检索结果-内蒙古大学图书馆

15th International Symposium on Wireless Communication Systems, ISWCS 2018

作者： Zhang, Yangying Jing, Xiaojun Gao, Hui Li, Bohan Xie, Jianxiao Key Laboratory of Trustworthy Distributed Computing and Service Beijing University of Posts and Telecommunications Ministry of Education Beijing China

ISBN: (纸本)9781538650059

In this paper, we apply an accurate millimeter wave (mmWave) path loss model, obtained from outdoor measurement operated at 39 GHz in Qingdao, China, into the stochastic geometry analysis to investigate the system performance of small cell networks (SCNs) with non-identical user equipment (UE) - base station (BS) antenna heights. The analytical expressions for coverage probability and outage probability are derived in detail, which are functions of BS density and absolute difference between the antenna heights of BS and UE. The analytical results of coverage probability and outage probability are verified through Monte Carlo simulation. Our study shows that as the SCNs become denser, the impact of antenna heights difference on coverage and outage probability is more significant. © 2018 IEEE.

关键词： Millimeter waves

来源：评论

学校读者我要写书评

暂无评论

Emergency analysis based on affective computing in universities forum 5th

Emergency analysis based on affective computing in universit...

引用

5th International Conference on Artificial Intelligence and Security, ICAIS 2019

作者： Zhang, Lu Wu, Xu Xie, Xiaqing Xu, Jin Zhang, Tianle Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education Beijing100876 China School of Cyberspace Security BUPT Beijing100876 China Beijing University of Posts and Telecommunications Library Beijing100876 China Cyberspace Institute of Advanced Technology Guangzhou University Guangzhou510006 China

ISBN: (纸本)9783030242701

Emergency analysis for social networking sites have gained increased attention. In order to detect emergencies in University Forums, we present an emergency analysis method based on affective computing. The method detects the emergency and calculates the scores in real-time based on affective computing and the University Public Opinion Ontology (UPO_Ontology) established manually. The method is evaluated on two test datasets. The results show that the UPO_Ontology and affective computing greatly improved the accuracy, recall and F-measure. The method proposed in this paper meets the requirement of real-time detection. What's more, It gain of 1.24% in F-measure over the "event-specific detection" proposed by Laylavi et al. and outperforms emergency detect using contextual semantics by nearly 7.1% in F-measure. The analysis of the emergencies in University Forums will help Universities deal with emergencies more effectively and provide students with better service. © Springer Nature Switzerland AG 2019.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Intelligent reflecting surface aided multi-user millimeter-wave communications for coverage enhancement

arXiv

引用

arXiv 2019年

作者： Cao, Yashuai Lv, Tiejun Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China

Intelligent reflecting surface (IRS) is envisioned as a promising solution for controlling radio propagation environments in future wireless systems. In this paper, IRS is exploited to extend the millimeter wave (mmW) signal coverage to blind spots, thereby reducing power consumption whilst improving communication performance. To merge IRS with mmW communications enjoying gigabit data-rate, we introduce a distributed IRS aided mmW system to support multi-user transmission. Taking into account the multi-user interference, we study a joint active and passive beamforming problem for weighted sum-rate maximization. Then, an alternating iterative algorithm with closed-form expressions is proposed to tackle the non-convex problem. Moreover, we design a quantitative projection method for the IRS with discrete phase shifts. Finally, the simulation results demonstrate that the distributed IRS can effectively support multi-user mmW transmissions based on our proposed algorithm. Copyright © 2019, The Authors. All rights reserved.

关键词： Millimeter waves

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning for Demand-Aware Joint VNF Placement-and-Routing

Deep Reinforcement Learning for Demand-Aware Joint VNF Place...

引用

IEEE Globecom Workshops

作者： Shaoyang Wang Tiejun Lv Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9781728109602

ISBN: (纸本)9781728109619

One main challenge facing the deployment of the network function virtualization is the resource allocation on demand. As the primary stage of the resource allocation, the effective virtual network function (VNF) placement-and-routing (P&R) is particularly difficult. To this end, we propose a deep reinforcement learning (DRL)-based approach for solving the joint VNF P&R problem subject to diverse service demands. Our approach exhibits strong stability and excellent load balancing ability. It can also effectively counter the non-uniformity of P&R policies. We first introduce the service request model, and formulate the VNF P&R problem, while taking both the resource consumption cost and service delay into the optimization objective. A demand-aware factor is also employed to characterize the diversity of service demands. In the considered problem, the DRL-based P&R scheme is presented, invoking the deep deterministic policy gradient as the main learning algorithm. According to the results of extensive experiments made on the realistic "COST266" network topology, our scheme can approach the optimum, and is superior to existing heuristic algorithms.

关键词： Delays Routing Bandwidth Resource management Machine learning Optimization Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Adversarial Residual Variational Graph Autoencoder with Batch Normalization

Adversarial Residual Variational Graph Autoencoder with Batc...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Qisheng Liao Xu Wu Xiaqing Xie Jingchen Wu Lirong Qiu Lijuan Sun Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education Beijing University of Posts and Telecommunications Beijing China School of Cyberspace Security BUPT Beijing University of Posts and Telecommunications Beijing China Beijing University of Posts and Telecommunications Library Beijing University of Posts and Telecommunications Beijing China School of Computer Science (National Pilot Software Engineering School) BUPT Beijing University of Posts and Telecommunications Beijing China School of Economics and Management BUPT Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9781665418164

The variational graph autoencoder (VGAE), a framework for unsupervised learning on graph-structured data, has captured more attention recently in graph embedding area. However, it has been faced up with the challenge of KL vanishing, which will converge to local optimum and make the graph embedding unavailable for downstream tasks like link prediction. This paper proposes a novel variational graph autoencoder framework to achieve more effective graph embedding. Firstly, we introduce batch normalization to make sure the KL distribution consistent with the whole dataset by keeping its expectation positive, thus avoiding posteriori collapse. In addition, we invite residual connection and adversarial network to simultaneously embed the topology information and content information into graph representation stably, enhancing the expressive ability of latent vector. Finally, link prediction experiments on three citation datasets demonstrate that the AUC scores of our algorithm are higher than 92% and the average accuracies are higher than 93%, which is competitive comparing with the state-of-the-art variational graph autoencoders.

关键词： Network topology Conferences Cyberspace Data science Prediction algorithms Topology Task analysis

来源：评论

学校读者我要写书评

暂无评论

Insider Threat Detection Based on User Historical Behavior and Attention Mechanism

Insider Threat Detection Based on User Historical Behavior a...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Weiyu He Xu Wu Jingchen Wu Xiaqing Xie Lirong Qiu Lijuan Sun Ministry of Education Key Laboratory of Trustworthy Distributed Computing and Service Beijing University of Posts and Telecommunications Beijing China School of Cyberspace Security BUPT Beijing University of Posts and Telecommunications Beijing China Beijing University of Posts and Telecommunications Library Beijing University of Posts and Telecommunications Beijing China School of Computer Science (National Pilot Software Engineering School) BUPT Beijing University of Posts and Telecommunications Beijing China School of Economics and Management BUPT Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9781665418164

Insider threat makes enterprises or organizations suffer from the loss of property and the negative influence of reputation. User behavior analysis is the mainstream method of insider threat detection, but due to the lack of fine-grained detection and the inability to effectively capture the behavior patterns of individual users, the accuracy and precision of detection are insufficient. To solve this problem, this paper designs an insider threat detection method based on user historical behavior and attention mechanism, including using Long Short Term Memory (LSTM) to extract user behavior sequence information, using Attention-based on user history behavior (ABUHB) learns the differences between different user behaviors, uses Bidirectional-LSTM (Bi-LSTM) to learn the evolution of different user behavior patterns, and finally realizes fine-grained user abnormal behavior detection. To evaluate the effectiveness of this method, experiments are conducted on the CMU-CERT Insider Threat Dataset. The experimental results show that the effectiveness of this method is 3.1% to 6.3% higher than that of other comparative model methods, and it can detect insider threats in different user behaviors with fine granularity.

关键词： Conferences Neural networks Cyberspace Organizations Data science History Data mining

来源：评论

学校读者我要写书评

暂无评论

Sensitive Image Information Recognition Model of Network Community based on Content Text

Sensitive Image Information Recognition Model of Network Com...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Li Gao Xu Wu Jingchen Wu Xiaqing Xie Lirong Qiu Lijuan Sun Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education Beijing University of Posts and Telecommunications Beijing China School of Cyberspace Security BUPT Beijing University of Posts and Telecommunications Beijing China Beijing University of Posts and Telecommunications Library Beijing University of Posts and Telecommunications Beijing China School of Computer Science (National Pilot Software Engineering School) BUPT Beijing University of Posts and Telecommunications Beijing China School of Economics and Management BUPT Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9781665418164

With the advent of the multimedia era and the age of picture-reading, the recognition effect of sensitive content of image data has become the key to maintain the information security of network communities. At present, the image classification and recognition technology for sensitive images in network communities cannot obtain the semantic content of images, and it is difficult to combine the image information with the knowledge in network communities, resulting in low recognition accuracy and poor interpretability, and it is difficult to trace the transmission and fermentation of image information in network communities. To solve this problem, this paper proposes a sensitive image information recognition model of network community based on content text by using image caption technology. Through the text description of the image content of the network community, and the integration of a large number of network community text knowledge, the model can finally identify the images containing sensitive content more accurately and more understandable, and the transmission of image information on the network can be traced through the content text. In this paper, MSCOCO(Microsoft Common Objects in Context) dataset and sensitive image self-made dataset of network community are used as the training set. The experimental results show that the method presented in this paper is significantly better than the model based on image classification task in terms of accuracy and traceability of image sensitive information recognition results, which proves the feasibility and effectiveness of sensitive image information recognition in network communities based on content text.

关键词： Knowledge engineering Training Image recognition Text recognition Semantics Information security Cyberspace

来源：评论

学校读者我要写书评

暂无评论

Graph Neural Network Based User Group Comments Interaction Behavior Prediction on Microblog Websites

Graph Neural Network Based User Group Comments Interaction B...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Yisen Chen Xu Wu Xiaqing Xie Jingchen Wu Lirong Qiu Lijuan Sun Ministry of Education Key Laboratory of Trustworthy Distributed Computing and Service Beijing University of Posts and Telecommunications Beijing China School of Cyberspace Security BUPT Beijing University of Posts and Telecommunications Beijing China Beijing University of Posts and Telecommunications Library Beijing University of Posts and Telecommunications Beijing China School of Computer Science(National Pilot Software Engineering School) BUPT Beijing University of Posts and Telecommunications Beijing China School of Economics and Management BUPT Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9781665418164

The interactive behavior of comments within the user group on microblog website is bidirectional and dynamic, reflecting the level of familiarity among users. Predicting the future comment interaction behavior within the user group is of great significance for commercial recommendation and crime fighting. Related research groups regard it as a temporal link prediction problem, assume the evolution is smooth or there is no evolution at all. Meanwhile, the feature in those studies is too unitary, leading to low link prediction performance. In this paper, we propose a method called User Group Comment Interaction Behaviour Prediction (UGCIBP), which combines structure extraction layer and evolution extraction layer to do dynamic graph representation learning to acheive the modeling of user group historical comment interaction graphs, and build the features of communication weight, interest similarity, and common degree of activity between users on microblog website. Then, we combine dynamic graph representation learning and the constructed features to do link prediction, finally, the purpose of predicting comment interaction is acheived. Experiments are conducted on the public datasets Enron and Twitter datasets to evaluate the method. The results show that the AUC scores of this method are 4.74% and 9.95% higher than existing methods, respectively, which proves the effectiveness of the UGCIBP method.

关键词： Representation learning Social networking (online) Blogs Cyberspace Predictive models Data science Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Fixed-state Log-MAP detection for intensity-modulation and direct-detection optical systems over dispersion-uncompensated links

arXiv

引用

arXiv 2020年

作者： Shuangyue, L.I.U. Zhou, Ji Wang, Haide Mengqi, G.U.O. Xuekai, X.U. Yueming, L.U. Qiao, Yaojun State Key Laboratory of Information Photonics and Optical Communications School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China Department of Electronic Engineering College of Information Science and Technology Jinan University Guangzhou510632 China Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education School ofCyberspace Security Beijing University of Posts and Telecommunications Beijing100876 China

In this paper, an optimized detection using log-maximum a posteriori estimation with a fixed number of surviving states (fixed-state Log-MAP) is proposed for a C-band 64-Gbit/s intensity-modulation and direct-detection (IM/DD) on-off keying (OOK) system over a 100-km dispersion-uncompensated link. For dispersion-uncompensated links, maximum likelihood sequence estimation (MLSE) is usually employed to deal with the severe inter-symbol interference (ISI) caused by chromatic dispersion. However, MLSE has an exponential increase in computational complexity and state storage with an increase in memory length, which overloads the computing resources and internal storage space of the hardware. Compared to MLSE, the fixed-state Log-MAP decreases the computational complexity and state storage from an exponential order of memory length to a linear order of surviving states. The memory length of fixed-state Log-MAP is no longer limited by computing resources and storage resources of the hardware, which has the potential to compensate larger ISI. The experimental results show that the optimal receiver sensitivity using fixed-state Log-MAP detection has a 2-dB improvement compared to that using MLSE. In conclusion, the fixed-state Log-MAP detection shows potential for practical IM/DD optical systems over dispersion-uncompensated links. Copyright © 2020, The Authors. All rights reserved.

关键词： Computational complexity

来源：评论

学校读者我要写书评

暂无评论

An Intrusion Detection Model Based on SMOTE and Convolutional Neural Network Ensemble

引用

Journal of Physics: Conference Series 2021年第1期1828卷

作者： Luyao Tian Yueming Lu Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education Beijing University of Posts and Telecommunications (BUPT) Beijing 100876 China The School of Information and Communication Engineering Beijing University of Posts and Telecommunications (BUPT) Beijing 100876 China

Massive, multi-dimensional and imbalanced network traffic data has brought new challenges to traditional intrusion detection systems (IDSs). The detection performance of traditional algorithms is closely related to feature extractions, which are not effective in the massive and imbalanced data environments. In this paper, we propose an intrusion detection model based on synthetic minority oversampling technology (SMOTE) and convolutional neural network (CNN) ensemble. It converts original traffic vectors into images, designs a CNN structure, and combines SMOTE and CNN ensemble to solve the problem of imbalanced datasets. Using the standard KDD CUP 99 dataset to evaluate the performance of the proposed model and analysing the contribution of features to model decision-making show that the model's F1 score are better than traditional algorithms in the classes with few samples and the model improves the efficiency of network intrusion detection.

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：