检索结果-内蒙古大学图书馆

arXiv 2017年

作者： Zhang, Weile Lin, Hai MOE Key Lab for Intelligent Networks and Network Security Xi'An Jiaotong University Xi'an China Department of Electrical and Information Systems Osaka Prefecture University Osaka Japan

Pilot contamination attack is an important kind of active eavesdropping activity conducted by a malicious user during channel training phase. In this paper, motivated by the fact that frequency asynchronism could introduce divergence of the transmitted pilot signals between intended user and attacker, we propose a new uncoordinated frequency shift (UFS) scheme for detection of pilot contamination attack in multiple antenna system. An attack detection algorithm is further developed based on source enumeration method. Both the asymptotic detection performance analysis and numerical results are provided to verify the proposed studies. The results demonstrate that the proposed UFS scheme can achieve comparable detection performance as the existing superimposed random sequence based scheme, without sacrifice of legitimate channel estimation performance. Copyright © 2017, The Authors. All rights reserved.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

Violence Video Detection Based on Multi-modal Fusion and Dual Channel Contrastive Learning

Violence Video Detection Based on Multi-modal Fusion and Dua...

引用

Human-Centered Cognitive Systems (HCCS)

作者： Huan Li Zhijian Bai Yue Li Tao Qin Faculty of Electronic and Information Engineering Xi’an Jiaotong University Xi’an China MOE Key Lab for Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an Chin

There are more and more violence videos propagated on the Internet, it is important to detect them to provide support for online social network management. In the traditional detection methods, the utilization of different modal data is insufficient. In this paper, we propose a violence detection method based on multimodal fusion and dual channel contrastive learning. Firstly, an adaptive feature fusion method based on the attention mechanism is proposed. The problem of original information missing in the fused features is effectively solved by adaptively weighting the original modal features and the attention fusion features. And then the similarity of the same data representations is improved by contrastive learning between different feature fusion methods, in turn, the local problems caused by different fusion methods are solved. Experimental results based on public datasets show that the proposed method can learn the audio and video features and then generate high quality multimodal fusion features, the detection accuracy is improved by 1.3% to 4.8% compared with popular violence detection methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Online balance strategy on byproduct gas in iron and steel industry

引用

Xitong Gongcheng Lilun yu Shijian/System Engineering Theory and Practice 2013年第6期33卷 1486-1491页

作者： Cao, Yong-Feng Xu, Yin-Feng School of Management Xi'an Jiaotong University Xi'an 710049 China Ministry of Education Key Lab. for Intelligent Networks and Network Security Xi'an Jiaotong University Xi'an 710049 China The MOE Key Lab. for Process Control and Efficiency Engineering Xi'an Jiaotong University Xi'an 710049 China

This paper develops a new framework for the analysis of byproduct gas supply in iron and steel industry. Based on the online theory, this paper studies the online balance assignment problem of the byproduct gas. In the production process, the online decision maker makes decisions to balance the supply of byproduct gas in the online case. Under some reasonable assumptions, the paper constructs a balance assignment model of the byproduct gas to solve the balance range unknown problem. First, this researcher attempts to analyze the special nature of the offline case and the characteristics of the online case under different scenes. Then the paper designs an online balance strategy with a competitive ratio of (1+3M/m)/4 without the knowledge of supply interval. This study provides some ideas and theories for the balance assignment and use of the byproduct in manufacture industry.

关键词： Steelmaking

来源：评论

学校读者我要写书评

暂无评论

Infer-AVAE: An Attribute inference model based on adversarial variational autoencoder

arXiv

引用

arXiv 2020年

作者： Zhou, Yadong Ding, Zhihao Liu, Xiaoming Shen, Chao Tong, Lingling Guan, Xiaohong MOE Key Lab for Intelligent Networks and Network Security Xi'an Jiaotong University China National Computer network Emergency Response technical Team Center for Intelligent and Networked Systems and TNLIST Lab Tsinghua University

User attributes, such as gender and education, face severe incompleteness in social networks. In order to make this kind of valuable data usable for downstream tasks like user profiling and personalized recommendation, attribute inference aims to infer users' missing attribute labels based on observed data. Recently, variational autoencoder (VAE), an end-to-end deep generative model, has shown promising performance by handling the problem in a semi-supervised way. However, VAEs can easily suffer from over-fitting and over-smoothing when applied to attribute inference. To be specific, VAE implemented with multi-layer perceptron (MLP) can only reconstruct input data but fail in inferring missing parts. While using the trending graph neural networks (GNNs) as encoder has the problem that GNNs aggregate redundant information from neighborhood and generate indistinguishable user representations, which is known as over-smoothing. In this paper, we propose an attribute Inference model based on Adversarial VAE (Infer-AVAE) to cope with these issues. Specifically, to overcome over-smoothing, Infer-AVAE unifies MLP and GNNs in encoder to learn positive and negative latent representations respectively. Meanwhile, an adversarial network is trained to distinguish the two representations and GNNs are trained to aggregate less noise for more robust representations through adversarial training. Finally, to relieve over-fitting, mutual information constraint is introduced as a regularizer for decoder, so that it can make better use of auxiliary information in representations and generate outputs not limited by observations. We evaluate our model on 4 real-world social network datasets, experimental results demonstrate that our model averagely outperforms baselines by 7.0% in accuracy. © 2020, CC BY-NC-SA.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

TrafficGPT: Breaking the Token Barrier for Efficient Long Traffic Analysis and Generation

arXiv

引用

arXiv 2024年

作者： Qu, Jian Ma, Xiaobo Li, Jianfeng MOE Key Lab for Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an China Faculty of Electronic and Information Engineering Xi’an Jiaotong University Xi’an China

Over the years, network traffic analysis and generation have advanced significantly. From traditional statistical methods, the field has progressed to sophisticated deep learning techniques. This progress has improved the ability to detect complex patterns and security threats, as well as to test and optimize network performance. However, obstacles persist, such as the dependence on labeled data for analysis and the difficulty of generating traffic samples that follow realistic patterns. Pretrained deep neural networks have emerged as powerful tools to resolve these issues, offering improved performance by learning robust data representations from large unlabeled datasets. Despite their benefits, existing pre-trained models face challenges like token length limitation, which restricts their usefulness in comprehensive traffic analysis and realistic traffic generation. To address these challenges, we introduce TrafficGPT, a deep learning model that can tackle complex challenges related to long flow classification and generation tasks. This model uses generative pre-training with the linear attention mechanism, which allows for a substantially increased capacity of up to 12,032 tokens from the previous limit of only 512 tokens. TrafficGPT demonstrates superior performance in classification tasks, reaching state-of-the-art levels. In generation tasks, it closely resembles real traffic flows, with low JS divergence and an F1 score close to 0.5 (representing a random guess) in discriminating generated data. These advancements hold promise for future applications in both traffic flow classification and generation tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Network security Monitoring and Defense System Framework Design Using Mobile Agents Based on DoDAF

Network Security Monitoring and Defense System Framework Des...

引用

International Conference on Computer Sciences and Applications (CSA)

作者： Yan Tong Jian Zhang Ming-Di Xu Tao Qin System Software Department Wuhan Digital Engineering Institute Wuhan China MoE Key Lab for Intelligent Networks and Network Security Xi'an Jiaotong University Xi'an China

ISBN: (纸本)9781479999620

Network security and defense plays important roles in network management system. The traditional network security monitoring systems usually employ lots of agents to collected data and then perform abnormal detection based on measurement of those data. This kind of framework needs lots of agents and usually occupies many bandwidths. Focus on this problem, we introduce the mobile agents into the network security and monitoring system. As the mobile agents are intelligent and can move to other hosts according to the monitoring task, adoption of the mobile agents will increase the flexibility of the monitoring system while reduce the number of agents. Furthermore, we employ DoDAF to make the designed framework more easily used and deployed. Firstly, we analyzed the development standards of the mobile agent, including MASIF and FIPA, then mapped them to DM2 in DoDAF. We also analyzed the elements included in the traditional network security monitoring system and mapped them to DM2. Based on those mapping works, we can obtain DM2 which should be included in different views in DoDAF. Secondly, we divided the designed architecture into four parts based on the TOGAF, including the business architecture, application architecture, data architecture and technology architecture. And extract which view which should be included in the designed framework. Finally, according to the constraint relationship between different views, we obtain the developing sequence of those views and design and develop the network security monitoring and defense system framework using the mobile agent. Based on EA, we verified the designed framework and the results show that the proposed framework is correct.

关键词： security Monitoring Communication networks Mobile agents Standards Business Internet

来源：评论

学校读者我要写书评

暂无评论

MSIsensor-pro: Fast, Accurate, and Matched-normal-sample-free Detection of Microsatellite Instability

引用

Genomics, Proteomics & Bioinformatics 2020年第1期18卷 65-71页

作者： Peng Jia Xiaofei Yang Li Guo Bowen Liu Jiadong Lin Hao Liang Jianyong Sun Chengsheng Zhang Kai Ye School of Automation Science and Engineering Faculty of Electronic and Information EngineeringXi’an Jiaotong UniversityXi’an 710049China MOE Key Laboratory for Intelligent Networks&Networks Security Faculty of Electronic and Information EngineeringXi’an Jiaotong UniversityXi’an 710049China School of Computer Science and Technology Faculty of Electronic and Information EngineeringXi’an Jiaotong UniversityXi’an 710049China School of Life Science and Technology Xi’an Jiaotong UniversityXi’an 710049China Leiden Institute of Advanced Computer Science Leiden UniversityLeiden 2311 ZENetherlands School of Mathematics and Statistics Xi’an Jiaotong UniversityXi’an 710049China Precision Medicine Center the First Affiliated Hospital of Xi’an Jiaotong UniversityXi’an 710061China Jackson Laboratory for Genomic Medicine FarmingtonCT 06032USA Genome Institute the First Affiliated Hospital of Xi’an Jiaotong UniversityXi’an 710061China

Microsatellite instability(MSI)is a key biomarker for cancer therapy and *** experimental assays are laborious and time-consuming,and next-generation sequencingbased computational methods do not work on leukemia samples,paraffin-embedded samples,or patient-derived xenografts/organoids,due to the requirement of matched normal ***,we developed MSIsensor-pro,an open-source single sample MSI scoring method for research and clinical ***-pro introduces a multinomial distribution model to quantify polymerase slippages for each tumor sample and a discriminative site selection method to enable MSI detection without matched normal *** demonstrate that MSIsensor-pro is an ultrafast,accurate,and robust MSI calling *** samples with various sequencing depths and tumor purities,MSIsensor-pro significantly outperformed the current leading methods in both accuracy and computational ***-pro is available at https://***/xjtu-omics/msisensor-pro and free for non-commercial use,while a commercial license is provided upon request.

关键词： Microsatellite Polymerase slippage Multinomial distribution Microsatellite instability Tumor

来源：评论

学校读者我要写书评

暂无评论

Homeomorphic manifold analysis: Learning motion features of image sequence for lipreading

Homeomorphic manifold analysis: Learning motion features of ...

引用

IEEE International Conference on Software Engineering and Service Sciences (ICSESS)

作者： Longbin Lu Xinman Zhang Xuebin Xu Zhihui Wu MOE Key Lab for Intelligent Networks and Network Security Xi'an Jiaotong University Xi'an Shanxi Province China Guangdong Xi'an Jiaotong University Academy Guangdong Province China

ISBN: (纸本)9781479983544

Lipreading techniques have shown bright prospects for speech recognition under noisy environments and for hearing-impaired listeners. In this paper, we discuss a feature extraction method based on the homeomorphic manifold analysis for lipreading. Given a set of image sequences, we think there is an underlying low dimensional unified manifold embedded in the visual space, and each image sequence can be considered as a homeomorphic manifold twisted or even self-intersected in this space. In order to extract the motion features, each sequence is embedded and aligned to the unified manifold, and a mapping matrix is learned from the aligned embedding. Then we adopt the two-dimensional linear discriminant analysis on these mapping matrices to achieve low dimensional features. The proposed method is tested on the OuluVS database, and simulation experiments have shown it can achieve quite satisfying results.

关键词： Image sequences Manifolds Feature extraction Databases Hidden Markov models Kernel Linear discriminant analysis

来源：评论

学校读者我要写书评

暂无评论

A Multimodal Biometric Recognition Algorithm Based on Second Generation Curvelet and 2D Gabor Filter

A Multimodal Biometric Recognition Algorithm Based on Second...

引用

International Conference on Cybernetics, Robotics and Control (CRC)

作者： Xinman Zhang Qi Xiong Xuebin Xu School of Electronics and Information Engineering MOE Key Lab for Intelligent Networks and Network Security Xi'an Jiaotong University Xi'an Guangdong Xi'an Jiaotong University Academy Foshan China

ISBN: (数字)9781728146201

ISBN: (纸本)9781728146218

Aiming at the problems of unimodal biometric recognition, such as easy interference and low recognition rate in practical application, a multimodal biometric recognition method is proposed in this paper. This method uses the second generation curvelet to extract face features and the 2D Gabor phase method to extract iris features. Then the two features are fused in the feature layer, and the fusion feature vectors are recognized by ELM classification. The experiments are carried out on the YaleB face dataset and CASIA-Iris-Lamp dataset. The experiment results show that the average accuracy of recognition of the algorithm can reach up to 99.74%, which is better than recognition methods of unimodal face and unimodal iris. The rate increases by 3.35%, which provides an effective model for multimodal biometric recognition.

关键词： Iris recognition Feature extraction Face Face recognition Gabor filters Transforms Two dimensional displays

来源：评论

学校读者我要写书评

暂无评论

Energy Trading in Smart Grid:A Deep Reinforcement Learning-based Approach

Energy Trading in Smart Grid:A Deep Reinforcement Learning-b...

引用

第32届中国控制与决策会议

作者： Feiye Zhang Qingyu Yang School of Automation Science and Engineering Xi'an Jiaotong University SKLMSE Lab MOE Key Laboratory for Intelligent Networks and Network SecuritySchool of Automation Science and EngineeringXi'an Jiaotong University

To achieve the efficient operation of the smart grid,appropriate energy trading strategy plays an important role in reducing multi-agent costs in the trading process as well as alleviating grid ***,with the increase of the number of participants in smart grid,energy trading has been greatly challenged in terms of stable and effective *** this paper,we propose a deep reinforcement learning-based energy double auction trading *** the deep reinforcement learning algorithm,buyers and sellers can gradually learn the environment by treating the three elements:total supply,total demand and their own supply and demand as states,in addition,regarding both bidding price and quantity as bidding *** from simulation indicate that as the learning continues and reaches the convergence,both the cost which buyers pay in the auction has decreased significantly,and the profit which sellers earn in the auction will increase.

关键词： Smart Grid Energy Trading Double Auction Deep Reinforcement Learning

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：