检索结果-内蒙古大学图书馆

12th IEEE Global Conference on Consumer Electronics, GCCE 2023

作者： Zhang, Jun Yue, Kun School of Information Science and Engineering Yunnan University Kunming China Yunnan Key Laboratory of Intelligent Systems and Computing Yunnan University Kunming China

ISBN: (纸本)9798350340181

Node classification is to predict the labels of the unlabeled nodes in a graph, which is useful for various applications of social network and biological information analysis. To measure the uncertainty of structural information, we propose the structural entropy theory based method for graph node classification. First, we calculate the structural entropy of different graph structures, since the smaller the structural entropy, the less the uncertainty of the structural relationship in the graph. Then, we use the minimal structural entropy to determine the uncertainty of graphical structures. Finally, the nodes with similar structural relationships in the graph are classified. Experimental results show that our method outperforms some state-of-the-art competitors. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

A Method for Measuring Node Similarity in Heterogeneous information Networks 9

A Method for Measuring Node Similarity in Heterogeneous Info...

引用

9th International Conference on Fuzzy systems and Data Mining, FSDM 2023

作者： Zhan, Liudi Chen, Hongmei Zhou, Lihua Xiao, Qing School of Information Science and Engineering Yunnan University Kunming China Yunnan Key Laboratory of Intelligent Systems and Computing Yunnan University Kunming China

ISBN: (纸本)9781643684703

Meta-path-based methods for measuring the similarities between nodes in Heterogeneous information Networks (HINs) have attracted attention from researchers due to excellent performance. However, these methods suffer from some issues: (1) it is difficult for users to provide effective meta-paths of complex HINs;(2) it is inefficient to enumerate all instances of meta-paths. In order to solve the above issues, this paper proposes a novel method, K-order Neighbors based Heterogeneous Graph Neural Network (KN-HGNN), for measuring node similarity. Firstly, KN-HGNN generates meta-paths based on network schema. Then, KN-HGNN obtains the features of nodes by aggregating itself type feature and its k-order neighbors' type features under the constraints of meta-paths. Finally, KN-HGNN calculates the similarities between nodes based on the features of nodes. The experimental results on real datasets show that KN-HGNN outperforms the baselines. © 2023 The authors and IOS Press.

关键词： information services

来源：评论

学校读者我要写书评

暂无评论

Graph Neural Network with Heterogeneous Attributes for Node Classification 4

Graph Neural Network with Heterogeneous Attributes for Node ...

引用

4th International Conference on Neural Networks, information and Communication Engineering, NNICE 2024

作者： Jiang, Bohou Wang, Jiahui Yue, Kun Yunnan University School of Information Science and Engineering Kunming China Yunnan University Yunnan Key Laboratory of Intelligent Systems and Computing Kunming China

ISBN: (纸本)9798350394375

Node classification on heterogeneous graphs with multiple node types and relationships has been widely used in commodity classification, friend recommendation, and so on. Most of the existing models need to define the meta paths manually with incomplete attribute information, leading to the low accuracy of classification. To improve the accuracy of node classification task, we propose a novel graph neural network with heterogeneous attributes (GNNHA) by introducing the heterogeneous attributes of nodes and edges without defining meta paths. First, we design a spatial mapping for heterogeneous edges by mapping and fusing the source and target nodes to a hidden layer space. Then, we make a unique linear projection for each node to obtain the embeddings containing the attributes of nodes and edges by aggregating the information of neighbor nodes. Finally, we provide an improved loss function by leveraging the information loss of mapping and node class imbalance. Our model can capture more complete heterogeneous graph attributes and obtain more objective and accurate classification results. Experimental results show that our proposed model outperforms state-of-the-art ones. © 2024 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks 1

引用

16th European Conference on Computer Vision, ECCV 2020

作者： Liu, Yunfei Ma, Xingjun Bailey, James Lu, Feng State Key Laboratory of Virtual Reality Technology and Systems School of CSE Beihang University Beijing China Peng Cheng Laboratory Shenzhen China School of Information Technology Deakin University Geelong Australia School of Computing and Information Systems University of Melbourne Parkville Australia

ISBN: (数字)9783030586072

ISBN: (纸本)9783030586065

Recent studies have shown that DNNs can be compromised by backdoor attacks crafted at training time. A backdoor attack installs a backdoor into the victim model by injecting a backdoor pattern into a small proportion of the training data. At test time, the victim model behaves normally on clean test data, yet consistently predicts a specific (likely incorrect) target class whenever the backdoor pattern is present in a test example. While existing backdoor attacks are effective, they are not stealthy. The modifications made on training data or labels are often suspicious and can be easily detected by simple data filtering or human inspection. In this paper, we present a new type of backdoor attack inspired by an important natural phenomenon: reflection. Using mathematical modeling of physical reflection models, we propose reflection backdoor (Refool) to plant reflections as backdoor into a victim model. We demonstrate on 3 computer vision tasks and 5 datasets that, Refoolcan attack state-of-the-art DNNs with high success rate, and is resistant to state-of-the-art backdoor defenses. © 2020, Springer Nature Switzerland AG.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Unequal-interval based loosely coupled control method for auto-scaling heterogeneous cloud resources for web applications

Unequal-interval based loosely coupled control method for au...

引用

作者： Cai, Zhicheng Liu, Duan Lu, Yifei Buyya, Rajkumar School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China Laboratory School of Computing and Information Systems The University of Melbourne ParkvilleVIC Australia

Most existing quality of service (QoS) control algorithms of Web applications take into account Web Server or database connections which can be released immediately. However, many applications are deployed on virtual machines (VMs) or even Spot VMs elastically rented from public clouds. To save costs, interval-priced VMs are not released until the ends of rented intervals. Such delays of control effects make existing methods rent or release excess VMs leading to overcontrol. Fluctuated prices make Spot VMs unreliable due to unexpected termination which makes fault-tolerant strategies crucial. In this article, an unequal-interval-based loosely coupled control method is proposed to improve the quality of service (QoS) control ability of fault-tolerant strategies. A queuing model with arrival-rate-adjustment coefficient is used to predict required capacity as a feedforward controller. Another two-threshold and queuing-model-based method is applied to update the coefficient as a loosely coupled feedback controller. Meanwhile, unequal-interval controller collaborating method is proposed to avoid overcontrol and react quickly to workload changes. Our approach is evaluated on both a simulation platform and a real Kubernetes Cluster. Experimental results illustrate that our approach decreases the percentage of waiting times larger than service level agreements with similar or lower rental costs compared with existing algorithms. © 2020 John Wiley & Sons, Ltd.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

Bridging the Gap using Contrastive Learning and Semantic Consistency for Unsupervised Neural Machine Translation 5

Bridging the Gap using Contrastive Learning and Semantic Con...

引用

5th International Conference on Artificial Intelligence and Computer Engineering, ICAICE 2024

作者： Zhang, Chuancai Qu, Dan Du, Liming Yang, Kaiyuan School of Information Systems Engineering University of Information Engineering Zhengzhou China Laboratory for Advanced Computing and Intelligence Engineering Zhengzhou China School of Cyberspace Security Zhengzhou University Zhengzhou China

ISBN: (纸本)9798331528911

In Unsupervised Neural Machine Translation (UNMT) tasks, the lack of extensive parallel corpora makes it challenging for the model to directly optimize the correspondence between the source and target languages. UNMT models primarily rely on learning from monolingual data, making it difficult to fully capture cross-linguistic semantic alignment and consistency during training. Therefore, effectively enhancing semantic alignment between the source and target languages under unsupervised conditions has become a key challenge in the field of UNMT. To address this issue, this study proposes a semantic alignment and consistency enhancement mechanism based on contrastive learning, aiming to improve the model's ability to capture cross-lingual semantic differences by constructing an optimization objective focused on semantic consistency. The method utilizes a pretrained cross-lingual model to generate semantic embeddings for both the source and target languages, then designs a contrastive learning-based loss function that minimizes the semantic distance between correct translations and source sentences while increasing the semantic distance between incorrect translations and source sentences, thereby enhancing the model's performance in semantic consistency. The experiments validate the effectiveness and broad applicability of the semantic consistency optimization method based on contrastive learning, demonstrating great potential and advantages, especially in multilingual tasks of UNMT. The model achieved significant improvements in BLEU scores across various language pairs. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Analysis Model of Terrorist Attacks Based on Big Data 32

Analysis Model of Terrorist Attacks Based on Big Data

引用

第32届中国控制与决策会议

作者： LIN Zhenkai DOU Yimin LI Jinping School of Information Science and Engineering University of Jinan Shandong Provincial Key Laboratory of Network Based Intelligent Computing(University of Jinan) Shandong College and University Key Laboratory of Information Processing and Cognitive Computing in 13th Five-year Institute of Pattern Recognition and Intelligent Systems University of Jinan

ISBN: (数字)9781728158556

ISBN: (纸本)9781728158563

With the continuous deepening of international anti-terrorism movement,the anti-terrorism has entered a new stage,and it is facing new *** of the new challenges is to extract useful and valuable information from massive data *** anti-terrorism system model based on local shallow information is imperfect,which is not conducive to obtaining accurate prediction *** shortcomings of existing research are the lack of comprehensive analysis and deeper mining of *** order to improve the efficiency and accuracy of the present anti-terrorism system,we propose an effective method for risk assessment and prediction based on machine learning by using Global Terrorism Database(GTD).There are four basic steps:first,we reduce the data dimension through correlation calculation and Singular Value Decomposition(SVD),then,the function is established to rank the harmfulness of terrorist attacks;second,the cascaded network with attention mechanism is used to predict suspects;third,k-means is used to cluster the regions of terrorist attacks,and then we establish a generalized linear regression model to predict the situation of terrorist *** verify the feasibility of the model by comparing with the real *** experimental results show that the proposed method can analyze and predict the information related to terrorist attacks comprehensively and accurately.

关键词： anti-terrorism warning data modeling SVD cascade network with attention mechanism K-means

来源：评论

学校读者我要写书评

暂无评论

A provable-secure and practical two-party distributed signing protocol for SM2 signature algorithm

引用

Frontiers of Computer Science 2020年第3期14卷 203-215页

作者： Yudi ZHANG Debiao HE Mingwu ZHANG Kim-Kwang Raymond CHOO Key Laboratory of Aerospace Information Security and Trusted Computing of Ministry of Education School of Cyber Science and EngineeringWuhan UniversityWuhan 430072China School of Computer Sciences Hubei University of TechnologyWuhan 430068China Department of Information Systems and Cyber Security and Department of Electrical and Computer Engineering University of Texas at San AntonioSan AntonioTX 78249USA

Mobile devices are widely used for data access,communications and ***,storing a private key for signature and other cryptographic usage on a single mobile device can be challenging,due to its computational ***,a number of(t,n)threshold secret sharing schemes designed to minimize private key from leakage have been proposed in the ***,existing schemes generally suffer from key reconstruction *** this paper,we propose an efficient and secure two-party distributed signing protocol for the SM2 signature *** latter has been mandated by the Chinese government for all electronic commerce *** proposed protocol separates the private key to storage on two devices and can generate a valid signature without the need to reconstruct the entire private *** prove that our protocol is secure under nonstandard ***,we implement our protocol using MIRACL Cryptographic SDK to demonstrate that the protocol can be deployed in practice to prevent key disclosure.

关键词： SM2 signature two-party signing wireless environment provable security threshold secret sharing

来源：评论

学校读者我要写书评

暂无评论

Deep support vector machines for speech emotion recognition 19th

Deep support vector machines for speech emotion recognition

引用

19th International Conference on Intelligent systems Design and Applications, ISDA 2019

作者： Aouani, Hadhami Ben Ayed, Yassine National School of Engineers ENIS University of Sfax Sfax Tunisia Multimedia InfoRmation Systems and Advanced Computing Laboratory MIRACL University of Sfax Sfax Tunisia

ISBN: (纸本)9783030493417

Speech Emotions recognition has become the active research theme in speech processing and in applications based on human-machine interaction. In this work, our system is a two-stage approach, namely feature extraction and classification engine. Firstly, two sets of feature are investigated which are: the first one is extracting only 13 Mel-frequency Cepstral Coefficient (MFCC) from emotional speech samples and the second one is applying features fusions between the three features: zero crossing rate (ZCR), Teager Energy Operator (TEO), and Harmonic to Noise Rate (HNR) and MFCC features. Secondly, we use two types of classification techniques which are: the Support Vector Machines (SVM) and the k-Nearest Neighbor (k-NN) to show the performance between them. Besides that, we investigate the importance of the recent advances in machine learning including the deep kernel learning. A large set of experiments are conducted on Surrey Audio-Visual Expressed Emotion (SAVEE) dataset for seven emotions. The results of our experiments showed given good accuracy compared with the previous studies. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

The future of cloud computing: Opportunities, challenges and research trends 2

The future of cloud computing: Opportunities, challenges and...

引用

2nd International Conference on I-SMAC (IoT in Social, Mobile, Analytics and cloud), I-SMAC 2018

作者： Kaur, Amanpreet Singh, V.P. Singh Gill, Sukhpal Computer Science and Engineering Department Thapar Institute of Engineering and Technology Patiala Punjab India Laboratory School of Computing and Information Systems University of Melbourne Australia

ISBN: (纸本)9781538614426

In a cloud computing environment, datacenter consists of number of servers, cooling and power delivery equipment's that require enormous measure of computational energy to drive complex frameworks. Due to the rising demand of the computation power, datacenter has become the hub for significant increase in the power consumption, heat dissipation and rise in temperature of the servers. cloud datacenter's energy consumption has increased tremendously due to increase in the computation requirements of the user workload. Thus, saving energy has become an important concern to address. Researchers proposed different techniques to optimize the energy consumption. In this paper, we focus on different aspects of cloud computing for holistic management of cloud resources in an energy-efficient, reliable and sustainable manner. We recognized different opportunities, identified research challenges and propose possible future research directions for cloud computing. © 2018 IEEE.

关键词： Energy efficiency

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：