检索结果-内蒙古大学图书馆

Annual IEEE Northeast Workshop on Circuits and Systems (NEWCAS)

作者： Di Chen Hui Gao Na Chen Ruohan Cao 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 Graduate School of Science and Technology Nara Institute of Science and Technology Ikoma Japan

Reconfigurable intelligent surface (RIS) has gained wide attention recently as a promising solution to address the blockage issue in millimeter wave (mmWave) communication networks. In this paper, we consider a RIS-assisted mmWave communication system consisting of multiple RISs and users. A novel integrated scheme based on deep reinforcement learning (DRL) is proposed to jointly optimize the hybrid beamforming, phase shifts, and power allocation. Specifically, we design a multi-variable action output to achieve integrated optimization in both beam and power domains. We also design a weighted sum reward to balance the influence of beam and power domain optimizing variables in the training process. Experimental results demonstrate that the proposed DRL-based method can achieve at least 37% higher sum rates than the baseline algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Named Entity Recognition of Chinese Diabetic Literature by Integrating General Domain Knowledge 4

Named Entity Recognition of Chinese Diabetic Literature by I...

引用

4th IEEE International Conference on Computer and Communication Engineering Technology, CCET 2021

作者： Zhang, Duochuan Beijing University of Posts and Telecommunications School of Computer National Demonstrative Software School Beijing China Key Laboratory of Trustworthy Distributed Computing and Service Beijing University of Posts and Telecommunications Ministry of Education Beijing China

ISBN: (纸本)9781665438902

In the field of named entity recognition of diabetes literature, due to the lack of large-scale and high-quality annotation data sets, the traditional named entity recognition technology has the drawback of insufficient language feature extraction and poor generalization ability. In view of the above problems, this paper proposes an entity recognition method that integrates general domain knowledge for naming entity recognition in diabetes literature. This method uses Word2vec algorithm to generate feature level vectors based on Chinese diabetes literature. On this basis, the feature vectors are fused with the feature vectors generated by the pretraining model of BERT on the Chinese Wikipedia corpus, and uses principal component analysis to reduce the redundant feature vectors and enhance the expression ability of feature vectors in the general language scope. Then the context features are extracted by bidirectional long-term and short-term memory network, and finally the entity label sequence is generated by conditional random field decoding. The experiment proves that the model which integrates general domain knowledge is better than other traditional models in the recognition of Chinese diabetes literature, and the highest F1 value is 71.08%. © 2021 IEEE.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

Multi-source and multi-dimensional network security situational awareness model

Multi-source and multi-dimensional network security situatio...

引用

2020 International Conference on Cyberspace Innovation of Advanced Technologies, CIAT 2020

作者： Lv, Luqin Lu, Yueming School of Cyberspace Security Key Lab of Trustworthy Distributed Computing and Service Ministry of Education Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9781450387828

Aiming at the problem that single protection technology is difficult to meet the needs of network security, the rationality and accuracy of situation assessment index are poor, the multi-source and multi-dimensional network security situation awareness model and multi-source data association analysis method are proposed. This model combines with data acquisition, data preprocessing, abnormal analysis, security threat assessment and situation visualization. By using Apriori algorithm to mine the relationship between multiple sources of data, the strong rules are filtered out. The experimental results show that the model can accurately perceive known intrusion, unknown threat and its own vulnerability. © 2020 ACM.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Robust text clustering with graph and textual adversarial learning 5

Robust text clustering with graph and textual adversarial le...

引用

5th IEEE International Conference on Data Science in Cyberspace, DSC 2020

作者： Liang, Yongming Tian, Tian Jin, Kaifu Yang, Xiaoyu Lv, Yuefei Zhang, Xi Beijing University of Posts and Telecommunications Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education Beijing China

ISBN: (纸本)9781728195582

Text clustering is a fundamental task that finds groups of similar texts in the corpus. Deep learning based models can capture the semantic and syntactic information in local word sequences to represent the texts but may ignore global text structures in the corpus. Recently, Graph Convolutional Networks (GCNs) have achieved the state-of-the-art performance in many applications, which may facilitate the text clustering task by exploiting the graph structures between texts via words and phrases. However, GCNs are vulnerable to adversarial attacks, e.g., small perturbations in graph structures and node attributes lead to poor performance. To address this issue, we propose a Robust Text Clustering (RTC) approach which consists of both autoencoder and GCN modules to exploit the local text features and global text structures respectively in one unified framework. We generate two types of adversarial perturbations targeting text structure and graph structure, and develop an adversarial training method to improve the robustness and generalization of the RTC framework. Extensive experiments on two real-world datasets demonstrate the effectiveness of our proposal in text clustering. © 2020 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Framework Design for Decentralized Digital Identity Across Borders

引用

Strategic Study of CAE 2025年第1期27卷 88-97页

作者： Jian, Chen Zhiming, Cai Jiayin, Qi Binxing, Fang Faculty of Data Science City University of Macau Macao999078 China Faculty of Digital Science and Technology Macau Millennium College Macao999078 China Cyberspace Institute of Advanced Technology Guangzhou University Guangzhou510006 China Huangpu Graduate School of Guangzhou University Guangzhou510006 China Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education Beijing100084 China

In the digital era, the challenges of data sovereignty and the conflict between personal data privacy protection and efficient access are becoming more pronounced. As a critical foundational support for resolving this contradiction, the digital identity framework holds significant research values. Based on a review of the research and development trends in cross-border digital identity authentication models, this study proposes a decentralized, distributed framework for cross-border identity authentication. The framework incorporates a data classification and grading strategy, and features three core components: a blockchain-based decentralized identity management mechanism, a universal certification pool model for dynamic data attribute classification and grading, and privacy protection and access control strategies. These components are designed to overcome the trust and compliance issues inherent in traditional centralized models in cross-border scenarios. Furthermore, this study delves into the application challenges of the cross-border digital identity authentication framework, such as the efficiency and accuracy of attribute association and heterogeneous grading, and the strategic interaction of trust boundaries for attribute authorization between cross-border parties. It refines corresponding solutions from the perspectives of application encapsulation of the authentication framework through application programming interface (API) models, evaluation criteria for the authentication framework, and implementation pathways. The proposed framework not only provides practical references for cross-border digital identity authentication but also offers new technical insights and implementation pathways for establishing unified standards and security protocols for cross-border data flow. © 2025 Beijing Zhongguo Gongcheng Kexue Zazhishe. All rights reserved.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Incomplete Fingerprint Recognition Based on Inproved GA-PSO

引用

Chinese Journal of Electronics 2023年第4期22卷 769-772页

作者： JING Xiaojun ZHANG Jie JIANG Haixia ZHONG Mingliang TAO Lei School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China Key Labaratory of Trustworthy Distributed Computing and Service (BUPI) Ministry of Education Beijing University of Posts and Telecommunications Beijing China College of Information and Communication Engineering Harbin Engineering University Harbin China

Minutiae-based algorithm plays a more and more important role in fingerprint recognition. It is greatly limited by its demand for good image quality and dependence on fingerprint aligning, especially for incomplete fingerprint recognition. Improved Genetic algorithm-Particle swarm optimization (GA-PSO) algorithm is applied to deal with these problems. The proposed algorithm improves GA-PSO in two aspects, population initialization based on reference point pre-aligning and fitness function construction based on fusion of minutiae-matching and orientation-matching. The experimental results on the FVC2004 show the high effectiveness and practicability of our algorithm.

关键词： Image quality Sociology Fingerprint recognition Wavelet analysis Statistics Particle swarm optimization Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

A Logical Combination Based Application Layer Intrusion Detection Model

A Logical Combination Based Application Layer Intrusion Dete...

引用

2020 International Conference on Cyberspace Innovation of Advanced Technologies, CIAT 2020

作者： Wang, Hao Yang, Jian Lu, Yueming School of Cyberspace Security Key Lab of Trustworthy Distributed Computing and Service Ministry of Education Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9781450387828

In enterprise network attack intrusion detection system, false positives and false negatives are the opposite of each other, and it is difficult to achieve both, so reducing false positives rate and false negatives rate is one of the core problems of IDS. Snort and Suricata adopts misuse detection mode, which has low calculation cost and high accuracy, but it has a high false negatives rate and cannot detect unknown attacks. The anomaly detection system based on machine learning and data mining has a high detection rate for unknown attacks, but a high false positives rate. In view of the shortcomings of the two detection technologies, this paper proposes LC-IDS (logical combination based intrusion detection system), which combines the advantages of misuse detection method based on rule matching and anomaly detection method based on LSTM model, and adopts the methods of phased detection, alarm merge aggregation. The experimental results show that, compared with the single intrusion detection technology, this scheme can maintain a low false positives rate and improve the true positive rate of attack traffic. © 2020 ACM.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Mask Neural Network for Predicting Flight Ticket Price 6th

Mask Neural Network for Predicting Flight Ticket Price

引用

6th Conference on Signal and Information Processing, Networking and Computers, ICSINC 2019

作者： Zhang, Qianqian He, Yuan Jing, Xiaojun Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9789811541629

Recently, the global air traffic has increased rapidly, most passengers choose to buy tickets in their own experiences. So accurately predicting flight ticket price is of great significance. Recently there exist some works on flight ticket price prediction. However, these works pay attention to solve a single flight price prediction. However, it’s unrealistic to build a lot of models for different flights. In this paper, we consider a lot of factors, including additional service data, flight data and time data. Firstly, we analyze data and extract flight information and time features. Furthermore, we propose a model: mask neural network, to solve flight ticket price prediction, which divides the features into two parts: individual information and general information. General information represents the portrait of a certain flight and individual information represents features of a certain flight. Since every flight has its own distribution, we cannot put individual information into the network directly. So we introduce mask concept and use general information as a mask to filter individual information. Experiments on a competition dataset with 3 months datasets introduce the effectiveness of our approaches, that can achieve the state-of-the-art in ticket price prediction. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Not All Image Regions Matter: Masked Vector Quantization for Autoregressive Image Generation

Not All Image Regions Matter: Masked Vector Quantization for...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Mengqi Huang Zhendong Mao Quan Wang Yongdong Zhang University of Science and Technology of China Hefei China Institute of Artificial intelligence Hefei Comprehensive National Science Center Hefei China MOE Key Laboratory of Trustworthy Beijing University of Posts and Telecommunications Distributed Computing and Service Beijing China

Existing autoregressive models follow the two-stage generation paradigm that first learns a codebook in the latent space for image reconstruction and then completes the image generation autoregressively based on the learned codebook. However, existing codebook learning simply models all local region information of images without distinguishing their different perceptual importance, which brings redundancy in the learned codebook that not only limits the next stage's autoregressive model's ability to model important structure but also results in high training cost and slow generation speed. In this study, we borrow the idea of importance perception from classical image coding theory and propose a novel two-stage framework, which consists of Masked Quantization VAE (MQVAE) and Stackformer, to relieve the model from modeling redundancy. Specifically, MQ-VAE incorporates an adaptive mask module for masking redundant region features before quantization and an adaptive de-mask module for recovering the original grid image feature map to faithfully reconstruct the original images after quantization. Then, Stackformer learns to predict the combination of the next code and its position in the feature map. Comprehensive experiments on various image generation validate our effectiveness and efficiency. Code will be released at https://***/CrossmodalGroup/MaskedVectorQuantization.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Not All Image Regions Matter: Masked Vector Quantization for Autoregressive Image Generation

arXiv

引用

arXiv 2023年

作者： Huang, Mengqi Mao, Zhendong Wang, Quan Zhang, Yongdong University of Science and Technology of China Hefei China MOE Key Laboratory of Trustworthy Distributed Computing and Service Beijing University of Posts and Telecommunications Beijing China Institute of Artificial intelligence Hefei Comprehensive National Science Center Hefei China

Existing autoregressive models follow the two-stage generation paradigm that first learns a codebook in the latent space for image reconstruction and then completes the image generation autoregressively based on the learned codebook. However, existing codebook learning simply models all local region information of images without distinguishing their different perceptual importance, which brings redundancy in the learned codebook that not only limits the next stage’s autoregressive model’s ability to model important structure but also results in high training cost and slow generation speed. In this study, we borrow the idea of importance perception from classical image coding theory and propose a novel two-stage framework, which consists of Masked Quantization VAE (MQ-VAE) and Stackformer, to relieve the model from modeling redundancy. Specifically, MQ-VAE incorporates an adaptive mask module for masking redundant region features before quantization and an adaptive de-mask module for recovering the original grid image feature map to faithfully reconstruct the original images after quantization. Then, Stackformer learns to predict the combination of the next code and its position in the feature map. Comprehensive experiments on various image generation validate our effectiveness and efficiency. Code will be released at https: / / github. com / CrossmodalGroup / MaskedVectorQuantization. Copyright © 2023, The Authors. All rights reserved.

关键词： Redundancy

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：