检索结果-内蒙古大学图书馆

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Bingxu Piao Xu Wu Jingchen Wu Xiaqing Xie Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education

ISBN: (数字)9781728195582

ISBN: (纸本)9781728195599

Microblog becomes one of the most popular media for sharing first-hand information. As more close to real event, detecting and tracking event in microblogs is a research hotspot. To alleviate feature sparsity problem, traditional event detection and tracking methods exploit comments, replies, and reposts to enrich the information of posts. However, ignoring text relationship only leads to more irrelevant information. Aiming at this issue, a novel real-time event detection and tracking method for microblog stream is proposed. For each microblog from the real-time stream, similarity against historical event set is first evaluated. Then, known event microblogs are partitioned by the proposed method sentiment time series, clustered based on word relation graph, and compare with the previous graph to track burst keywords. Meanwhile, text chain is introduced to detect events for unknown event microblogs. Text chain is a unique relationship of microblogs, in which comments, replies, and reposts are used to form a word relation graph of the corresponding post. Posts and attached graphs are clustered to detect new events. Experiments are performed on real-time microblog datasets to evaluate the effectiveness of methods. Results show that the proposed method gains better F-measure than similar methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SemHARQ: Semantic-Aware HARQ for Multi-task Semantic Communications

arXiv

引用

arXiv 2024年

作者： Hu, Jiangjing Wang, Fengyu Xu, Wenjun Gao, Hui Zhang, Ping The State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China The School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China The State Key Laboratory of Network and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China The Peng Cheng Laboratory Shenzhen518066 China The Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education Beijing University of Posts and Telecommunications Beijing100876 China

Intelligent task-oriented semantic communications (SemComs) have witnessed great progress with the development of deep learning (DL). In this paper, we propose a semantic-aware hybrid automatic repeat request (SemHARQ) framework for the robust and efficient transmissions of semantic features. First, to improve the robustness and effectiveness of semantic coding, a multi-task semantic encoder is proposed. Meanwhile, a feature importance ranking (FIR) method is investigated to ensure the important features delivery under limited channel resources. Then, to accurately detect the possible transmission errors, a novel feature distortion evaluation (FDE) network is designed to identify the distortion level of each feature, based on which an efficient HARQ method is proposed. Specifically, the corrupted features are retransmitted, where the remaining channel resources are used for incremental transmissions. The system performance is evaluated under different channel conditions in multi-task scenarios in Internet of Vehicles. Extensive experiments show that the proposed framework outperforms state-of-the-art works by more than 20% in rank-1 accuracy for vehicle re-identification, and 10% in vehicle color classification accuracy in the low signal-to-noise ratio regime. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Linear uncertainty quantification of graphical model inference 24

Linear uncertainty quantification of graphical model inferen...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Chenghua Guo Han Yu Jiaxin Liu Chao Chen Qi Li Sihong Xie Xi Zhang Key Laboratory of Trustworthy Distributed Computing and Service (MoE) Beijing University of Posts and Telecommunications China College of Artificial Intelligence Beijing University of Posts and Telecommunications China Department of Computer Science and Engineering Lehigh University School of Computer Science and Technology Harbin Institute of Technology (Shenzhen) China Department of Computer Science Iowa State University AI Thrust The Hong Kong University of Science and Technology (Guangzhou) China

ISBN: (纸本)9798331314385

Uncertainty Quantification (UQ) is vital for decision makers as it offers insights into the potential reliability of data and model, enabling more informed and risk-aware decision-making. Graphical models, capable of representing data with complex dependencies, are widely used across domains. Existing sampling-based UQ methods are unbiased but cannot guarantee convergence and are time-consuming on large-scale graphs. There are fast UQ methods for graphical models with closed-form solutions and convergence guarantee but with uncertainty underestimation. We propose LinUProp, a UQ method that utilizes a novel linear propagation of uncertainty to model uncertainty among related nodes additively instead of multiplicatively, to offer linear scalability, guaranteed convergence, and closed-form solutions without underestimating uncertainty. Theoretically, we decompose the expected prediction error of the graphical model and prove that the uncertainty computed by LinUProp is the generalized variance component of the decomposition. Experimentally, we demonstrate that LinUProp is consistent with the sampling-based method but with linear scalability and fast convergence. Moreover, LinUProp outperforms competitors in uncertainty-based active learning on four real-world graph datasets, achieving higher accuracy with a lower labeling budget.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Human motion recognition by three-view kinect sensors in virtual basketball training

Human motion recognition by three-view kinect sensors in vir...

引用

2020 IEEE Region 10 Conference, TENCON 2020

作者： Yao, Baoqi Gao, Hui Su, Xin Beijing University of Posts and Telecommunications Key Laboratory of Trustworthy Distributed Computing and Service China Tsinghua University Beijing National Research Center for Information Science and Technology Beijing China

ISBN: (纸本)9781728184555

In recent years, human action recognition has received a considerable amount of research attention because of it's potential in a variety of applications, such as video surveillance, human-computer interaction, and virtual reality (VR). However, many researches on human action recognition performed in single-camera or double-camera system, which achieve reduced performance due to vulnerability to partial occlusion and miss-recognition of back. Some works on human action recognition use multiple cameras but are too complex for practical application. In this paper, we propose a new human action recognition system using triple Kinect sensors for VR application. Particularly, we design a mark detection method to determine the front of user and fusion skeleton data in real time. Features are extracted from three-dimensional (3D) skeleton data sequences, and divided into five parts according to body parts. A classification model based on the part-aware long short-term memory networks is proposed to recognize human motion. Finally, we demonstrate the system with a virtual reality basketball application and the results of experiment validate the feasibility of the proposed system. © 2020 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

TAFM: Topic-Attention FM-encoder for Text Generation 7

TAFM: Topic-Attention FM-encoder for Text Generation

引用

7th IEEE International Conference on Data Science in Cyberspace, DSC 2022

作者： He, Dongye Sun, Lijuan Wu, Jingchen Gao, Yutong Wu, Xu Qiu, Lirong Beijing University of Posts and Telecommunications Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education Beijing China Beijing University of Posts and Telecommunications School of Cyberspace Security Bupt Beijing China Beijing University of Posts and Telecommunications School of Economics and Management Bupt Beijing China Bupt Beijing China Beijing Jiaotong University Beijing University of Posts and Telecommunications Beijing China Beijing University of Posts and Telecommunications Library Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9781665474801

ISBN: (纸本)9781665474801

With the development and application of deep learning, the research of text generation has made great progress, especially in the fields of machine translation, dialogue generation, etc. However, with the application of text generation model in practical engineering, the semantic control of text generation becomes an important problem to be solved urgently. At present, text generation has some good effects in emotional control and temporal control, but it has not achieved good results in semantic control of keywords. The key problem is how to use the keywords semantic information encoding and how to use the keywords semantic information in the text generation process. In view of the above problems, a self encoding and decoding framework integrating factorization machine and topic-weighted attention mechanism is proposed, which is named TAFM. The factorization machine model can focus on refining the combination characteristics between keywords, so as to more comprehensively represent the semantic information of keywords combination. The topic-weighted attention mechanism weights and adds the generated text coding and keyword semantic coding. Adjusting the weight can be vividly understood as adjusting the control intensity of semantic information. Thus, it is more conducive to the expression of topic information. The experimental results show that our method obtains a better BLEU score. In addition, our method can generate coherent sentences containing keywords through manual evaluation. © 2022 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Dynamic Music emotion recognition based on CNN-BiLSTM

Dynamic Music emotion recognition based on CNN-BiLSTM

引用

IEEE Information Technology and Mechatronics Engineering Conference (ITOEC)

作者： Pengfei Du Xiaoyong Li Yali Gao Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Ministry of Education

ISBN: (数字)9781728143231

ISBN: (纸本)9781728143248

Most of the music information will express the emotional signal, the emotional classification of music can be more convenient for the organization and retrieval of music, is the use of music for psychological intervention and physiological adjustment of the premise. In this paper, the dynamic emotion recognition of music, using the VA model, a song to produce a set of VA value. This paper first elaborates the relevant background and emotion classification model of music emotion recognition, and explain the representations of emotion, designs the overall framework of dynamic music emotion recognition, and adopts the convolution neural network and the BiLSTM fusion way to carry on the music dynamic VA And then compared with other relevant methods of identification.

关键词： Music Emotion recognition Feature extraction Logic gates Multiple signal classification Psychology Task analysis

来源：评论

学校读者我要写书评

暂无评论

Research on Staged Practice Teaching System Based on Systems Engineering

引用

计算机教育 2021年第12期 51-55页

作者： Wanjiang Han Jincui Yang Tao Qi Pengfei Sun Xin Jin Jinpeng Chen Yongping Zhang School of Computer Science(National Pilot Software Engineering School)Beijing University of Posts and Telecommunication Key Laboratory of Trustworthy Distributed Computing and Service(BUPT)Ministry of EducationBeijing100876China

The practical teaching management system is an important factor to ensure the quality of *** training of systematic thinking needs a systematic teaching system,and a systematic process is a gradual process and a standardized *** paper discusses the process of establishing a standardized practice teaching system step by step through a progressive *** the same time,taking test practice as an example,it describes how the practice teaching system enables students to gradually adapt to and benefit from the management of the *** project practice,students not only enhance their practical ability,but also learn the standardized practice *** skills can help students adapt to the work pace of the enterprise faster,and make students’practical ability meet the requirements of the enterprise.

关键词： Practice Teaching System Test Practice Staged Practical Process Standardization System Practice Base

来源：评论

学校读者我要写书评

暂无评论

Employ Multimodal Machine Learning for Content Quality Analysis

Employ Multimodal Machine Learning for Content Quality Analy...

引用

IEEE Information Technology, Networking, Electronic and Automation Control Conference

作者： Pengfei Du Xiaoyong Li Yali Gao Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Ministry of Education

ISBN: (数字)9781728143903

ISBN: (纸本)9781728143910

User-generated content varies drastically, and todays mainstream media sites have a lot of information presented in graphic form. So the task of identifying high-quality content becomes increasingly important, and it can improve overall reading time and ctr(click-through rate estimates). Traditional quality assessment method based only on single modes, for example in image quality assessment area it can divide into IQA method and NR-IQA method, and in text quality assessment area we use different indicators such as readability and smoothness, but there are some limitations in analyzing quality from single mode, many information will lose by single modal analysis. In this paper we propose a multimodal quality recognition approach. We use Transformers-XL which is more efficient and accurate for text feature extract, and use inceptionv3 for the original image feature extract, in order to solve the problem of multi-graph fusion we use NeXtVLAD for graph fusion. Then we use siamese network to score the content quality, and the rank loss is used as the optimization objective. We crawled many data from different website such as WeiboTwitter to constitute the validation data set. Compare with other method such as single modal method and other multimodal deep learning method, our approach got a state of art result.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Review of Semi-Structured Document Information Extraction Techniques Based on Deep Learning

Review of Semi-Structured Document Information Extraction Te...

引用

Machine Learning, Cloud computing and Intelligent Mining (MLCCIM), International Conference on

作者： Yangchun Li Wei Jiang Shouyou Song Chinese Academy of Cybersapce Studies School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing China Chinese Academy of Cybersapce Studies Beijing China Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Chinese Academy of Cybersapce Studies Ministry of Education Beijing University of Posts and Telecommunications Beijing China

With the advent of global digital transformation, using an intelligent method based on deep learning to extract crucial information from semi-structured documents, as represented by various types of receipts and invoices, has emerged as an imperative measure to ensure business stability, data security, and improved work efficiency. This paper provides a detailed review on deep learning-based techniques for information extraction, with systematic introduction, hierarchical analysis, method comparison, and summary with expectations for future development. The review begins with a comprehensive explication of the defining characteristics of semi-structured documents, along with a detailed introduction to the research background, application areas, and technical challenges related to information extraction from semi-structured documents. Then the review extends to an overview of two developmental stages, i.e. the shift from traditional information extraction to deep learning-based information extraction, followed by discussion about technical architecture and method classification, which elaborates on key technologies in terms of typical datasets, detection and recognition, and information reduction. Lastly, paper summarizes the prospects and development in the field. Future research will focus on strengthening algorithm universal and lightweight, as well as improving information protection capabilities and the diversity of datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Effective Encrypted Traffic Classification Method Based on Pruning Convolutional Neural Networks for Cloud Platform

An Effective Encrypted Traffic Classification Method Based o...

引用

作者： Zilong Han Erxia Li Shichao Li Xiaoyong Li Chaoqun Kang Ruiwen Deng Yali Gao State Grid Shanghai Energy Interconnection Research Institute Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Ministry of Education Beijing University of Posts and Telecommunications

With the rapid development of cloud computing technology,the traffic of cloud platform also increases *** of these traffic adopt encryption technology,the original traffic classification method is no longer *** this paper,we propose an efficient encrypted traffic classification method based on pruning convolution neural network:*** method does not need to extract features manually,but automatically extracts high-level features through CNN,which makes the model have generalization ability and reduces the *** the pruning technology is adopted to prune the model and retain the parameters that are highly important to the model,which greatly reduces the size and computation of the model and will not affect the performance of the *** used the public network dataset ISCXVPN2016 to verify our proposed method,the experiments show that the F1 score of our proposed approach is 93% which is improved by 3%,and the precision is 94%,which is improved by 5%.

关键词： encrypted traffic classification convolutional neural network pruning end-to-end

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：