检索结果-内蒙古大学图书馆

Unified Contextualized Knowledge Embedding Method for Static and Temporal Knowledge Graph

IEEE/ACM Transactions on Audio Speech and Language Processing 2024年 33卷 82-95页

作者： Gao, Yifu Qiao, Linbo Huang, Zhen Kan, Zhigang He, Yongquan Li, Dongsheng National University of Defense Technology National Key Laboratory of Parallel and Distributed Computing College of Computer Science and Technology Changsha410000 China Intelligent Game and Decision Lab Beijing China Meituan Beijing100102 China

Recent years, there is a growing interest in knowledge graph embedding (KGE), which maps symbolic entities and relations into low-dimensional vector space to effectively represent structured data from the knowledge graph. In addition, the concept of temporal knowledge graph is proposed to document dynamically changing facts in the real world. Existing works attempt to incorporate temporal information into static KGE methods to accomplish temporal knowledge representations. However, existing static or temporal KGE approaches focus on the single query fact and ignore the query-relevant contextual information in the graph structure. This paper moves beyond the traditional way of scoring facts in distinct vector space and proposes a unified framework with pre-trained language models (PLM) to learn dynamic contextualized static/temporal knowledge graph embeddings, called CoS/TKGE. Given the query-specific subgraph, our model transforms it into an input sequence and uses the PLM to obtain the contextualized knowledge representations, which is flexible adaptive to the input graph contexts. We reformulate the link prediction task as a mask prediction problem to fine-tune the pre-trained language model. And the contrastive learning technique is employed to align dynamic contextual embeddings with static global embeddings. Experimental results on three widely used static and temporal KG datasets show the superiority of our model. © 2014 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Predicting cement compressive strength using double-layer multi-expression programming

Predicting cement compressive strength using double-layer mu...

引用

4th International Conference on Computational and Information Sciences, ICCIS 2012

作者： Zhang, Qingke Yang, Bo Wang, Lin Zhu, Fuxiang Shandong Province Key Laboratory of Network Based Intelligent Computing University of Jinan Jinan China Computer Networks and Distributed Systems Laboratory Beijing Institute Technology Beijing China

ISBN: (纸本)9780769547893

This paper presents a novel algorithm named Double-layer Multi-expression Programming (DMEP). Then DMEP model is applied to the prediction of 28-day Portland cement compressive strength. We compare DMEP model with other four soft computing models, namely Multi-Expression Programming model (MEP), Gene Expression Programming model (GEP), Neural Networks model (NN) and Fuzzy logic model (FL) on 28-day cement strength prediction. The experiment results show that DMEP model has a lower rate in RMSE and MAE, and the prediction average percentage error of the cement strength data using DMEP model is reduced to 2.18%, which is lower than other four models. The results obtained from the computational tests demonstrate that DMEP is a promising technique for the prediction of cement strength. © 2012 IEEE.

关键词： Soft computing

来源：评论

学校读者我要写书评

暂无评论

Pre-training of an artificial neural network for software fault prediction 7

Pre-training of an artificial neural network for software fa...

引用

7th International Conference on Computer and Knowledge Engineering, ICCKE 2017

作者： Owhadi-Kareshk, Moein Sedaghat, Yasser Akbarzadeh, Mohammad-R.-T. Center of Excellence On Soft Computing and Intelligent Information Processing Ireland Dependable Distributed Embedded Systems Laboratory Department of Computer Engineering Ferdowsi University of Mashhad Mashhad Iran

ISBN: (纸本)9781538608043

Software fault prediction is one of the significant stages in the software testing process. At this stage, the probability of fault occurrence is predicted based on the documented information of the software systems that are already tested. Using this prior knowledge, developers and testing teams can better manage the testing process. There are many efforts in the field of machine learning to solve this classification problem. We propose to use a pre-training technique for a shallow, i.e. with fewer hidden layers, Artificial Neural Network (ANN). While this method is usually employed to prevent over-fitting in deep ANNs, our results indicate that even in a shallow network, it improves the accuracy by escaping from local minima. We compare the proposed method with four SVM-based classifiers and a regular ANN without pre-training on seven datasets from NASA codes in the PROMISE repository. Results confirm that the pre-training improves accuracy by achieving the best overall ranking of 1.43. Among seven datasets, our method has higher accuracy in four of them, while ANN and support vector machine are the best for two and one datasets, respectively. © 2017 IEEE.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

Collaborative Caching in P2P Streaming Systems 15th

Collaborative Caching in P2P Streaming Systems

引用

15th Web Information Systems and Applications Conference, WISA 2018

作者： Gao, Guoqiang Li, Ruixuan Engineering Research Center of Hubei Province for Clothing Information Wuhan Textile University Wuhan430073 China Intelligent and Distributed Computing Laboratory School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9783030029333

In the past decade, Peer-to-Peer (P2P) Systems achieved great successes. Its fascinating characteristics, such as decentralized control, self-governance, fault tolerance and load balancing, make it the default infrastructure for file sharing applications. Today, P2P system is one of the largest Internet bandwidth consumers. In order to relieve the burden on Internet backbone and improve the user access experience, efficient caching strategies should be applied. In this paper, we propose a novel collaborative caching in P2P streaming systems. This strategy first calculates the factor of each cached file through their caching value, and then replaces the file with the lowest factor. The simulation experiments show that our strategy has higher cache hits and lower system load. © 2018, Springer Nature Switzerland AG.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

Joint Deep Matching Model of OCT Retinal Layer Segmentation

引用

Computers, Materials & Continua 2020年第6期63卷 1485-1498页

作者： Mei Yang Yuanjie Zheng Weikuan Jia Yunlong He Tongtong Che Jinyu Cong School of Information Science and Engineering at Shandong Normal University Jinan250358China Key Lab of Intelligent Computing and Information Security in Universities of Shandong Shandong Provincial Key Laboratory for Novel Distributed Computer Software TechnologyInstitute of Biomedical SciencesShandong Normal UniversityJinan250358China INSA Lyon University of LyonCNRSInsermVilleurbanne69621 CedexFrance

Optical Coherence Tomography(OCT)is very important in medicine and provide useful diagnostic *** retinal layer thicknesses plays a vital role in pathophysiologic factors of many ocular *** the existing retinal layer segmentation approaches,learning or deep learning-based methods belong to the ***,most of these techniques rely on manual-marked layers and the performances are limited due to the image *** order to overcome this limitation,we build a framework based on gray value curve matching,which uses depth learning to match the curve for semi-automatic segmentation of retinal layers from *** depth convolution network learns the column correspondence in the OCT image *** whole OCT image participates in the depth convolution neural network operation,compares the gray value of each column,and matches the gray value sequence of the transformation column and the next *** this algorithm,when a boundary point is manually specified,we can accurately segment the boundary between retinal *** experimental results obtained from a 54-subjects database of both normal healthy eyes and affected eyes demonstrate the superior performances of our approach.

关键词： OCT retinal segmentation deep learning 1D convolution

来源：评论

学校读者我要写书评

暂无评论

SMEF: An Entropy-Based Security Framework for Cloud-Oriented Service Mashup

SMEF: An Entropy-Based Security Framework for Cloud-Oriented...

引用

IEEE International Conference on Trust, Security and Privacy in computing and Communications (TrustCom)

作者： Ruixuan Li Li Nie Xiaopu Ma Meng Dong Wei Wang Intelligent and Distributed Computing Laboratory School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

Cloud-oriented service mashup can aggregate many services to provide personalized services for end-users on demand. However, how to securely aggregate mashup services becomes a bottleneck of hampering the development of cloud computing. In this paper, we present a secure cloud service mashup framework called SMEF to address this problem. In SMEF, we employ security entropy to measure the unascertained security degree of service mashup. The nonfunctional criteria of SMEF are aggregated as a single criterion by defining a utility function. Then the relatively optimal mashup services are selected to meet the user requirements. Finally, we have implemented a simulation of SMEF and conducted extensive experiments using simulations of different sizes of services and security factors. Experimental results show the feasibility and efficiency of the SMEF service mashup framework.

关键词： Security Mashups Entropy Cloud computing Quality of service Joints Uncertainty

来源：评论

学校读者我要写书评

暂无评论

ASRNet: Adversarial Segmentation and Registration Networks for Multispectral Fundus Images

引用

Computer Systems Science & Engineering 2021年第3期36卷 537-549页

作者： Yanyun Jiang Yuanjie Zheng Xiaodan Sui Wanzhen Jiao Yunlong He Weikuan Jia School of Information Science and Engineering Shandong Normal UniversityJinan250358China Key Laboratory of Intelligent Computing&Information Security in Universities of Shandong Shandong Provincial Key Laboratory for Novel Distributed Computer Software TechnologyInstitute of Biomedical SciencesShandong Normal UniversityJinan250358China Shandong Provincial Hospital Affiliated to Shandong University Jinan250021China INSA Lyon University of LyonCNRSInsermVilleurbanne69621CedexFrance

Multispectral imaging (MSI) technique is often used to capture imagesof the fundus by illuminating it with different wavelengths of light. However,these images are taken at different points in time such that eyeball movementscan cause misalignment between consecutive images. The multispectral imagesequence reveals important information in the form of retinal and choroidal bloodvessel maps, which can help ophthalmologists to analyze the morphology of theseblood vessels in detail. This in turn can lead to a high diagnostic accuracy of several diseases. In this paper, we propose a novel semi-supervised end-to-end deeplearning framework called “Adversarial Segmentation and Registration Nets”(ASRNet) for the simultaneous estimation of the blood vessel segmentation andthe registration of multispectral images via an adversarial learning process. ASRNet consists of two subnetworks: (i) A segmentation module S that fulfills theblood vessel segmentation task, and (ii) A registration module R that estimatesthe spatial correspondence of an image pair. Based on the segmention-drivenregistration network, we train the segmentation network using a semi-supervisedadversarial learning strategy. Our experimental results show that the proposedASRNet can achieve state-of-the-art accuracy in segmentation and registrationtasks performed with real MSI datasets.

关键词： Deep learning deformable image registration image segmentation multispectral imaging(MSI)

来源：评论

学校读者我要写书评

暂无评论

Fast Snippet Generation Based on CPU-GPU Hybrid System

Fast Snippet Generation Based on CPU-GPU Hybrid System

引用

International Conference on Parallel and distributed Systems (ICPADS)

作者： Ding Liu Ruixuan Li Xiwu Gu Kunmei Wen Heng He Guoqiang Gao Intelligent and Distributed Computing Laboratory School of Computer Science and Technology Huazhong University of Science and Technology Wuhan Hubei China

As an important part of searching result presentation, query-biased document snippet generation has become a popular method of search engines that makes the result list more informative to users. Generating a single snippet is a lightweight task. However, it will be a heavy workload to generate multiple snippets of multiple documents as the search engines need to process large amount of queries per second, and each result list usually contains several snippets. To deal with this heavy workload, we propose a new high-performance snippet generation approach based on CPU-GPU hybrid system. Our main contribution of this paper is to present a parallel processing stream for large-scale snippet generation tasks using GPU. We adopt a sliding document segmentation method in our approach which costs more computing resources but can avoid the common defect that the high relevant fragment may be cut off. The experimental results show that our approach gains a speedup of nearly 6 times in average process time compared with the baseline approach-Highlighter.

关键词： Graphics processing unit Search engines Time factors Throughput Vectors Sorting Parallel processing

来源：评论

学校读者我要写书评

暂无评论

Detecting Human in Still Images by Learning Multi-Scale Mid-Level Features

Detecting Human in Still Images by Learning Multi-Scale Mid-...

引用

International Conference on Innovative computing, Information and Control (ICICIC)

作者： Tianjiang Wang Liyu Gong Fang Liu Intelligent and Distributed Computing Laboratory School of Computer Science and Technology Huazhong University of Science and Technology Wuhan Hubei China

Detecting human in still images is one of the most challenging object detection problems. In this paper we apply the scale theory to human detection. By integrating Gaussian Pyramids multi-scale object representation approach we present a Learned Multi-scale Mid-level Feature (LMMF) based human detection algorithm. Firstly multiscale low-level features are extracted by Gaussian Pyramid decomposition and gradient computation. Then LMMFs are learned from multi-scale low-level features using AdaBoost algorithm. The final human/non-human decision is made by classification on the LMMFs. Using LMMF descriptors, our method attempts to harvest more information than using uni-scale feature descriptors. Experiments on INRIA person dataset demonstrate that our method outperforms the previous state of the art detector.

关键词： Shape Detectors Feature extraction Classification algorithms Training Conferences Computer vision

来源：评论

学校读者我要写书评

暂无评论

A Lie group based spatiogram similarity measure

A Lie group based spatiogram similarity measure

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Liyu Gong Tianjiang Wang Fang Liu Gang Chen Intelligent and Distributed Computing Laboratory School of Computer Science and Technology Huazhong University of Science and Technology HUST Wuhan Hubei China

Spatiograms were generalization of histograms, which can harvest spatial information of images. The similarity measure is important when applying spatiograms to various computer vision problems such as tracking and image retrieval. The original proposed measures use Mahalanobis distance of coordinate mean to measure spatial information in spatiograms. However, spatial information which is described by spatiograms does not lie on vector space. Measures for vector space such as Mahalanobis distance are not effective measures for them. In this paper, We model spatial information as Gaussian approximation of coordinate distributions. Then we parameterize them as a Lie group. Based on Lie group theory, we analyze function space structure of Gaussian pdfs (probability density function) and propose an effective spatiogram similarity measure. We test our measure in object tracking scenarios. Experiments show better tracking results compared with previously proposed measures.

关键词： Level measurement Coordinate measuring machines Histograms Pixel Extraterrestrial measurements Space technology Image retrieval Gaussian approximation Probability density function Testing

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：