检索结果-内蒙古大学图书馆

Automatic detection of breast nodule in the ultrasound images using CNN

The Journal of China Universities of Posts and Telecommunications 2019年第2期26卷 9-16页

作者： Pang Hao Bu Yunyun Wang Cong Xiao Hui School of Software Beijing University of Posts and TelecommunicationsBeijing 100876China Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Ministry of EducationBeijing 100876China Department of Ultrasound Beijing Friendship HospitalCapital Medical University China Electronic Data Service Company Limited

Breast cancer is the most common cancer among women *** is widely used as a harmless test for early breast cancer *** ultrasound network(USNet) model is *** is an improved object detection model specifically for breast nodule detection on ultrasound *** improved the backbone network,optimized the generation of feature maps,and adjusted the loss ***,USNet trained with real clinical *** evaluation results show that the trained model has strong nodule detection *** mean average precision(mAP) value can reach 0.734 *** nodule detection rate is 95.11%,and the in situ cancer detection rate is 79.65%.At the same time,detection speed can reach 27.3 frame per second(FPS),and the video data can be processed in real time.

关键词： convolutional neural network object detection ultrasound breast nodule

来源：评论

学校读者我要写书评

暂无评论

A recommend system for modelling large-scale advertising

A recommend system for modelling large-scale advertising

引用

International Conference on Cyberspace Technology, CCT 2014

作者： Ma, Jing Lu, Yueming School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China Key Laboratory of Trustworthy Distributed Computing and Service BUPT Ministry of Education Beijing China

ISBN: (纸本)9781849199285

In a large-scale network environment, the Internet has produced an amount of digital information such as social media, e-commercial comments, online shopping records and advertising click logs. So, recommend systems not only furnish users with satisfied requirements but also bring about healthy profit to companies. To cope with massive data, we proposed an effective recommend system (ERS) for modelling abundant history data. Firstly, we advise a new data split strategy to make the recommend system fit for large scale advertising. Then, a distributed-recommendation algorithm is designed. Finally, we apply ERS and distributed computing and storage tools (such as Spark, Hadoop, etc.) to model history data aiming at improving the system efficiency. In this paper, we also compare and analyse diverse performances of ERS including its efficiency and its accuracy.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

Chinese Open Relation Extraction with Pointer-Generator Networks

Chinese Open Relation Extraction with Pointer-Generator Netw...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

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

ISBN: (数字)9781728195582

ISBN: (纸本)9781728195599

Most of the traditional Chinese open relation extraction (Open RE) system exploit the syntactic, lexical and other language structure information obtained by natural language processing (NLP) tools from sentences to build hand-crafted patterns for extraction, which is easy to cause error propagation and affect the accuracy of extraction. In this paper, we propose an end-to-end abstract Chinese Open RE model based on the Pointer-Generator network, PGCORE. We employ the results extracted by the state-of-the-art pattern-based Chinese Open RE system as the training set of the model. Experimental results show that our method is outperforms the pattern-based several baselines system, which proves the feasibility and effectiveness of using deep learning models for Chinese Open RE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-time Event Detection and Tracking in Microblog via Text Chain and Sentiment time series

Real-time Event Detection and Tracking in Microblog via Text...

引用

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

A tensor-based sub-mode coordinate algorithm for stock prediction 3

A tensor-based sub-mode coordinate algorithm for stock predi...

引用

3rd IEEE International Conference on Data Science in Cyberspace, DSC 2018

作者： Huang, Jieyun Zhang, Yunjia Zhang, Jialai Zhang, Xi Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education Beijing University of Posts and Telecommunications Beijing China School of Electronic Information Sichuan University Chengdu China

ISBN: (纸本)9781538642108

The investment on the stock market is prone to be affected by the Internet. For the purpose of improving the prediction accuracy, we propose a multi-task stock prediction model that not only considers the stock correlations but also supports multi-source data fusion. Our proposed model first utilizes tensor to integrate the multi-sourced data, including financial Web news, investors' sentiments extracted from the social network and some quantitative data on stocks. In this way, the intrinsic relationships among different information sources can be captured, and meanwhile, multi-sourced information can be complemented to solve the data sparsity problem. Secondly, we propose an improved sub-mode coordinate algorithm (SMC). SMC is based on the stock similarity, aiming to reduce the variance of their subspace in each dimension produced by the tensor decomposition. The algorithm is able to improve the quality of the input features, and thus improves the prediction accuracy. And the paper utilizes the Long Short-Term Memory (LSTM) neural network model to predict the stock fluctuation trends. Finally, the experiments on 78 A-share stocks in CSI 100 and thirteen popular HK stocks in the year 2015 and 2016 are conducted. The results demonstrate the improvement on the prediction accuracy and the effectiveness of the proposed model. © 2018 IEEE.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

A method based on MD5 and time for preventing deception in electronic commerce

A method based on MD5 and time for preventing deception in e...

引用

International Conference on Cyberspace Technology, CCT 2014

作者： Hu, Zhenggang Lu, Yueming School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China Key Laboratory of Trustworthy Distributed Computing and Service BUPT Ministry of Education Beijing China

ISBN: (纸本)9781849199285

Aiming at reducing the risk of data being intercepted and preventing deceptions in the electronic commerce, this paper proposes a method based on MD5 and time which can effectively prevent the deception in data transmission. The method uses the traditional MD5 algorithm to encrypt and validate important data, then verifying the validity and legitimacy of the data by using time.

关键词： Electronic commerce MD5 algorithm Preventing deception Time

来源：评论

学校读者我要写书评

暂无评论

Security-Critical Components Recognition Algorithm for Complex Heterogeneous Information Systems

引用

Computers, Materials & Continua 2021年第8期68卷 2579-2595页

作者： Jinxin Zuo Yueming Lu Hui Gao Tong Peng Ziyv Guo Tong An Enjie Liu School of Cyberspace Security Beijing University of Posts and TelecommunicationsBeijing100876China Key Laboratory of Trustworthy Distributed Computing and Service(BUPT) Ministry of EducationBeijing100876China School of Information and Communication Engineering Beijing University of Posts and TelecommunicationsBeijing100876China University of Bedfordshire Institute for Research in Applicable Computing(IRAC)LutonUK

With the skyrocketing development of technologies,there are many issues in information security quantitative evaluation(ISQE)of complex heterogeneous information systems(CHISs).The development of CHIS calls for an ISQE model based on security-critical components to improve the efficiency of system security evaluation *** this paper,we summarize the implication of critical components in different filed and propose a recognition algorithm of security-critical components based on threat attack tree to support the ISQE *** evaluation model establishes a framework for ISQE of CHISs that are updated ***,with the support of asset identification and topology data,we sort the security importance of each asset based on the threat attack tree and obtain the security-critical components(set)of the ***,we build the evaluation indicator tree of the evaluation target and propose an ISQE algorithm based on the coefficient of variation to calculate the security quality value of the ***,we present a novel indicator measurement uncertainty aiming to better supervise the performance of the proposed *** results show the advantages of the proposed algorithm in the evaluation of CHISs.

关键词： Complex heterogeneous information system security-critical component threat attack tree information security quantitative evaluation

来源：评论

学校读者我要写书评

暂无评论

Multiple Vandermonde Decomposition Based Channel Estimation for Mm Wave MIMO High-Mobility Communication in 5G and Beyond

引用

China Communications 2023年第4期20卷 12-25页

作者： Zhao Yi Xiaojun Jing School of Electronics and Information Hunan First Normal UniversityChangsha 410205China Key Laboratory of Trustworthy Distributed Computing and Service Ministry of EducationBeijing University of Posts and TelecommunicationsBeijing 100876China School of Information and Communication Engineering Beijing University of Posts and TelecommunicationsBeijing 100876China

Millimeter wave(mmWave)massive massive multiple input multiple output(MIMO)technique has been regarded as the viable solution for vehicular communications in 5G and *** achieve the substantial increase in date rates,it is important to take an effective channel state information(CSI).However,existing channel estimation strategies are unavailable since the users *** solve above issues,in this paper,inspired by a specific antenna structure,we propose a novel approach for fast time-varying channel ***,by considering the vehicle scenario with high-mobility,a corresponding mathematical model is firstly ***,based on the special structural of the sparse array,the switch network is used to replace the convention phase shifter of mmWave hybrid system,which can effectively reduce the number of radio-frequency(RF)chains and ***,by solving the semidefinite programming(SDP)duality problem,the Doppler frequency and path parameters are effectively *** results are shown that the computational complexity and estimation accuracy of the proposed algorithm is superior than that of the traditional schemes.

关键词： MIMO mmWave channel estimation high-mobility time-variant

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

Neural Network Based Target User Recognition Model for Network Community 6

Neural Network Based Target User Recognition Model for Netwo...

引用

6th Annual 2018 International Conference on Geo-Spatial Knowledge and Intelligence, GSKI 2018

作者： Wu, Xu Dai, Yulun Xie, Xiaqing Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education China School of Cyberspace Security BUPT China Beijing University of Posts and Telecommunications Library Beijing100876 China

For multi-dimensional feature of user data in network community, available methods mainly use Rank scoring algorithm or user classification algorithm for target user recognition. However, Rank method has a low performance, and the classification algorithm needs high construction cost. Therefore, this paper uses a target user recognition model integrating the user content analysis and the user behavior analysis to improve performance and speed of the target user recognition by a neural network content analysis model with a single-layer neural network and N-gram features for discovering automatically the user feature. The proposed method outperforms the current Rank scoring and classification methods in terms of performance, in which the F value reaches 0.89 and the accuracy reaches 0.91. Moreover, avoiding the cost of manual design dependent on specific tasks shortens the training time. Ten thousand data can be modeled in one minute. © Published under licence by IOP Publishing Ltd.

关键词： Network layers

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：