检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Zhang, Yuebing Miao, Duoqian Wang, Jiaqi Department of Computer Science and Technology Tongji University Shanghai China Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai China

Cross-domain sentiment classification (CDSC) is an importance task in domain adaptation and sentiment classification. Due to the domain discrepancy, a sentiment classifier trained on source domain data may not works well on target domain data. In recent years, many researchers have used deep neural network models for cross-domain sentiment classification task, many of which use Gradient Reversal Layer (GRL) to design an adversarial network structure to train a domain-shared sentiment classifier. Different from those methods, we proposed Hierarchical Attention Generative Adversarial Networks (HAGAN) which alternately trains a generator and a discriminator in order to produce a document representation which is sentimentdistinguishable but domain-indistinguishable. Besides, the HAGAN model applies Bidirectional Gated Recurrent Unit (Bi-GRU) to encode the contextual information of a word and a sentence into the document representation. In addition, the HAGAN model use hierarchical attention mechanism to optimize the document representation and automatically capture the pivots and non-pivots. The experiments on Amazon review dataset show the effectiveness of HAGAN. Copyright © 2019, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Consensus in Second-Order Discrete-Time MAS With Distinct and Multiple Coupling Matrices

Consensus in Second-Order Discrete-Time MAS With Distinct an...

引用

International Conference on systems and Informatics (ICSAI)

作者： Chenggong Sun Xiwei Liu Department of Computer Science and Technology Tongji University Shanghai China Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai China

ISBN: (数字)9798331510138

ISBN: (纸本)9798331510145

In this paper, we explore and establish several necessary and sufficient conditions that are instrumental in achieving consensus within second-order discrete-time multi-agent systems (SDMAS). Different with previous research, this study addresses the more intricate scenario where the velocity coupling matrix is distinct from the position coupling matrix. We introduce a novel eigenvector condition tailored to this challenge. Furthermore, in response to the burgeoning interest in multiweighted networks, this study is extended to SDMAS with multiple weights. We employ a technique, that rearranges the order of variables, to effectively simplify the analysis of multiweighted networks by transforming them into single-weighted equivalents. The efficacy of our method is substantiated through three numerical examples, which illustrate the practical value in elucidating consensus dynamics within SDMAS featuring diverse coupling matrices.

关键词： Couplings Sufficient conditions Instruments Numerical simulation Trajectory Numerical models Multiaccess communication Informatics Pragmatics Multi-agent systems

来源：评论

学校读者我要写书评

暂无评论

Real-time action recognition with enhanced motion vector CNNs

Real-time action recognition with enhanced motion vector CNN...

引用

2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016

作者： Zhang, Bowen Wang, Limin Wang, Zhe Qiao, Yu Wang, Hanli Shenzhen Key Lab of Comp. Vis. and Pat. Rec. Shenzhen Institutes of Advanced Technology CAS China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China Computer Vision Lab ETH Zurich Switzerland

ISBN: (纸本)9781467388511

The deep two-stream architecture [23] exhibited excellent performance on video based action recognition. The most computationally expensive step in this approach comes from the calculation of optical flow which prevents it to be real-time. This paper accelerates this architecture by replacing optical flow with motion vector which can be obtained directly from compressed videos without extra calculation. However, motion vector lacks fine structures, and contains noisy and inaccurate motion patterns, leading to the evident degradation of recognition performance. Our key insight for relieving this problem is that optical flow and motion vector are inherent correlated. Transferring the knowledge learned with optical flow CNN to motion vector CNN can significantly boost the performance of the latter. Specifically, we introduce three strategies for this, initialization transfer, supervision transfer and their combination. Experimental results show that our method achieves comparable recognition performance to the state-of-the-art, while our method can process 390.7 frames per second, which is 27 times faster than the original two-stream method.

关键词： Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Heuristic Elastic Scaling for Kubernetes Heterogeneous Microservices 21

Heuristic Elastic Scaling for Kubernetes Heterogeneous Micro...

引用

21st International Conference on Networking, Sensing and Control, ICNSC 2024

作者： Wang, Song He, Sheng Ning, Yishuang Gao, Xiang Ding, Zhijun The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai201804 China The Department of Computer Science and Technology Tongji University Shanghai201804 China Kingdee Research Kingdee International Software Group Co. Ltd Shenzhen518057 China Intelligent Computing Facility Innovation Center ZhejiangLab Hangzhou30012 China

ISBN: (纸本)9798350365221

Kubernetes has become the basic platform for building cloud native applications. However, existing horizontal scaling methods based on Kubernetes have problems with resource redundancy. Furthermore, the combined horizontal and vertical scaling based on Kubernetes takes a long time. Regarding the issue above, first, we describe the execution processes of three scaling techniques and compare them in different dimensions;second, we construct a formal elastic scaling model for expansion scenarios, with the goal of minimizing the total cost;and third, we introduce a heuristic expansion algorithm after balancing resource redundancy and execution time as the heuristic information. The experiment results show that the elastic scaling algorithm proposed in this paper achieves better performance than other algorithms. © 2024 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

A comparative study of redundant feature detection based feature selection methods

A comparative study of redundant feature detection based fea...

引用

International Conference on Computer, Information and Telecommunication systems (CITS)

作者： Xue-Qiang Zeng Qian-Sheng Chen Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China Computer Center Nanchang University Nanchang China

As a high dimensional problem, analysis of largescale data sets is a challenging task, where many weakly relevant or redundant features hurt generalization performance of classification models. In order to solve this problem, many effective feature selection methods have proposed to eliminate redundant features in recent years. However, the comparative performances of these redundant feature detection based methods have not been reported yet, which makes the choice of feature selection method relatively difficult for many real applications. The paper presents a novel comparative study of redundant feature detection based feature selection methods. Experiments on several benchmark data sets demonstrate the comparative performances of some state-of-the-arts methods. Based on the extensive empirical results, the minimum Redundancy-Maximum Relevance (mRMR) method has been found to be the best one among all compared feature selection models.

关键词： Breast Colon Lungs Redundancy

来源：评论

学校读者我要写书评

暂无评论

Genetic Fuzzy + PI Path Tracking Control of a Nonholonomic Mobile Robot*

引用

Chinese Journal of Electronics 2023年第1期20卷 31-34页

作者： Zhengcai Cao Yingtao Zhao Qidi Wu College of Information Science and Technology Beijing University of Chemical Technology Beijing China The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China

A mobile robot is one of the well-known nonholonomic systems. The genetic fuzzy + PI path tracking control applied to a mobile robot is presented. The proposed controller composes of two fuzzy + PI controllers which are employed to control the angular velocity together, and one fuzzy + PI controller that is utilized to adjust the speed of mobile robot solely. Moreover, the fuzzy controller is designed to track reference path in approaching phase and PI controller is operated to diminish the tracking error in stable phase. In order to obtain better tracking performance, Genetic algorithm (GA) is used to optimize controller parameters. Finally, computer simulation results are given to illustrate the effectiveness of the proposed control scheme.

关键词： PI control Computer simulation Genetics Angular velocity Mobile robots Tuning Optimization

来源：评论

学校读者我要写书评

暂无评论

A method to calculate recommendation trust of web services

Journal of Software Engineering

引用

Journal of Software Engineering 2014年第2期8卷 108-115页

作者： Liu, Wei Du, Yu-Yue Yan, Chun Sha, Jing College of Information Science and Engineering Shandong University of Science and Technology Qingdao China The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China

Web services are widely accepted and used in the e-commerce. Trust plays an important role in selecting one Web service for application among many services satisfying the demand of requesters and trust for Web services is a hot topic in research fields. This study proposes a method to calculate recommendation trust of Web services and the weight of every recommender is confirmed by norm grey correlation analysis method. The detailed process of the given method is revealed by a specific instance. The method avoids the vicious recommendation and improves the reliability of selected services. © 2014 Academic Journals Inc.

关键词： Web services

来源：评论

学校读者我要写书评

暂无评论

Construction algorithms for index model based on Web page classification

引用

Journal of Computational Information systems 2014年第2期10卷 655-664页

作者： Zhang, Yangjie Yan, Chungang Wang, Pengwei Sun, Haichun Department of Computer Science and Technology Tongji University Shanghai 201804 China The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai 201804 China

Web pages on the Internet are massive, diverse, heterogeneous and redundant. How to organize and manage them effectively is an urgent problem. In this paper, we propose a method to index web pages and build an index model based on web page classification and hyperlink analysis. First, an initialization algorithm is given to construct an index model for an initial set of web pages. Then, considering the dynamics of web pages on the Internet, we propose an incremental updating algorithm which can update an index model incrementally. Through theoretical analysis, the complexity of proposed algorithms shows linear relationships with the scale of web pages and their growth. The experimental results show that initialization algorithm can construct an index model for a fixed number of web pages relatively fast, while the incremental updating algorithm can satisfy the update speed of web pages on the Internet. Thus, the proposed algorithms are feasible and effective. The constructed index model can provide supports for diversified information service systems to enable them to make better use of web resources and provide more valuable services to users. Copyright © 2014 Binary Information Press.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

A Location Privacy Preserving Scheme Based on Repartitioning Anonymous Region in Mobile Social Network

引用

Procedia Computer Science 2018年 129卷 368-371页

作者： Lina Ni Yanfeng Yuan Xiao Wang Mengmeng Zhang Jinquan Zhang College of Computer Science and Engineering Shandong University of Science and Technology Qingdao China The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China

Applying the proliferated location-based services (LBS) to social networks has spawned mobile social network (MSN) services that it allows users to discover potential friends around them. In this paper, we focus on the problem of location privacy preserving in MSN. Particularly, we propose a location privacy preserving (RPAR) scheme via to repartition anonymous region where the central anonymous location minimizes the traffic between the anonymous server and the LBS server while protecting the privacy of the user location.

关键词： Privacy preserving mobile social network location-based service location privacy anonymous region repartition

来源：评论

学校读者我要写书评

暂无评论

Capacity and delay in mobile cognitive networks with random way-point mobility model

引用

AEU - International Journal of Electronics and Communications 2011年第4期65卷 288-295页

作者： Xingzhen Bai Shu Li Changjun Jiang Juan Xu Cheng Wang Lina Han The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai 200092 China College of Information & Electrical Engineering Shandong University of Science & Technology Qingdao 266510China

We study the throughput and delay scaling laws of the mobile cognitive network. There are n primary users and m secondary users in the primary network and the secondary network, respectively. They are distributed uniformly and independently on the surface of a unit torus, moving according to the random way-point mobility model (RWMM). The primary users have priority to access the spectrum, and do not alter their protocol in the presence of the secondary network. The secondary users opportunistically use the licensed spectrum when it remains unused. Under the improved 2-hop relay policy, we derive the constant throughput of Θ ( 1 ) per primary source–destination (S–D) pair when the radius of the preservation region r p = Θ ( 1 / m ) . The expected delay scales as Θ ( n / v ( n ) ) , where v ( n ) is the average speed of the primary nodes. Moreover, if the secondary network is denser than the primary network, i.e., m = n γ with γ > 1 , the constant throughput of Θ ( 1 ) per secondary S–D pair and the expected delay of Θ ( m / v ( m ) ) can be derived surprisingly when the radius of the avoidance region r s = Θ ( 1 / n ) and r p = Θ ( 1 / m ) , where v ( m ) is the average speed of the secondary nodes.

关键词： Throughput Delay Scaling law Cognitive networks Mobility

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：