检索结果-内蒙古大学图书馆

Multi-Label Learning Based on Transfer Learning and Label Correlation

Computers, Materials & Continua 2019年第7期61卷 155-169页

作者： Kehua Yang Chaowei She Wei Zhang Jiqing Yao Shaosong Long College of Computer Science and Electronic Engineering and Key Laboratory for Embedded and Network Computing of Hunan Province Hunan UniversityChangsha410082China Oath Verizon Company ManhattanNew York10007USA

In recent years,multi-label learning has received a lot of ***,most of the existing methods only consider global label correlation or local label *** fact,on the one hand,both global and local label correlations can appear in real-world situation at same *** the other hand,we should not be limited to pairwise labels while ignoring the high-order label *** this paper,we propose a novel and effective method called GLLCBN for multi-label ***,we obtain the global label correlation by exploiting label semantic ***,we analyze the pairwise labels in the label space of the data set to acquire the local ***,we build the original version of the label dependency model by global and local label *** that,we use graph theory,probability theory and Bayesian networks to eliminate redundant dependency structure in the initial version model,so as to get the optimal label dependent ***,we obtain the feature extraction model by adjusting the Inception V3 model of convolution neural network and combine it with the GLLCBN model to achieve the multi-label *** experimental results show that our proposed model has better performance than other multi-label learning methods in performance evaluating.

关键词： Bayesian networks multi-label learning global and local label correlations transfer learning

来源：评论

学校读者我要写书评

暂无评论

keyphrase Generation Based on Self-Attention Mechanism

引用

Computers, Materials & Continua 2019年第8期61卷 569-581页

作者： Kehua Yang Yaodong Wang Wei Zhang Jiqing Yao Yuquan Le College of Computer Science and Electronic Engineering and Key Laboratory for Embedded and Network Computing of Hunan Province Hunan UniversityChangsha410082China Oath Verizon Company ManhattanNew York10007USA

keyphrase greatly provides summarized and valuable *** information can help us not only understand text semantics,but also organize and retrieve text content *** task of automatically generating it has received considerable attention in recent *** the previous studies,we can see many workable solutions for obtaining *** method is to divide the content to be summarized into multiple blocks of text,then we rank and select the most important *** disadvantage of this method is that it cannot identify keyphrase that does not include in the text,let alone get the real semantic meaning hidden in the *** approach uses recurrent neural networks to generate keyphrases from the semantic aspects of the text,but the inherently sequential nature precludes parallelization within training examples,and distances have limitations on context *** works have demonstrated the benefits of the self-attention mechanism,which can learn global text dependency features and can be *** by the above observation,we propose a keyphrase generation model,which is based entirely on the self-attention *** is an encoder-decoder model that can make up the above disadvantage *** addition,we also consider the semantic similarity between keyphrases,and add semantic similarity processing module into the *** proposed model,which is demonstrated by empirical analysis on five datasets,can achieve competitive performance compared to baseline methods.

关键词： keyphrase generation self-attention mechanism encoder-decoder framework

来源：评论

学校读者我要写书评

暂无评论

Brief Industry Paper: Response Time Evaluation of Cross-Domain Communication in CAN-FD and TSN 44

Brief Industry Paper: Response Time Evaluation of Cross-Doma...

引用

44th IEEE Real-Time Systems Symposium, RTSS 2023

作者： Ma, Wenhong Huang, Xiaoyi Wei, Dongsheng Li, Renfa Zhang, Yunfei Xie, Guoqi Chang, Wanli Hunan University Key Laboratory for Embedded and Network Computing of Hunan Province China Tencent Future Network Lab Tencent Corporation China

ISBN: (纸本)9798350328578

With the advancement of intelligence and networked automotive, the domain-centralized architecture, which employs time sensitive networking (TSN) as the inter-domain backbone network and control area network with flexible data rate (CAN-FD) as the intra-domain network, has garnered significant attention. However, cross-domain end-to-end communication involves multiple components, and significant disparities between TSN and CAN-FD render response time analysis within domain-centralized architecture for mixed-critical traffic exceptionally complex. In this paper, we develop a cross-domain with TSN and CAN-FD end-to-end response time evaluation tool, which analyzes the response time of mixed-critical traffic under different design options segment by segment. We specifically analyze the waiting times of different messages in the domain control unit when faced with the design options of one-to-one and multi-to-one conversion of CAN-FD and TSN frames. The proposed evaluation tool can be easily extended to different design options to support more application scenarios. Theoretical computational analysis and real hardware measurements show the effectiveness of our tool. © 2023 IEEE.

关键词： network architecture

来源：评论

学校读者我要写书评

暂无评论

A perspective on Petri Net learning

引用

Frontiers of Computer Science 2023年第6期17卷 1-3页

作者： Hongda QI Changjun JIANG Key Laboratory of Embedded System and Service Computing(Ministry of Education) Tongji UniversityShanghai 201804China National(Province-Ministry Joint)Collaborative Innovation Center for Financial Network Security Tongji UniversityShanghai 201804China

Petri Nets(PNs)are used for modeling and analyzing discreteevent systems,such as communication protocols,trafficsystems,human-computer interaction,and fault ***’state space explosion problem means that the state spaceof PNs grows exponentially with PNs’*** thefundamental reachability problem is still an NP-Hard problemin *** has been proved that the equivalence problem forthe reachability sets of arbitrary PNs is undecidable except forsome subclass of PNs[1].That is,the reachability problem ofarbitrary PNs cannot be solved ***,there is noefficient and accurate algorithm to solve the problem.10172In recent years,with the emergence of big data and thedevelopment of computing hardware,a series ofbreakthroughs have been achieved in machine learning,suchas AlphaGo,AlphaFold,and ChatGPT[2−4].As a data-drivenapproach,machine learning can learn potential mappingrelationships between inputs and outputs from large-scaledata.

关键词： breakthrough hardware learning

来源：评论

学校读者我要写书评

暂无评论

A novel combination method for conflicting evidence in open frame of discernment 17

A novel combination method for conflicting evidence in open ...

引用

2017 International Conference on Data Mining, Communications and Information Technology, DMCIT 2017

作者： Yang, Kehua Liu, Youfang Key Laboratory for Embedded and Network Computing of Hunan Province College of Computer Science and Electronics Hunan University Changsha China

ISBN: (纸本)9781450352185

Dempster-Shafer theory is a useful method in data fusion. To avoid counter-intuitive result of classical Dempster-Shafer's combination rule dealing with highly conflict evidences, many improved combination methods have been proposed through modifying the classical Dempster-Shafer's rule or original evidence by using a certain measure of the degree of conflict or uncertain data. However, usually the frame of discernment is incomplete, the current methods have limitation in handling this *** order to solve this problem, an improved combination method for conflicting evidence in open frame of discernment is proposed. In this paper, according to information theory the information entropy of each evidence is calculated and assigned to the unknown proposition which is added into the frame of discernment. Then reliability degree of evidences obtained by the Jousselme distance is used to revise source evidences. Finally, Dempster-Shafer's rule is applied to combine the mean of revised evidences several times. One numerical example is employed and in comparison with the existing alternatives, the proposed approach can effectively solve the conflicting problem and the incompleteness of frame. © 2017 Association for computing Machinery.

关键词： Information theory

来源：评论

学校读者我要写书评

暂无评论

Diverse Image Colorizaiton via Deep Color Prior and Triplet Latent Regularization

Diverse Image Colorizaiton via Deep Color Prior and Triplet ...

引用

2022 IEEE International Conference on Multimedia and Expo, ICME 2022

作者： Jiang, Bin Dai, Jiawu Zeng, Weiyuan Wang, Renjun College of Computer Science and Electronic Engineering Hunan University China Key Laboratory for Embedded and Network Computing of Hunan Province China

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

Automatic image colorization has made tremendous progress in recent years. However, previous methods rarely consider the inherent diversity of natural images, and existing diverse colorization approaches still suffer from the following two limitations. i) The diversity of generated images is limited. ii) Some inevitable artifacts substantially degrade the quality of colorization results. To cope with such problems, we propose a novel diverse image colorization network based on vanilla GAN, which extracts the deep color priors through an initial colorization network first, and then utilizes these priors to modulate the diverse generation to achieve high-fidelity colorization outputs. In addition, a novel triplet latent regularization is proposed to constrain the correspondence between latent codes and generated images, which efficiently alleviates mode collapse and encourages more diverse colorization results. Extensive experiments on three benchmark datasets demonstrate the superiority of our method over existing diverse image colorization models. © 2022 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Energy optimization on dynamic multiple functions automotive cyber-physical systems 21

Energy optimization on dynamic multiple functions automotive...

引用

21st IEEE International Conference on High Performance computing and Communications, 17th IEEE International Conference on Smart City and 5th IEEE International Conference on Data Science and Systems, HPCC/SmartCity/DSS 2019

作者： Liu, Yan Xie, Guoqi Jin, Linlin Li, Renfa Key Laboratory for Embedded and Network Computing of Hunan Province College of Computer Science and Electronic Engineering Hunan University Changsha Hunan China

ISBN: (纸本)9781728120584

A new generation of automotive electronic systems is a typical cyber-physical systems (CPS) based on an integrated architecture, in which multiple functions can be executed on one electronic control unit (ECU) and one function can be assigned to different ECU. Heterogeneity and dynamics are essential characteristics of automotive CPS (ACPS). Considering heterogeneity and dynamics of ACPS, optimizing functional safety and energy consumption in system design is still a challenge. In this paper, we focus on the collaborative optimization of functional safety and energy consumption with global method in the context of prioritizing functional safety. Considering the requirements of functional safety, we propose a deadline driven processor merging for multiple dynamic functions (DPMMDF) algorithm to maximizes the number of functions that meet deadlines when a function arrives dynamically from the perspective of global optimization. Further, we use a global energy saving for multiple dynamic functions (GESMDF) algorithm, combined with the integrated architecture features, to optimize the energy consumption of ACPS by selecting multiple candidate executable ECUs for a task. Experimental results show that combination of the proposed two algorithms can effectively reduce deadline missed ratio (DMR), and minimize energy consumption compared with existing methods. © 2019 IEEE.

关键词： Global optimization

来源：评论

学校读者我要写书评

暂无评论

Optimizing Word Embedding for Fine-Grained Sentiment Analysis 1

引用

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

作者： Zhang, Wei Zhang, Yue Yang, Kehua Key Laboratory for Embedded and Network Computing of Hunan Province College of Computer Science and Electronic Engineering Hunan University Changsha410082 China

ISBN: (数字)9783030242657

ISBN: (纸本)9783030242640

Word embeddings have been extensively used for various Natural Language Processing tasks. However, word vectors trained based on corpus context information fail to distinguish words with the same context but different semantics, which may lead to a similar word vector with opposite semantic terms. This will affect some Natural Language Processing tasks, such as fine-grained sentiment analysis tasks. In this paper, a new word vectors optimization model is proposed. This model can be applied to any pre-trained word vectors. Within a certain range, it can make the opposite semantic words away from each other, and the same semantic words are close to each other. The experimental results show that our model can improve the traditional word embedding in the fine-grained emotional analysis task of Chinese Weibo, and the optimized word vector using our model outperforms the unoptimized word vector. © 2019, Springer Nature Switzerland AG.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Real-time depth estimation with an optimized encoder-decoder architecture on embedded devices 21

Real-time depth estimation with an optimized encoder-decoder...

引用

作者： Tu, Xiaohan Xu, Cheng Liu, Siping Xie, Guoqi Li, Renfa Key Laboratory for Embedded and Network Computing of Hunan Province China College of Computer Science and Electronic Engineering Hunan University Changsha410082 China

ISBN: (纸本)9781728120584

As a strategy to obtain dense depth maps from a single image, sparse depths, or the fusion of both (RGBd), depth estimation receives much attention. Usually relying on high-performance workstations, existing depth prediction methods, are not particularly suitable for embedded devices. Moreover, the accuracy of depth estimation needs to be improved. Towards real-time and reliable depth prediction on portable embedded platforms, we propose an encoder-decoder architecture (EDA). Specifically, these are the three contributions of this work. (1) We present a light-weight encoder, which takes three modalities of data as inputs, namely, RGB images, sparse depths, or RGBd. The encoder is efficient to extract features on portable devices. (2) A novel decoder is designed to obtain accurate and high-resolution depth maps. (3) We use the existing TVM to deploy, compile, and optimize EDA on embedded platforms, for further improvements in the computational speed and power of depth estimation. In real scenarios, the optimized EDA achieves remarkable results with low latency. Through extensive experimental evaluation on two public datasets, we show that the optimized EDA outperforms the state of the arts in accuracy and computational resources. To the best of our knowledge, this is the first paper that provides an efficient encoder, learnable decoder, and end-to-end optimized encoder-decoder architecture for precise depth prediction. © 2019 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

An Evidence Combination Method based on DBSCAN Clustering

引用

Computers, Materials & Continua 2018年第11期57卷 269-281页

作者： Kehua Yang Tian Tan Wei Zhang College of Computer Science and Electronic Engineering and Key Laboratory for Embedded and Network Computing of Hunan ProvinceHunan UniversityChangshaHunan410082China Department of Electrical and Computer Engineering Virginia Polytechnic Institute and State UniversityVirginiaBlacksburg24060USA

Dempster-Shafer(D-S)evidence theory is a key technology for integrating uncertain information from multiple ***,the combination rules can be paradoxical when the evidence seriously conflict with each *** the paper,we propose a novel combination algorithm based on unsupervised Density-Based Spatial Clustering of Applications with Noise(DBSCAN)density *** the proposed mechanism,firstly,the original evidence sets are preprocessed by DBSCAN density clustering,and a successfully focal element similarity criteria is used to mine the potential information between the evidence,and make a correct measure of the conflict ***,two different discount factors are adopted to revise the original evidence sets,based on the result of DBSCAN density ***,we conduct the information fusion for the revised evidence sets by D-S combination *** results show that the proposed method can effectively solve the synthesis problem of high-conflict evidence,with better accuracy,stability and convergence speed.

关键词： D-S evidence theory information fusion DBSCAN combination rules

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：