检索结果-内蒙古大学图书馆

2011 8th International Conference on Fuzzy systems and Knowledge Discovery, FSKD 2011, Jointly with the 2011 7th International Conference on Natural Computation, ICNC'11

作者： Alham, Nasullah Khalid Li, Maozhen Liu, Yang Hammoud, Suhel Ponraj, Mahesh School of Engineering and Design Brunel University Uxbridge Middlesex UB8 3PH United Kingdom Key Laboratory of Embedded Systems and Service Computing Ministry of Education Tongji University China

ISBN: (纸本)9781612841816

Machine learning techniques have facilitated image retrieval by automatically classifying and annotating images with keywords. Among them Support Vector Machines (SVMs) are used extensively due to their generalization properties. However, SVM training is notably a computationally intensive process especially when the training dataset is large. This paper presents MRSVM, a distributed SVM algorithm for large scale image annotation which partitions the training data set into smaller subsets and train SVM in parallel using a cluster of computing nodes. MRSVM is evaluated in an experimental environment showing that the distributed SVM algorithm reduces the training time significantly while maintaining a high level of accuracy in classifications. © 2011 IEEE.

关键词： MapReduce

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

Load balancing in MapReduce environments for data intensive applications

Load balancing in MapReduce environments for data intensive ...

引用

2011 8th International Conference on Fuzzy systems and Knowledge Discovery, FSKD 2011, Jointly with the 2011 7th International Conference on Natural Computation, ICNC'11

作者： Liu, Yang Li, Maozhen Alham, Nasullah Khalid Hammoud, Suhel Ponraj, Mahesh School of Engineering and Design Brunel University Uxbridge Middlesex UB8 3PH United Kingdom Key Laboratory of Embedded Systems and Service Computing Ministry of Education Tongji University China

ISBN: (纸本)9781612841816

The distributed computations are widely used in the modern world for processing large scale jobs. Hadoop framework which is based on Google MapReduce model becomes popular due to its great processing power and ease to use. However, due to lack of load management, especially in a heterogeneous computing environment, the performance of Hadoop framework may be deteriorated. Therefore this paper presents a load balancing algorithm which aims to balance the load among heterogeneous nodes. And also, the Hadoop simulator HSim is involved to evaluate the performance of the load balancing algorithm. The results indicate that the performance of the cluster has been significantly enhanced. © 2011 IEEE.

关键词： MapReduce

来源：评论

学校读者我要写书评

暂无评论

Ontology based file retrieval framework for resource limited mobile devices

Ontology based file retrieval framework for resource limited...

引用

2011 8th International Conference on Fuzzy systems and Knowledge Discovery, FSKD 2011, Jointly with the 2011 7th International Conference on Natural Computation, ICNC'11

作者： Jan, Sadaqat Li, Maozhen Al-Sultany, Ghaidaa Al-Raweshidy, Hamed School of Engineering and Design Brunel University Uxbridge Middlesex UB8 3PH United Kingdom Key Laboratory of Embedded Systems and Service Computing Ministry of Education Tongji University China

ISBN: (纸本)9781612841816

Recent advances in mobile technologies have emerged new challenges for researchers. File management and retrieval on resource-limited devices has become a challenging problem as these devices are now equipped with larger storage capacities. This paper presents an overview about the possibilities of implementing Semantic Web Technologies in order to facilitate the file retrieval on resource-limited devices. We have proposed a semantic based file retrieval framework which utilizes a generic ontology in file search process. The search module is implemented in Java ME platforms as a case study. Performance of the proposed search module is evaluated through experimental tests along with probabilistic evaluations. The implemented module not only automates file retrieval process but also shows significant improvement in file retrieval efficiency by utilizing the knowledge of employed ontology in the search module. © 2011 IEEE.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Facial Action Video Capture Interactive mode Designed For embedded Device

Facial Action Video Capture Interactive mode Designed For Em...

引用

第三十四届中国控制会议

作者： Zixuan Gan Wenhua Shi Chen Ye Tongji University The Key Laboratory of Embedded System and Services Computing Ministry of Education Tongji University

ISBN: (纸本)9781467374439

This study was designed to develop solutions for facial action human computer interaction on embedded devices. This paper presents a new facial detection algorithm using dimension reduction and regionalization computing. Then, a dynamic action judgement algorithm based on simplified Facial Expression Coding system is proposed to describe human facial action. This paper also provide the facial action capture system ***, an accuracy report is presented to validate the usefulness of system.

关键词： Facial Detection,Expression Recognition,Facial Action Recognition

来源：评论

学校读者我要写书评

暂无评论

An optimized Apriori algorithm based on sparse matrix for intrusion detection

引用

Open Cybernetics and systemics Journal 2014年第1期8卷 8-11页

作者： Zeng, Xiaohui Lv, Jingxiang Li, Jingzhong Luo, Wenlang Dept. of Computer Science and Technology Jinggangshan University Ji’an China The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China

The original Apriori algorithm is widely used in the intrusion detection field, but it may consume incredible computing resources in the process of handling network packets. We propose our optimized-Apriori algorithm which can greatly improves the algorithm efficiency by means of reducing the data storage space and the number of frequent item sets. We take full advantage of the characteristics of sparse matrix to save storage space and shorten the running time. The experimental results show that our optimized-Apriori algorithm can make a larger progress in saving the storage space of network data to be processed, even shortening nearly half of the data mining time in the process of intrusion detection. © Zeng et al.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Extracting all minimal siphons from maximal unmarked siphons in manufacturing-oriented Petri nets

Extracting all minimal siphons from maximal unmarked siphons...

引用

2011 7th IEEE International Conference on Automation Science and Engineering, CASE 2011

作者： Wang, ShouGuang Zhou, MengChu Wang, ChengYing College of Information and Electronic Engineering Zhejiang Gongshang University Hangzhou 310018 China Department of Electrical and Computer Engineering New Jersey Institute of Technology Newark NJ 07102-1982 United States MoE Key Laboratory of Embedded System and Service Computing Tongji University Shanghai 200092 China

ISBN: (纸本)9781457717307

Deadlock control is an important research issue in automated manufacturing systems that have a high degree of resource sharing and concurrency. Since minimal siphons are closely tied with deadlocks in Petri net models, their efficient extraction is fundamentally important. The existing methods can rapidly extract one minimal siphon given a maximal unmarked siphon that is obtained by using a mixed integer programming approach. This paper for the first time presents an extraction algorithm that can efficiently extract all minimal ones. The idea is based on the generation and use of a subnet tree structure given the places in a maximal unmarked siphon. Several Petri net models of automated manufacturing systems are used to illustrate the proposed concepts and methods. © 2011 IEEE.

关键词： Petri nets

来源：评论

学校读者我要写书评

暂无评论

Intrusion detection using mobile agent in ad-hoc networks

Intrusion detection using mobile agent in ad-hoc networks

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Yan Xia Ren-Fa Li Ken-Li Li Key Laboratory of Embedded System and Computing College of Computer and Communication Hunan University Changsha China

ISBN: (纸本)0780384032

Security has become an important issue for mobile ad hoc networks especially for the more security-sensitive applications used in military and critical networks. As a positive protection, intrusion detection system has been successfully applied in wired networks. However, these correlative researches are not fit for mobile ad hoc networks. This paper puts forward a novel architecture based on mobile agent platform for superior intrusion detection in mobile ad hoc networks. Furthermore, an IDS agent selection algorithm and its security communication mechanism are proposed.

关键词： Intrusion detection Mobile agents Intelligent networks Ad hoc networks Mobile ad hoc networks Mobile communication Computer networks embedded computing Cryptography Routing

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

Bridge the Gap Between Network-Based Inference Method and Global Ranking Method in Personal Recommendation

Bridge the Gap Between Network-Based Inference Method and Gl...

引用

IEEE Conference on Industrial Electronics and Applications

作者： Xiwei Liu Department of Computer Science and Technology Tongji University China The Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai 200092 China

In this paper, we study the relationship between the network-based inference method and global ranking method in personal recommendation. By some theoretical analysis, we prove that the recommendation result under the... 详细信息

ISBN: (纸本)9781467386456

关键词： Eigenvalues and eigenfunctions Heating Bridges Inference algorithms Prediction algorithms Conferences Industrial electronics

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：