检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Wang, Xianlong Li, Minghui Liu, Wei Zhang, Hangtao Hu, Shengshan Zhang, Yechao Zhou, Ziqi Jin, Hai National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China

Traditional unlearnable strategies have been proposed to prevent unauthorized users from training on the 2D image data. With more 3D point cloud data containing sensitivity information, unauthorized usage of this new type data has also become a serious concern. To address this, we propose the first integral unlearnable framework for 3D point clouds including two processes: (i) we propose an unlearnable data protection scheme, involving a class-wise setting established by a category-adaptive allocation strategy and multi-transformations assigned to samples;(ii) we propose a data restoration scheme that utilizes class-wise inverse matrix transformation, thus enabling authorized-only training for unlearnable data. This restoration process is a practical issue overlooked in most existing unlearnable literature, i.e., even authorized users struggle to gain knowledge from 3D unlearnable data. Both theoretical and empirical results (including 6 datasets, 16 models, and 2 tasks) demonstrate the effectiveness of our proposed unlearnable framework. Our code is available at https://***/CGCL-codes/UnlearnablePC. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An attention-based syntax-tree and tree-LSTM model for sentence summarization

引用

International Journal of Performability Engineering 2017年第5期13卷 775-782页

作者： Liu, Wenfeng Liu, Peiyu Yang, Yuzhen Gao, Yaling Yi, Jing School of Information Science and Engineering Shandong Normal University Jinan250014 China Department of Computer and Information Engineering Heze University Heze274015 China Shandong Provincial Key Laboratory for Distributed Computer Software Novel Technology Jinan250014 China Ruipu Peony Industrial Technology Development Co. Ltd 274015 China School of Computer Science and Technology Shandong Jianzhu University Jinan250101 China

Generative Summarization is of great importance in understanding large-scale textual data. In this work, we propose an attention-based Tree-LSTM model for sentence summarization, which utilizes an attention-based syntactic structure as auxiliary information. Thereinto, block-alignment is used to align the input and output syntax blocks, while inter-alignment is used for alignment of words within that of block pairs. To some extent, block-alignment can prevent structural deviations on the long sentences and inter-alignment is capable of increasing the flexibility of the generation in the blocks. This model can be easily trained to end-to-end mode and deal with any length of the input sentences. Compared with several relatively strong baselines, our model has achieved the state-of-art on DUC-2004 shared task. © 2017 Totem Publisher, Inc. All rights reserved.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Epilepsy Classification for Mining Deeper Relationships between EEG Channels based on GCN

Epilepsy Classification for Mining Deeper Relationships betw...

引用

computer Vision, Image and Deep Learning (CVIDL), International Conference on

作者： Xin Chen Yuanjie Zheng Yi Niu Chengiiang Li School of Information Science and Engineering Shandong Normal University Jinan China Key Lab of Intelligent Computing and Information Security Universities of Shandong Jinan China Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology Institute of Biomedical Sciences Jinan China Shandong University of Science and Technology Jinan China

ISBN: (数字)9781728194813

ISBN: (纸本)9781728194820

Epilepsy is a brain disorder caused by abnormal discharges of neurons in brain. It is one of the most commonly studied disorders in neurology. The research of epilepsy electroencephalogram (EEG) has become a hot research topic. We find that in epilepsy EEG detection task, many previous methods focused on directly collecting the data of each channel, but these methods seldom analyse relationships between signals. Therefore, we propose the Epilepsy EEG Graph Convolutional Network EGCN, which makes full use of correlations between channels to deeply mine data information. We specifically design 5-layer graph convolutional network structure for classification of healthy and epileptic patients. The method is applied to public data set (Boon and CHB-MIT) to establish a reasonable classification model. And we compare it with some advanced algorithms. The experimental results show that the E-GCN method is superior to many existing methods in classification accuracy. In brief, the E-GCN method can be effectively used in classification and detection for epilepsy. This provides new ideas for colleagues, who study epilepsy EEG. In addition, this also provides richer experience for diagnosis of epilepsy.

关键词： Epilepsy Electroencephalography Convolution Brain modeling Feature extraction Correlation Task analysis

来源：评论

学校读者我要写书评

暂无评论

APR-LR: an approach to label ranking

引用

Journal of Computational Information Systems 2013年第7期9卷 2873-2879页

作者： Zhang, Shun Zhang, Huaxiang Cao, Linlin Liu, Li School of Information Science and Engineering Shandong Normal University Jinan 250014 China Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology China

Label ranking is a complex prediction task, in which the goal is to map instances to a total order over a finite set of predefined labels. To solve this problem, a novel approach named APRiori based Label Ranking (APR-LR) is proposed in this paper. APR-LR classifies the data using traditional multi-label classification methods, and ranks the labels of each instance based on the Apriori algorithm taking the effect of neighbors of an instance into account at the same time. Experiments show that, APR-LR outperforms the other label ranking algorithms in terms of two evaluation metrics. Copyright © 2013 Binary Information Press.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Personalized recommendation based on link prediction in dynamic super-networks

Personalized recommendation based on link prediction in dyna...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： Wang Hong Yanshen Sun Xiaomei Yu Institute of Information Science and Engineering Shandong Normal University Jinan Shandong CN Zhejiang University Hangzhou China Institute of Information Science and Engineering Shandong Normal University Jinan China Shandong Provincial Key Laboratory for Distributed Computer Software Novel Technology Jinan China

Personalized recommendation is one of the most effective methods to solve the problem of information overloading. As many real existing systems in nature, a recommendation system can also be considered as a complex network system, so we can do personalized recommendation by using the link prediction method which is a new one in complex networks research area. In this paper, we present personalized recommendation method based on the link prediction in Super-networks. Firstly, we give several definitions such as a Super-network, a dynamic Super-network and a utility matrix etc. Secondly, we construct a personalized recommendation model based on these definitions. Thirdly, we define a similarity metric for users and some similarity criteria, put forward five link prediction related algorithms in dynamic Supernetworks and present our recommendation algorithms based on these link prediction algorithms. Finally, we apply our methods to classic datasets in order to evaluate the performance of our algorithms.

关键词： Prediction methods Heuristic algorithms Algorithm design and analysis Complex networks Prediction algorithms Internet Social network services

来源：评论

学校读者我要写书评

暂无评论

Hybrid collaborative filtering recommendation based on time and diversity

引用

ICIC Express Letters, Part B: Applications 2015年第9期6卷 2539-2545页

作者： Wang, Hong Sun, Yanshen Yu, Xiaomei Wang, Jihua School of Information Science and Engineering Shandong Normal University No. 88 East Wenhua Road Jinan China Shandong Provincial Key Laboratory for Distributed Computer Software Novel Technology No. 88 East Wenhua Road Jinan China School of Earth Sciences Zhejiang University No. 388 Yuhangtang Road Hangzhou China

Many researchers have been attracted in personalized recommendation which is considered as one of the most effective methods to solve the problem of information overloading. We propose a hybrid collaborative filtering recommendation method based on time and diversity in this paper. Firstly, we construct a personalized recommendation model by using an improved frequent item mining method and an improved visibility graph, thus making us obtain user-item networks and user-user networks. Secondly, we define concepts of similarity and similarity index and then put forward a revised recommendation algorithm in the user-user networks based on link mining and diversity. Finally, we apply our methods to four classic datasets in order to evaluate the performance of our algorithms. Experimental results show that our methods do better than traditional collaborative filtering methods and content based recommendation methods in precision, recall and time. © 2015 ISSN 2185-2766

关键词： Visibility

来源：评论

学校读者我要写书评

暂无评论

科学研究的第五范式——以智能驱动的材料设计为例

引用

Engineering 2023年第5期24卷 126-137,I0003,I0004页

作者： Can Leng Zhuo Tang Yi-Ge Zhou Zean Tian Wei-Qing Huang Jie Liu Keqin Li Kenli Li Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense TechnologyChangsha 410073China Laboratory of Software Engineering for Complex Systems National University of Defense TechnologyChangsha 410073China National Supercomputing Center in Changsha Changsha 410082China College of Computer Science and Electronic Engineering Hunan UniversityChangsha 410082China Institute of Chemical Biology and Nanomedicine State Key Laboratory of Chemo/Biosensing and ChemometricsCollege of Chemistry and Chemical EngineeringHunan UniversityChangsha 410082China Department of Applied Physics School of Physics and ElectronicsHunan UniversityChangsha 410082China Department of Computer Science State University of New YorkNew PaltzNY 12561USA

科学正在进入一个新时代——第五范式——它被认为是知识整合到不同领域的主要特征,是基于无所不在的机器学习系统的计算社区中智能驱动的工作。在此,我们通过在天河一号超级计算机系统上构建的催化材料专门设计的典型平台案例,生动地... 详细信息

科学正在进入一个新时代——第五范式——它被认为是知识整合到不同领域的主要特征,是基于无所不在的机器学习系统的计算社区中智能驱动的工作。在此,我们通过在天河一号超级计算机系统上构建的催化材料专门设计的典型平台案例,生动地阐明了第五范式的本质,旨在促进第五范式在其他领域的培养。第五范式平台主要包括模型自动构建(原始数据提取)、指纹自动构建(神经网络特征选择)以及跨学科知识串联的重复迭代(“火山图”)。与分解一起进行的是对迭代中实现的体系结构的性能评估。通过讨论,第五范式的智能驱动平台可以极大地简化和改进研究中极其繁琐和具有挑战性的工作,并通过补偿机器学习中缺少样本和替代一些由于计算资源不足而导致的数值计算来实现数值计算与机器学习之间的相互反馈,从而加速探索过程。在数据驱动的学科中,跨学科专家的协同作用和对动态数据需求的急剧增长仍然是一个挑战。我们相信,对第五范式平台的一瞥可以为其在其他领域的应用铺平道路。

关键词：机器学习自动构建天河一号数据驱动神经网络动态数据知识整合科学研究

来源：评论

学校读者我要写书评

暂无评论

DIV： Dynamic Integrity Validation Framework for Detecting Compromises on Virtual Machine Based Cloud Services in Real Time

引用

China Communications 2014年第8期11卷 15-27页

作者： WANG Chunlu LIU Chuanyi LIU Bin DONG Yingfei School of Computer Science Beijing University of Posts and Telecommunications Beijing 100876 P. R. China School of Software Engineering Beijing University of Posts and Telecommunications Beijing 100876 P. R. China Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Ministry of Education Beijing 100876 P. R. China Department of Electrical Engineering University of Hawaii Honolulu Hawaii U.S.

with the increasing popularity of cloud services,attacks on the cloud infrastructure also increase ***,how to monitor the integrity of cloud execution environments is still a difficult *** this paper,a real-time dynamic integrity validation(DIV) framework is proposed to monitor the integrity of virtual machine based execution environments in the *** can detect the integrity of the whole architecture stack from the cloud servers up to the VM OS by extending the current trusted chain into virtual machine's architecture *** introduces a trusted third party(TTP) to collect the integrity information and detect remotely the integrity violations on VMs periodically to avoid the heavy involvement of cloud tenants and unnecessary information leakage of the cloud *** evaluate the effectiveness and efficiency of DIV framework,a prototype on KVM/QEMU is implemented,and extensive analysis and experimental evaluation are *** results show that the DIV can efficiently validate the integrity of files and loaded programs in real-time,with minor performance overhead.

关键词： cloud security remote attestation trusted computing cloud trustworthiness

来源：评论

学校读者我要写书评

暂无评论

An improved mixed-type data based kernel clustering algorithm

An improved mixed-type data based kernel clustering algorith...

引用

International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)

作者： Min Ren Peiyu Liu Zhihao Wang Xiao Pan School of Mathematic and Quantitative Economics Shandong University of Finance and Economics Jinan Shandong province China School of Information Science and Engineering Shandong Normal University Jinan Shandong province China Shandong Provincial Key Laboratory for Distributed Computer Software Novel Technology Jinan Shandong province China

ISBN: (纸本)9781509040940

Clustering algorithm is often used to analyze the communication data for network intrusion detection system. However, network communication data are mixed, e.g., numerical and categorical data. So, at first, this paper put forward a method for representing the cluster center (prototype) of mixed-type data. Then respectively in combination with the continuity characteristic of the numerical attributes and the semantic feature of the categorical attributes, the dissimilarity measurement formula was improved by use of the Gauss kernel function, on the base of which, defined the objective function. After that this paper further put forward an Improved Mixed-type Data based Kernel Clustering Algorithm (IKCA-MD), which showed a stable clustering result because the initial cluster centers are obtained by Maximum Density and Distance method (MDD). Finally the feasibility and effectiveness of the method for the network intrusion detection were verified by experiments.

关键词： Clustering algorithms Kernel Prototypes Intrusion detection Linear programming Training Testing

来源：评论

学校读者我要写书评

暂无评论

A new fractional-order chaotic complex system and its antisynchronization

Abstract and Applied Analysis

引用

Abstract and Applied Analysis 2014年第1期2014卷

作者： Jiang, Cuimei Liu, Shutang Luo, Chao College of Control Science and Engineering Shandong University Jinan 250061 China School of Information Science and Engineering Shandong Normal University Jinan 250014 China Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology Jinan 250014 China

We propose a new fractional-order chaotic complex system and study its dynamical properties including symmetry, equilibria and their stability, and chaotic attractors. Chaotic behavior is verified with phase portraits, bifurcation diagrams, the histories, and the largest Lyapunov exponents. And we find that chaos exists in this system with orders less than 5 by numerical simulation. Additionally, antisynchronization of different fractional-order chaotic complex systems is considered based on the stability theory of fractional-order systems. This new system and the fractional-order complex Lorenz system can achieve antisynchronization. Corresponding numerical simulations show the effectiveness and feasibility of the scheme. © 2014 Cuimei Jiang et al.

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：