Smart Wearable and Rehabilitation Devices School of Biomedical Engineering and Informatics Nanjing Medical University Nanjing China

Automatic detection of major depressive disorder (MDD) with multiple-channel electroencephalography (EEG) signals is of great significance for treatment of the mental diseases. In a U-net network, clear EEG signals are fed to obtain temporal feature tensor through encoder and decoder networks with several convolution operations. Moreover, the clear EEG signals can be converted into multi-scale spectrogram to obtain the rich saliency information and then the spectrogram feature tensor can be extracted by another symmetrical U-net. The temporal and spectrogram feature tensors can provide more comprehensive information, but may also contain redundant information, which may affect the detection of MDD. To deal with such issue, this paper proposed a novel Temporal Spectrogram Unet (TSUnet-CC), which embeds the cross channel-wise attention mechanism for multiple-channel EEGbased MDD identification. We make three novel contributions: 1. multi-scale saliency-encoded spectrogram using Fourierbased approach to capture rich saliency information under different scales, 2) TSUnet network using a symmetrical twostream U-net architecture that learns multiple temporal and spectrogram feature tensors in time and frequency domains, and 3) cross channel-wise block enabling the larger weights of key feature channels that contain MDD information. The leaveone-subject-out experiments show that our proposed TSUnetCC gains high performance with a classification accuracy up to 98.55% and 99.22% in eyes closed and eyes open datasets, which outperformed some state-of-the-art methods and revealed its clinical potential.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analysis and Improvement of an Efficient Controlled Quantum Secure Direct Communication and Authentication Protocol

引用

computers, Materials & Continua 2018年第12期57卷 621-633页

作者： Jifeng Zhong Zhihao Liu Juan Xu Navigation College Jimei UniversityXiamen361021China School of Computer Science and Engineering Southeast UniversityNanjing211189China Key Laboratory of Computer Network and Information Integration Southeast UniversityMinistry of EducationNanjing211189China Institute for Quantum Computing University of WaterlooWaterlooONCanadaN2L3G1

The controlled quantum secure direct communication(CQSDC)with authentication protocol based on four particle cluster states via quantum one-time pad and local unitary operations is *** is found that there are some serious security issues in this *** eavesdropper(Eve)can eavesdrop on some information of the identity strings of the receiver and the controller without being detected by the selective-CNOT-operation(SCNO)*** the same attack,Eve can also steal some information of the secret message that the sender *** addition,the receiver can take the same kind of attack to eavesdrop on some information of the secret message out of the control of the *** means that the requirements of CQSDC are not *** last,we improve the original CQSDC protocol to a secure one.

关键词： Quantum cryptography controlled quantum secure direct communication selective-CNOT-operation attack

来源：评论

学校读者我要写书评

暂无评论

Deep octonion networks

arXiv

引用

arXiv 2019年

作者： Wu, Jiasong Xu, Ling Kong, Youyong Senhadji, Lotfi Shu, Huazhong Laboratory of Image Science and Technology Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing210096 China INSERM U1099 RennesF-35000 France Université de Rennes 1 LTSI RennesF-35042 France

Deep learning is a research hot topic in the field of machine learning. Real-value neural networks (Real NNs), especially deep real networks (DRNs), have been widely used in many research fields. In recent years, the deep complex networks (DCNs) and the deep quaternion networks (DQNs) have attracted more and more attentions. The octonion algebra, which is an extension of complex algebra and quaternion algebra, can provide more efficient and compact expression. This paper constructs a general framework of deep octonion networks (DONs) and provides the main building blocks of DONs such as octonion convolution, octonion batch normalization and octonion weight initialization;DONs are then used in image classification tasks for CIFAR-1. and CIFAR-1.0 data sets. Compared with the DRNs, the DCNs, and the DQNs, the proposed DONs have better convergence and higher classification accuracy. The success of DONs is also explained by multi-task learning. Copyright © 201., The Authors. All rights reserved.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Fractional spectral graph wavelets and their applications

arXiv

引用

arXiv 2019年

作者： Wu, Jiasong Wu, Fuzhi Yang, Qihan Kong, Youyong Liu, Xilin Zhang, Yan Senhadji, Lotfi Shu, Huazhong LIST Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing210096 China International Joint Research Laboratory of Information Display and Visualization Southeast University Ministry of Education Nanjing210096 China INSERM U 1099 Université de Rennes 1 LTSI Rennes35000 France Centre de Recherche en Information Biomédicale Sino-francais Nanjing210096 China College of Data Science Taiyuan University of Technology Taiyuan030024 China

One of the key challenges in the area of signal processing on graphs is to design transforms and dictionaries methods to identify and exploit structure in signals on weighted graphs. In this paper, we first generalize graph Fourier transform (GFT) to graph fractional Fourier transform (GFRFT), which is then used to define a novel transform named spectral graph fractional wavelet transform (SGFRWT), which is a generalized and extended version of spectral graph wavelet transform (SGWT). A fast algorithm for SGFRWT is also derived and implemented based on Fourier series approximation. The potential applications of SGFRWT are also presented. Copyright © 201., The Authors. All rights reserved.

关键词： Signal processing

来源：评论

学校读者我要写书评

暂无评论

Tensor object classification via multilinear discriminant analysis network 40

Tensor object classification via multilinear discriminant an...

引用

40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 201.

作者： Zeng, Rui Wu, Jiasong Senhadji, Lotfi Shu, Huazhong LIST Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing China INSERM U 1099 Rennes France Laboratoire Traitement du Signal et de l'Image Universit de Rennes 1 Rennes France France

ISBN: (纸本)9781467369978

This paper proposes an multilinear discriminant analysis network (MLDANet) for the recognition of multidimensional objects, knows as tensor objects. The MLDANet is a variation of linear discriminant analysis network (LDANet) and principal component analysis network (PCANet), both of which are the recently proposed deep learning algorithms. The MLDANet consists of three parts: 1. The encoder learned by MLDA from tensor data. 2) Features maps obtained from decoder. 3) The use of binary hashing and histogram for feature pooling. A learning algorithm for MLDANet is described. Evaluations on UCF1. database indicate that the proposed MLDANet outperforms the PCANet, LDANet, MPCA+LDA, and MLDA in terms of classification for tensor objects. © 201. IEEE.

关键词： Deep learning LDANet MLDANet PCANet tensor object classification

来源：评论

学校读者我要写书评

暂无评论

Quantitative Measurement of Coronary Artery Stenosis in CCTA Images Using a 2D Parametric Intensity Model

Quantitative Measurement of Coronary Artery Stenosis in CCTA...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society

作者： Guanyu YANG Xinglou ZHAO Lijun TANG Huzhong SHU Christine TOUMOULIN Lab of Image Science and Technology Key Laboratory of Computer Network and Information Integration (Southeast University) Dept. of Radiology the First Affiliated Hospital of Nanjing Medical University INSERM-U1099 LTSI Universite de Rennes 1

ISBN: (纸本)9781424479276

In this paper, we propose an approach based on 2D vessel model to segment the vessel lumen in three-dimensional coronary computed tomographic angiography (CCTA) images. The 2D parametric intensity model is introduced first to simulate the intensity distribution of vessel lumen with different size in the longitudinal images. Then the Levenberg-Marquardt method is applied to fit the model within a series of region-of interests defined in the longitudinal image. The estimated parameters of the model are employed to define the boundary points of vessel lumen. The detected boundary points of vessel lumen in six longitudinal images are transformed to the cross-sectional planes in order to calculate the degree of stenosis according to the luminal areas. Our proposed method was evaluated in ten CCTA images with ten reported non-calcified stenosis. The degree of each stenosis was computed according to the luminal area and compared with the standard reference given by radiologists. Experimental results show that our method can estimate the degree of stenosis with a high accuracy.

关键词： Image segmentation Arteries Fitting Solid modeling Three-dimensional displays Computational modeling Accuracy

来源：评论

学校读者我要写书评

暂无评论

Evolutionary cryptography theory based generating method for a secure Koblitz elliptic curve and its improvement by a hidden Markov models

引用

Science China(information Sciences) 2012年第4期55卷 911-920页

作者： WANG Chao 1.ZHANG HuanGuo 2,3 & LIU LiLi 4 1.key Lab of Specialty Fiber Optics and Optical Access {1.,Ministry of Education,Shanghai University,Shanghai 200072,China 2 computer School of Wuhan University,Wuhan 430072,China 3 key laboratory of Aerospace information Security and Trusted Computing Ministry of Education,Wuhan 430072,China 4 Huawei Technologies CO.LTD.,Shanghai 201.06,China 1. Key Lab of Specialty Fiber Optics and Optical Access Network Ministry of Education Shanghai University Shanghai 200072 China2. Computer School of Wuhan University Wuhan 430072 China3. Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education Wuhan 430072 China4. Huawei Technologies CO. LTD. Shanghai 201206 China

Considering potential attacks from cloud-computing and quantum-computing,it is becoming nec-essary to provide higher security elliptic *** hidden Markov models are introduced for designing the trace-vector computation algorithm to accelerate the search for elliptic curve (EC) *** present a new algorithm for secure Koblitz EC generation based on evolutionary cryptography *** algorithm is tested by selecting a secure Koblitz EC over the field F(2 2000),with experiments showing that both the base field and base point of the secure curve generated exceed the parameter range for Koblitz curves recommended by *** base fields generated go beyond 1.00 bits,which is higher than the 571.bits recommended by *** also find new secure curves in the range F(2 1.3)-F(2 571. recommended by *** perform a detailed security analysis of those secure curves,showing that those we propose satisfy the same security criteria as NIST.

关键词： secure EC selection evolutionary cryptography theory ant colony algorithm Koblitz EC HMM

来源：评论

学校读者我要写书评

暂无评论

Restrictive mechanism of flow control among non-cooperative Internet users

引用

Science China(information Sciences) 2011年第1期54卷 12-22页

作者： TAO Jun1.2,ZHONG Xiao1.2 & LU YiFei1.2 1.0} {1. of computer network and information integration,Southeast University, Ministry of Education,Nanjing 21.096,China 2School of computer Science and Engineering,Southeast University,Nanjing 21.096,China 1. Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing 210096 China2. School of Computer Science and Engineering Southeast University Nanjing 210096 China

The flow and congestion control methods based on one-shot game model with non-cooperative game theory can explain the non-cooperative behavior of Internet ***,the low effciency of equilibrium solutions affects their *** the behavior of flow and congestion control based on infinitely repeated game models is addressed;the repeated and infinitely repeated flow and congestion control game model is presented; the existence and optimization of the Nash equilibrium point are proved;the discount factor in repeated game is discussed;the punishment and threat strategy to users'misbehavior is studied in N-users infinitely flow control game;the punishment restrictive method of users'behavior is designed in infinitely and finitely games;finally,a flow control algorithm based on repeated game,FCAR,is provided based on the conclusions of repeated game *** results of experiment and simulation show that FCAR algorithm could regularize and restrict users' misbehavior *** algorithm can also make non-cooperative Internet users achieve cooperation in order to optimize the utility of the whole flow and congestion control system.

关键词： Nash equilibrium utility infinitely and finitely repeated game flow and congestion control

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：