检索结果-内蒙古大学图书馆

2nd IEEE International Conference on Information technology, Big data and Artificial Intelligence, ICIBA 2021

作者： Tang, Xue Wen, Zhan Chen, Jiali Li, Yiquan Li, Wenzao College of Communication Engineer Chengdu University of Information Technology Chengdu China Network and Data Security Key Laboratory of Sichuan Province University of Electronic Science and Technology of China Chengdu611730 China

ISBN: (纸本)9781665428767

With increase of Internet of Things (IoT) devices, the burden of cloud computing servers is gradually increasing. Mobile Edge Computing (MEC), as an emerging solution, can relieve the pressure of computing and improve the quality of user experience. One of the critical challenges in MEC is to make effective use of communication and computing resources and select the task processing mode reasonably. In this paper, based on the scenario of a single mobile device (MD) to one mobile edge server (MES), we propose a Joint optimization method base on Discrete Binary Particle Swarm Optimization Algorithm (JOBPSO) for system load. The JOBPSO can optimize MD's task offloading, reduce delay and energy consumption. Finally, the simulation results indicate that the performance of JOBPSO in reducing system load is better than the other two traditional offloading methods. © 2021 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Conditional selection with CNN augmented transformer for multimodal affective analysis

引用

CAAI Transactions on Intelligence technology 2024年第4期9卷 917-931页

作者： Jianwen Wang Shiping Wang Shunxin Xiao Renjie Lin Mianxiong Dong Wenzhong Guo College of Computer and Data Science Fuzhou UniversityFuzhouChina College of Computer and Cyber Security Fujian Normal UniversityFuzhouChina Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou UniversityFuzhouChina Digital Fujian Institute of Big Data Security Technology Fujian Normal UniversityFuzhouChina Department of Sciences and Informatics Muroran Institute of TechnologyMuroranJapan

Attention mechanism has been a successful method for multimodal affective analysis in recent years. Despite the advances, several significant challenges remain in fusing language and its nonverbal context information. One is to generate sparse attention coefficients associated with acoustic and visual modalities, which helps locate critical emotional se-mantics. The other is fusing complementary cross‐modal representation to construct optimal salient feature combinations of multiple modalities. A Conditional Transformer Fusion network is proposed to handle these problems. Firstly, the authors equip the transformer module with CNN layers to enhance the detection of subtle signal patterns in nonverbal sequences. Secondly, sentiment words are utilised as context conditions to guide the computation of cross‐modal attention. As a result, the located nonverbal fea-tures are not only salient but also complementary to sentiment words directly. Experi-mental results show that the authors’ method achieves state‐of‐the‐art performance on several multimodal affective analysis datasets.

关键词： affective computing data fusion information fusion multimodal approaches

来源：评论

学校读者我要写书评

暂无评论

An Efficient and Provably Secure SM2 key-Insulated Signature Scheme for Industrial Internet of Things

引用

Computer Modeling in Engineering & sciences 2024年第1期138卷 903-915页

作者： Senshan Ouyang Xiang Liu Lei Liu Shangchao Wang Baichuan Shao Yang Zhao School of Mechanical Engineering Northwestern Polytechnical UniversityXi’anChina Department of Process and Information Technology Chengdu Aircraft Industrial(Group)Co.Ltd.ChengduChina School of Information and Software Engineering The Network and Data Security Key Laboratory of Sichuan ProvinceUniversity of Electronic Science and Technology of ChinaChengduChina

With the continuous expansion of the Industrial Internet of Things(IIoT),more andmore organisations are placing large amounts of data in the cloud to reduce ***,the channel between cloud servers and smart equipment is not trustworthy,so the issue of data authenticity needs to be *** SM2 digital signature algorithm can provide an authentication mechanism for data to solve such ***,it still suffers from the problem of key *** order to address this concern,this study first introduces a key-insulated scheme,SM2-KI-SIGN,based on the SM2 *** scheme boasts strong key insulation and secure *** scheme uses the elliptic curve algorithm,which is not only more efficient but also more suitable for IIoT-cloud ***,the security proof of SM2-KI-SIGN is given under the Elliptic Curve Discrete Logarithm(ECDL)assumption in the random oracle.

关键词： key-insulated SM2 algorithm digital signature Industrial Internet of Things(IIoT) provable security

来源：评论

学校读者我要写书评

暂无评论

Exploration on the key Issues of the Teaching Method of Student Independent Proposition

Exploration on the Key Issues of the Teaching Method of Stud...

引用

International Conference on Guidance, Navigation and Control, ICGNC 2020

作者： Zhang, Jin Quan, Weihong Li, Haoran Wang, Lizhi Gong, Xiaoli Wu, Qian College of Computer Science Nankai University Tianjin China College of Cyber Science Nankai University Tianjin China Tianjin Key Laboratory of Network and Data Security Technology Tianjin China Tianjin University of Science and Technology Tianjin China

ISBN: (纸本)9789811581540

In order to figure out the solutions to difficulties facing the university online education platform in the expansion of the question bank, this paper proposes a teaching method of student independent proposition that allows students to create exercises independently based on the content of the textbook. In view of the high cost of manual review of these student-created exercises, natural language processing and deep learning technologies are used to achieve automatic correctness checking. For the key issues encountered in the actual construction of the independent proposition system, a feasible solution is proposed. The research is of great significance to the construction and subsequent application of the question bank of the online education platform of universities. © 2022, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Malicious HTTPS Traffic Classification Algorithm Based on DCGAN_1D-CNN

Malicious HTTPS Traffic Classification Algorithm Based on DC...

引用

2021 IEEE Conference on Telecommunications, Optics and Computer science, TOCS 2021

作者： Luo, Wen Liu, Zhaohui Zhao, Rui Chen, Jianhua Deng, Xin University of South China School of Computer Science Hengyang China Key Laboratory of Network Assessment Technology CAS Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China

ISBN: (纸本)9781665424981

Aiming at the problems of fast classification and unbalanced data classification of encrypted malicious traffic in the internet, a classification method of encrypted malicious based on DCGAN 1D-CNN model is ***-IDCNN uses the idea of generating confrontation to generate a few samples in the data level to improve the lack of original training samples and sample imbalances,and use the ID-CNN to train the original sample and the generated few samples,so as to accurately classify the encrypted *** experimental results on the public dataset CICAndMal2017 show that the F1 value reaches 96.55% in the binary classification experiment, which is at most higher 11.77% than that of using 1D-CNN model alone,indicating that the DCGAN 1D-CNN model has stronger ability to classify encrypted malicious traffic. © 2021 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

MQGrad: Reinforcement learning of gradient quantization in parameter server

arXiv

引用

arXiv 2018年

作者： Cui, Guoxin Xu, Jun Zeng, Wei Lan, Yanyan Guo, Jiafeng Cheng, Xueqi CAS Key Laboratory of Network Data Science and Technology Institute of ComputingTechnology Chinese Academy of Sciences Beijing100190 China

One of the most significant bottleneck in training large scale machine learning models on parameter server (PS) is the communication overhead, because it needs to frequently exchange the model gradients between the workers and servers during the training iterations. Gradient quantization has been proposed as an effective approach to reducing the communication volume. One key issue in gradient quantization is setting the number of bits for quantizing the gradients. Small number of bits can significantly reduce the communication overhead while hurts the gradient accuracies, and vise versa. An ideal quantization method would dynamically balance the communication overhead and model accuracy, through adjusting the number bits according to the knowledge learned from the immediate past training iterations. Existing methods, however, quantize the gradients either with fixed number of bits, or with predefined heuristic rules. In this paper we propose a novel adaptive quantization method within the framework of reinforcement learning. The method, referred to as MQGrad, formalizes the selection of quantization bits as actions in a Markov decision process (MDP) where the MDP states records the information collected from the past optimization iterations (e.g., the sequence of the loss function values). During the training iterations of a machine learning algorithm, MQGrad continuously updates the MDP state according to the changes of the loss function. Based on the information, MDP learns to select the optimal actions (number of bits) to quantize the gradients. Experimental results based on a benchmark dataset showed that MQGrad can accelerate the learning of a large scale deep neural network while keeping its prediction accuracies. Copyright © 2018, The Authors. All rights reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Nondestructive technique for identifying nuclides using neutron resonance transmission analysis at CSNS Back-n

引用

Nuclear science and Techniques 2024年第1期35卷 178-187页

作者： Sheng-Da Tang Yong-Hao Chen Jing-Yu Tang Rui-Rui Fan Qiang Li Gong Li Dong Liu Zheng-Yao Jin Xing-Zhu Cui Tian-Xiang Chen Yi-Wei Yang Rong Liu Han Yi Yang Li Zhen Yang Qi An Hao-Fan Bai Jiang-Bo Bai Jie Bao Ping Cao Qi-Ping Chen Zhen Chen Zeng-Qi Cui An-Chuan Fan Chang-Qing Feng Fan-Zhen Feng Ke-Qing Gao Min-Hao Gu Chang-Cai Han Zi-Jie Han Guo-Zhu He Yong-Cheng He Yang Hong Yi-Wei Hu Han-Xiong Huang Wei-Hua Jia Hao-yu Jiang Wei Jiang Zhi-jie Jiang Ling Kang Bo Li Chao Li Jia-Wen Li Xiao Li Jie Liu Shu-Bin Liu Guang-Yuan Luan Chang-Jun Ning Bin-Bin Qi Jie Ren Zhi-Zhou Ren Xi-Chao Ruan Zhao-Hui Song Kang Sun Zhi-Xin Tan Li-Jiao Wang Peng-Cheng Wang Zhao-Hui Wang Zhong-Wei Wen Xiao-Guang Wu Xuan Wu Li-Kun Xie Yong-Ji Yu Guo-Hui Zhang Lin-Hao Zhang Mo-Han Zhang Qi-Wei Zhang Xian-Peng Zhang Yu-Liang Zhang Yue Zhang Zhi-Yong Zhang Mao-Yuan Zhao Lu-Ping Zhou Zhi-Hao Zhou Ke-Jun Zhu Sino-French Institute of Nuclear Engineering and Technology Sun Yat-sen UniversityZhuhai 519082China Institute of High-Energy Physics Chinese Academy of Sciences(CAS)Beijing 100049China Spallation Neutron Source Science Center Dongguan 523803China School of Nuclear Science and Technology University of Science and Technology of ChinaHefei 230026China State Key Laboratory of Particle Detection and Electronics University of Science and Technology of ChinaHefei 230026China State Key Laboratory of Particle Detection and Electronics Institute of High Energy PhysicsChinese Academy of SciencesBeijing 100049China USTC Archaeometry Laboratory University of Science and Technology of ChinaHefei 230026China Institute of Nuclear Physics and Chemistry China Academy of Engineering PhysicsMianyang 621900China Department of Modern Physics University of Science and Technology of ChinaHefei 230026China State Key Laboratory of Nuclear Physics and Technology School of PhysicsPeking UniversityBeijing 100871China Key Laboratory of Nuclear Data China Institute of Atomic EnergyBeijing 102413China Northwest Institute of Nuclear Technology Xi’an 710024China University of Chinese Academy of Sciences Beijing 100049China

Nondestructive and noninvasive neutron assays are essential applications of neutron *** resonance transmission analysis(NRTA)is a powerful nondestructive method for investigating the elemental composition of an *** back-streaming neutron line(Back-n)is a newly built time-of-flight facility at the China Spallation Neutron Source(CSNS)that provides neutrons in the eV to 300 MeV range.A feasibility study of the NRTA method for nuclide identification was conducted at the CSNS Back-n via two test *** results demonstrate that it is feasible to identify different elements and isotopes in samples using the NRTA method at *** study reveals its potential future applications.

关键词： CSNS White neutron beam NRTA Nuclide identification Nondestructive method

来源：评论

学校读者我要写书评

暂无评论

Multi-layer network embedding on scc-based network with motif

引用

Digital Communications and networks 2024年第3期10卷 546-556页

作者： Lu Sun Xiaona Li Mingyue Zhang Liangtian Wan Yun Lin Xianpeng Wang Gang Xu Department of Communication Engineering Institute of Information Science TechnologyDalian Maritime UniversityDalian116026China Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and TelecommunicationsChongqing400065China Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province DUT School of Software Technology&DUT-RU International School of Information Science and EngineeringDalian University of TechnologyDalian 116620China College of Information and Communication Engineering Harbin Engineering UniversityHarbin 150001China School of Information and Communication Engineering Hainan UniversityHaikou 570228China State Key Laboratory of Millimeter Waves School of Information Science and EngineeringSoutheast UniversityNanjing 210096China

Interconnection of all things challenges the traditional communication methods,and Semantic Communication and Computing(SCC)will become new *** is a challenging task to accurately detect,extract,and represent semantic information in the research of SCC-based *** previous research,researchers usually use convolution to extract the feature information of a graph and perform the corresponding task of node ***,the content of semantic information is quite *** graph convolutional neural networks provide an effective solution for node classification tasks,due to their limitations in representing multiple relational patterns and not recognizing and analyzing higher-order local structures,the extracted feature information is subject to varying degrees of ***,this paper extends from a single-layer topology network to a multi-layer heterogeneous topology *** Bidirectional Encoder Representations from Transformers(BERT)training word vector is introduced to extract the semantic features in the network,and the existing graph neural network is improved by combining the higher-order local feature module of the network model representation network.A multi-layer network embedding algorithm on SCC-based networks with motifs is proposed to complete the task of end-to-end node *** verify the effectiveness of the algorithm on a real multi-layer heterogeneous network.

关键词： Semantic communication and computing Multi-layer network Graph neural network Motif

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Algorithms Design and Implementation Based on Differential Privacy 3rd

Deep Learning Algorithms Design and Implementation Based on ...

引用

3rd International Conference on Machine Learning for Cyber Security, ML4CS 2020

作者： Xu, Xuefeng Yao, Yanqing Cheng, Lei Key Laboratory of Aerospace Network Security Ministry of industry and information technology School of Cyberspace Science and Technology Beihang University Beijing100191 China State Key Laboratory of Software Development Environment Beihang University Beijing100191 China Beijing Key Laboratory of Network Technology Beihang University Beijing China Shenzhen Research Institute of Big Data Shenzhen518000 China

ISBN: (纸本)9783030622220

Deep learning models bear the risks of privacy leakage. Attackers can obtain sensitive information contained in training data with some techniques. However, existing differentially private methods such as Differential Privacy-Stochastic Gradient Descent (DP-SGD) and Differential Privacy-Generative Adversarial network (DP-GAN) are not very efficient as they require to perform sampling multiple times. More importantly, DP-GAN algorithm need public data to set gradient clipping threshold. In this paper, we introduce our refined algorithms to tackle these problems. First, we employ random shuffling instead of random sampling to improve training efficiency. We also test Gaussian and Laplace Mechanisms for clipping gradients and injecting noise. Second, we employ zero Concentrated Differential Privacy (zCDP) to compute overall privacy budget. Finally, we adopt dynamical gradient clipping in DP-GAN algorithm. During each iteration, we random sample training examples and set the average gradients norm as the new threshold. This not only makes the algorithm more robust but also doesn’t increase the overall privacy budget. We experiment with our algorithms on MNIST data sets and demonstrate the accuracies. In our refined DP-SGD algorithm, we achieve test accuracy of 96.58%. In our refined DP-GAN algorithm, we adopt the synthetic data to train models and reach test accuracy of 91.64%. The results show that our approach ensures model usability and provides the capability of privacy protection. © 2020, Springer Nature Switzerland AG.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A Discriminative Semantic Ranker for Question Retrieval 21

A Discriminative Semantic Ranker for Question Retrieval

引用

11th ACM SIGIR International Conference on Theory of Information Retrieval, ICTIR 2021

作者： Cai, Yinqiong Fan, Yixing Guo, Jiafeng Zhang, Ruqing Lan, Yanyan Cheng, Xueqi University of Chinese Academy of Sciences Beijing China Cas Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China Institute for Ai Industry Research Tsinghua University Beijing China

ISBN: (纸本)9781450386111

Similar question retrieval is a core task in community-based question answering (CQA) services. To balance the effectiveness and efficiency, the question retrieval system is typically implemented as multi-stage rankers: The first-stage ranker aims to recall potentially relevant questions from a large repository, and the latter stages attempt to re-rank the retrieved results. Most existing works on question retrieval mainly focused on the re-ranking stages, leaving the first-stage ranker to some traditional term-based methods. However, term-based methods often suffer from the vocabulary mismatch problem, especially on short texts, which may block the re-rankers from relevant questions at the very beginning. An alternative is to employ embedding-based methods for the first-stage ranker, which compress texts into dense vectors to enhance the semantic matching. However, these methods often lose the discriminative power as term-based methods, thus introduce noise during retrieval and hurt the recall performance. In this work, we aim to tackle the dilemma of the first-stage ranker, and propose a discriminative semantic ranker, namely DenseTrans, for high-recall retrieval. Specifically, DenseTrans is a densely connected Transformer, which learns semantic embeddings for texts based on Transformer layers. Meanwhile, DenseTrans promotes low-level features through dense connections to keep the discriminative power of the learned representations. DenseTrans is inspired by DenseNet in computer vision (CV), but poses a new way to use the dense connectivity which is totally different from its original design purpose. Experimental results over two question retrieval benchmark datasets show that our model can obtain significant gain on recall against strong term-based methods as well as state-of-the-art embedding-based methods. © 2021 ACM.

关键词： Semantics

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：