检索结果-内蒙古大学图书馆

Motiviting Others Drives Jamshidi [SMC Innovators]

IEEE Systems, Man, and Cybernetics Magazine 2015年第3期1卷 67-72页

作者： M.E. El-Hawary School of Computer Science and Engineering Southeast University China Ministry of Education Key Laboratory of Computer Network and Information Integration China

Presents an interview conducted with Dr. Jamshidi.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dust:Real-Time Code Offloading System for Wearable Computing

Dust:Real-Time Code Offloading System for Wearable Computing

引用

IEEE Global Communications Conference

作者： Di Huang Luning Yang Sanfeng Zhang Key Laboratory of Computer Network and Information Integration (Southeast University) Nanjing University

ISBN: (纸本)9781479959532

Runtime performance seriously bothers application developers and users for wearable devices such as Apple Watch and Google Glass. To ease such pains, one approach is to transplant the computation to the cloud, known as cloud offloading. This paradigm works well when the Internet is accessible. Another solution, known as device-to-device (D2D) offloading, is to utilize nearby devices for computation offloading. In this paper, propose the Dust, a D2D code offloading prototype for wearable computing. To our best knowledge, Dust is the first code offloading system for wearable computing with an implementation on Google Glass. Dust includes a programmer friendly framework based on Java annotation, a lightweight offloading service, and a runtime task scheduler to make offloading decisions. Extensive experiments demonstrate that Dust achieves real-time performance with speedup of 6.1X.

关键词： Wearable computers UNLOADING CLOUDS Clouds DIRT application developer Speeding

来源：评论

学校读者我要写书评

暂无评论

Multi-threshold image segmentation through an improved quantum-behaved particle swarm optimization algorithm 1st

Multi-threshold image segmentation through an improved quant...

引用

1st International Conference on Cloud Computing and Security, ICCCS 2015

作者： Jiali, Wang Hongshen, Liu Yue, Ruan School of Computer Science Anhui University of Technology Maanshan243005 China School of Computer Science and Engineering Southeast University Nanjing210096 China Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University Nanjing210096 China

ISBN: (纸本)9783319270500

Multi-threshold segmentation is a basic and widely used technique in image segmentation. The key step of accomplishing this task is to find the optimal multi-threshold value, which in essence can be reduced to multi-objective optimization problem. The quantum particle-behaved swarm algorithm (QPSO) is an effective method to resolve the problem of this class. However in practice, we found the original QPSO has imperfections, such as the excessive dropping of the diversity of the population and trapping in local optimum. In order to improve the ability of searching the global optimum and accelerate the speed of convergence, we proposed an improved quantum-behaved particle swarm algorithm (IQPSO). The experiments showed that IQPSO was superior to PSO and QPSO on the searching of multi-threshold value in image segmentation under the premise of ensuring the accuracy of solutions. © Springer International Publishing Switzerland 2015.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A novel search engine-based method for discovering command and control server 15th

A novel search engine-based method for discovering command a...

引用

15th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2015

作者： Guo, Xiaojun Cheng, Guang Pan, Wubin Dinhtu, Truong Liang, Yixin School of Computer Science and Engineering Southeast University Nanjing211189 China Key Laboratory of Computer Network and Information Integration Southeast University Nanjing211189 China School of Information Engineering Xizang Minzu University Xianyang712082 China XiZang Key Laboratory of Optical Information Processing and Visualization Technology Xizang Minzu University Xianyang712082 China

ISBN: (纸本)9783319271361

To solve the problem of getting command and control (C&C) server address covertly for malware of Botnet or advanced persistent threats, we propose a novel C&C-server address discovery scheme via search engine. This scheme is com-posed of five modules. The botmaster uses publish module to issue C&C-server IPs in diaries of several free blogs on Internet firstly. Then these diaries could be indexed by search engine (SE). When the infected terminal becomes a bot, it uses keyword production module to produce search keyword and submits some or all these keywords to SEs to obtain the search engine result pages (SERPs). For items in SERPs, the bot uses filtering algorithm to remove noise items and leave valid items whose abstract contain C&C-server IPs. Lastly the bot utilizes extraction and conversion module to extract these C&C-server IPs and translates them into binary format. The experimental results show that our proposed scheme is fully able to discover and obtain C&C-server IPs via various search engines. Furthermore, if we set proper threshold value for SE, it can extract C&C-server IPs accurately and efficiently. © Springer International Publishing Switzerland 2015.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

Leveraging Implicit Relative Labeling-Importance information for Effective Multi-label Learning

Leveraging Implicit Relative Labeling-Importance Information...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Yu-Kun Li Min-Ling Zhang Xin Geng Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education China

ISBN: (纸本)9781467395052

In multi-label learning, each training example is represented by a single instance while associated with multiple labels, and the task is to predict a set of relevant labels for the unseen instance. Existing approaches learn from multi-label data by assuming equal labeling-importance, i.e. all the associated labels are regarded to be relevant while their relative importance for the training example are not differentiated. Nonetheless, this assumption fails to reflect the fact that the importance degree of each associated label is generally different, though the importance information is not explicitly accessible from the training examples. In this paper, we show that effective multi-label learning can be achieved by leveraging the implicit relative labeling-importance (RLI) information. Specifically, RLI degrees are formalized as multinomial distribution over the label space, which are estimated by adapting an iterative label propagation procedure. After that, the multi-label prediction model is learned by fitting the estimated multinomial distribution as regularized with popular multi-label empirical loss. Comprehensive experiments clearly validate the usefulness of leveraging implicit RLI information to learn from multi-label data.

关键词： Yttrium Training Reliability Predictive models Symmetric matrices Semantics Estimation

来源：评论

学校读者我要写书评

暂无评论

Tensor object classification via multilinear discriminant analysis network

Tensor object classification via multilinear discriminant an...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Rui Zeng Jiasong Wu L. Senhadji Huazhong Shu LIST Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education Nanjing 210096 China

ISBN: (纸本)9781467369985

This paper proposes an multilinear discriminant analysis network (MLDANet) for the recognition of multidimensional objects, knows as tensor objects. The MLDANet is a variation of linear discriminant analysis network (LDANet) and principal component analysis network (PCANet), both of which are the recently proposed deep learning algorithms. The MLDANet consists of three parts: 1) The encoder learned by MLDA from tensor data. 2) Features maps obtained from decoder. 3) The use of binary hashing and histogram for feature pooling. A learning algorithm for MLDANet is described. Evaluations on UCF11 database indicate that the proposed MLDANet outperforms the PCANet, LDANet, MPCA+LDA, and MLDA in terms of classification for tensor objects.

关键词： Deep learning LDANet MLDANet PCANet tensor object classification

来源：评论

学校读者我要写书评

暂无评论

A novel community detection method based on discrete particle swarm optimization algorithms in complex networks

A novel community detection method based on discrete particl...

引用

Congress on Evolutionary Computation

作者： Cen Cao Qingjian Ni Yuqing Zhai School of Computer Science and Engineering Nanjing China Key Lab of Computer Network & Information Integration MOE P.R.China

ISBN: (纸本)9781479974931

The community structure is one of the most common and important attributes in complex networks. Community detection in complex networks has attracted much attention in recent years. As an effective evolutionary computation technique, particle swarm optimization (PSO) algorithm has become a candidate for many optimization applications. However, PSO algorithm was originally designed for continuous optimization. In this paper, an improved simple discrete particle swarm optimization (ISPSO) algorithm and a discrete particle swarm optimization with redefined operator (IDPSO-RO) algorithm are proposed in the discrete context of community detection problem. Furthermore, a community correcting strategy is used to optimize the results. The performance of the two algorithms is tested on three real networks with known community structures. The experiment results show that ISPSO and IDPSO-RO algorithms using community correcting strategy can detect community structures more efficiently without prior knowledge about the size of communities and the number of communities.

关键词： Particle swarm optimization Complex networks Sociology Statistics Algorithm design and analysis Optimization Image edge detection

来源：评论

学校读者我要写书评

暂无评论

Tensor object classification via multilinear discriminant analysis network 40

Tensor object classification via multilinear discriminant an...

引用

40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015

作者： Zeng, Rui Wu, Jiasong Senhadji, Lotfi Shu, Huazhong LIST Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing China INSERM U 1099 Rennes France Laboratoire Traitement du Signal et de l'Image Universit de Rennes 1 Rennes France France

ISBN: (纸本)9781467369978

关键词： Deep learning LDANet MLDANet PCANet tensor object classification

来源：评论

学校读者我要写书评

暂无评论

Carriers Selection for Content Dissemination in Social Opportunistic networks

Carriers Selection for Content Dissemination in Social Oppor...

引用

International Conference on Collaborative Computing: networking, Applications and Worksharing (CollaborateCom)

作者： Yongqiang Dong Wang Yang Taieb Znati Key Laboratory of Computer Network and Information Integration Southeast University Nanjing China Department of Computer Science School of Arts and Sciences Pittsburgh PA USA

Content dissemination in social opportunistic networks has attracted great interests in the field. Most of the researches in literature focused on the data forwarding and routing mechanisms in such network scenarios. There were few studies on the assignment of content originators. This paper is concerned about how to identify a small subset of users as content carriers through which the content can be disseminated more efficiently. The problem is modeled as a dominating set problem in bipartite graph, in which a minimum number of carriers are selected to cover all the venues with required probability, by using available location affinity information. The NP-complete property of the problem is pointed out, along with an exact exponential exhaustive algorithm. Then three polynomial heuristic algorithms are presented to solve the venue coverage problem. Among them, the adaptive metric-based algorithm chooses carriers based on dynamically calculated metric values. Several user-centric and expected contribution based metrics are discussed and examined. The submodular algorithm selects carriers greedily based on the estimation of marginal coverage gain from each user. The reduced-union algorithm asks each venue to select a candidate set separately based on its own individual affinity information. Then the candidate union set is reduced gradually by reasonable greedy method. Synthetized data and real trace experiment results show that the submodular algorithm can be applied in scenarios where coverage threshold is low and small number of carriers is required. In most cases we can rely on metric-based algorithm to solve the carriers selection problem. Among all the metrics, total affinity and proportional contribution perform more valuable than other metrics. Meanwhile, the adaptive operation in metric-based algorithm plays more important role than the metrics in seeking the most qualified carriers. When complete affinity information is not available, the reduced-union algo

关键词： Bipartite graph Algorithm design and analysis Routing Heuristic algorithms Delays network topology

来源：评论

学校读者我要写书评

暂无评论

A novel PSO for portfolio optimization based on heterogeneous multiple population strategy

A novel PSO for portfolio optimization based on heterogeneou...

引用

Congress on Evolutionary Computation

作者： Xushan Yin Qingjian Ni Yuqing Zhai College of Software Engineering Southeast University Nanjing China MOE Key Lab of Computer Network & Information Integration P.R.China

ISBN: (纸本)9781479974931

The problem of portfolio selection in the field of financial engineering has received more attention in recent years. This paper presents a novel heterogeneous multiple population particle swarm optimization algorithm (HMPPSO) for solving a generalized Markowitz mean-variance portfolio selection model. The proposed HMPPSO is based on heterogeneous multiple population strategy, in which the whole population is divided into several sub-populations and all the sub-populations evolve with different PSO variants. The communication between the sub-populations is executed at regular intervals to maintain the information exchange inside the entire population and coordinate exploration and exploitation according to certain migration rules. The generalized portfolio selection model is classified as a quadratic mixed-integer programming model for which no computational efficient algorithms have been proposed. We employ the proposed HMPPSO to find the solution for the model and compare the performance of HMPPSO with several classic PSO variants. The test data set is the weekly prices from March, 1992 to September, 1997 including the following indices: Hang Seng in Hong Kong, DAX 100 in Germany, FTSE 100 in UK, S&P 100 in USA and Nikkei 225 in Japan. The computational results demonstrate that HMPPSO is much effective and robust, especially for problems with high dimensions, thus provides an effective solution for the portfolio optimization problem.

关键词： Portfolios Sociology Statistics Optimization Computational modeling Standards Particle swarm optimization

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：