检索结果-内蒙古大学图书馆

Graph-cluster-mine: weighted closed key path mining in complex software executing network modules

Journal of Computational information Systems 2015年第1期11卷 285-295页

作者： Ren, Jiadong Li, Weina Han, Gaowei College of Information Science and Engineering Yanshan University Qinhuangdao China The Key Laboratory for Computer Virtual Technology and System Integration Qinhuangdao China

Previous key path mining algorithms have high computation complexity in the whole software executing network. But the network can be clustered into modules to find key paths in the module. If simplified strategy, weight and closed checking of paths are considered, interesting weighted closed key paths can be found more efficiently. Therefore, a novel algorithm Graph-Cluster-Mine is proposed. Firstly, weighted complex software executing network is constructed, definition of software executing network modules is given. Secondly, GN algorithm is improved to cluster the network into modules on limiting scale of a module. And DFS is adopted for each module to find paths. Path-Simplified-Bundle and Path-Simplified- Hierarchy strategies are devised to simplify paths. Thirdly, key-Path-Mine and Path-Closed-Checking are developed to mine weighted closed key paths. Experimental results indicate Graph-Cluster-Mine is more efficient in finding weighted closed key paths in complex software executing network. ©, 2014, Journal of Computational information Systems. All right reserved.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Research on Router Algorithm Based on Trust Primary Node in the Environment of P2P network

Research on Router Algorithm Based on Trust Primary Node in ...

引用

2015 International Conference on Informatics, Control and Automation(ICA 2015)

作者： Jing CHEN Yun WAN Department of Computer College of Information Science and EngineeringYanshan University Key Laboratory of Computer Virtual Technology and System Integration of Hebei Province

The distributed, heterogeneous and anonymous attribute of P2 P networks make the node information sharing facing security problems. In order to prevent malicious and false service of nodes, and improve the retrieval efficiency, the primary node selection algorithm based on trust mechanism is proposed in this paper. Firstly, the network topology based on virtual community is described, and the function of primary node is discussed. Secondly, the primary node is selected according to direct trust value and recommendation trust value of each node in the virtual community. Finally, resource retrieval algorithm is designed according to the selected trust primary node, and the algorithm is experimentally verified. In some certain extent, the results show that the method is able to reduce the fraud of primary node and improve the retrieval efficiency.

关键词： P2P network Virtual community Primary node Trust mechanism Router algorithm

来源：评论

学校读者我要写书评

暂无评论

Deep Label Distribution Learning for Apparent Age Estimation

Deep Label Distribution Learning for Apparent Age Estimation

引用

International Conference on computer Vision Workshops (ICCV Workshops)

作者： Xu Yang Bin-Bin Gao Chao Xing Zeng-Wei Huo Xiu-Shen Wei Ying Zhou Jianxin Wu Xin Geng School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Ministry of Education China National Key Laboratory for Novel Software Technology Nanjing University Nanjing China Southeast University Nanjing Jiangsu CN

In the age estimation competition organized by ChaLearn, apparent ages of images are provided. Uncertainty of each apparent age is induced because each image is labeled by multiple individuals. Such uncertainty makes this age estimation task different from common chronological age estimation tasks. In this paper, we propose a method using deep CNN (Convolutional Neural network) with distribution-based loss functions. Using distributions as the training tasks can exploit the uncertainty induced by manual labeling to learn a better model than using ages as the target. To the best of our knowledge, this is one of the first attempts to use the distribution as the target of deep learning. In our method, two kinds of deep CNN models are built with different architectures. After pre-training each deep CNN model with different datasets as one corresponding stream, the competition dataset is then used to fine-tune both deep CNN models. Moreover, we fuse the results of two streams as the final predicted ages. In the final testing dataset provided by competition, the age estimation performance of our method is 0.3057, which is significantly better than the human-level performance (0.34) provided by the competition organizers.

关键词： Face Estimation Streaming media Training Hidden Markov models Uncertainty Standards

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

Research on community detection in social network based on Pairwise Merging

引用

Journal of Computational information Systems 2015年第19期11卷 7079-7086页

作者： Chen, Jing Wan, Yun Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao China College of Information Science and Engineering Yanshan University Qinhuangdao China

Community detection has become an important challenge during the past decade. network is divided into some groups or communities that are densely connected to each other inside while less connected to the nodes outside. Community detection in social networks using hybrid merging of sub-communities is proposed. It is based on the idea of bottom to up. But the initial phase of algorithm resulted in many sub- communities and hybrid merging generated some weak communities. In order to resolve these problems, the algorithm CDPM (Community Detection based on Pairwise Merging of sub-communities) is proposed in this paper. The main idea of the algorithm starts with some small communities. Then, these small communities are extended by using similarity in order to decrease the number of sub-communities. Finally, these sub-communities are merged by pairwise merging which is mainly based on maximization modularity. Meanwhile, checking structure of every community is to avoid the appearance of weak community. The CDPM is proved on two real networks, and the results show that the performance of CDPM is close to real network and the quality of community detection is improved. © 2015 by Binary information Press.

关键词： Merging

来源：评论

学校读者我要写书评

暂无评论

Improving neighbourhood quality for CHUCKY: An empirical study

引用

Journal of Computational information Systems 2015年第16期11卷 5967-5977页

作者： Zhao, Fengda Yang, Ke Ren, Jiadong College of Information Science and Engineering Yanshan University Qinhuangdao China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao China

Vulnerability discovery is at the centre of attention in computer security. Most vulnerability detection methods need considerable human auditing, thus making vulnerability detection inefficient and unreliable. Similar neighbourhood-based missing check detection method solves this problem to some degree. However, semantic noises that degrade the quality of the neighbourhood list remain. To reduce these noises, we firstly define a q-gram-based name similarity to measure the correlation of function names or file names. The context similarity of function is then defined to measure the commonness of two functional working environment. Finally, two filters are proposed: one is the naive neighbourhood filter which filters irrelative functions by name similarity;the other is the improved integrate neighbourhood filter, which awards strong correlated functions by recognising remarkable name and context similarity. The filter-based methods are experimentally evaluated in five widely used open-source software and are compared with the original method. Result shows that the improved neighbourhood rank lists are more accurate than the original list. © 2015 by Binary information Press

关键词： Static analysis

来源：评论

学校读者我要写书评

暂无评论

Community detection algorithm in signed social networks based on statistics and merger

引用

Journal of information and Computational Science 2015年第15期12卷 5589-5599页

作者： Guo, Jingfeng Zhao, Yue Hu, Xinzhuan Liu, Yuanying College of Information Science and Engineering Yanshan University Qinhuangdao China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao China

Researches on community detection in signed social networks focus on the assignment of positive and negative edges. However, the community detection approaches that positive and negative edges are handled separately in two phases cannot make full use of negative edges, which seriously affects the accuracy of community detection. To solve the problem, a new algorithm called CDA SM (Community Detection Algorithm Based on Statistics and Merger) is proposed: merge into the two phases as an unified process;in the process of community detection, the node shall be added to the community in which the node has the maximum contribution as well as the minimum interference degree. The accuracy and time efficiency of CDA SM have been demonstrated through a set of experiments including both un-weighted common networks and un-weighted signed social networks. © 2015 by Binary information Press

关键词： Signal detection

来源：评论

学校读者我要写书评

暂无评论

Analysis on impact of node failure in software execution network

引用

Journal of Computational information Systems 2015年第6期11卷 2217-2225页

作者： He, Haitao Ren, Rong Zhang, Bing Ren, Jiadong College of Information Science and Engineering Yanshan University Qinhuangdao China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao China

One or few failure nodes will cause cascading failure in software network, which would bring about security issues. Thus, analyzing nodes becomes an indispensable aid in software security. In this paper, software execution process is abstracted as weighted complex network. Based on this, a cascading failure diffusion analyzing (CFDA) algorithm is put forward to evaluate the impact of node failure on software during its runtime dynamically. It explores nodes' failure spreading range and the number of infected nodes by malicious attacks on high in-strength nodes and strong failure propagation probability nodes in software execution networks respectively. Meanwhile, the propagation behavior of cascading failures in the software system is studied. The experiment results prove that strong failure propagation ability nodes under attack have greater devastating impact on software than others. Copyright © 2015 Binary information Press.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

引用

Journal of Computational information Systems 2015年第2期11卷 535-545页

作者： Ren, Jiadong Li, Weina Han, Gaowei College of Information Science and Engineering Yanshan University Qinhuangdao China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao China

Dissimilar path detection is an important task in software behavior detection. Previous dissimilar path mining algorithms ignore time-interval weight and dissimilarity. Therefore, a dissimilar path detecting algorithm called Graph-Dissimilar-Detect in complex software behavior network based on time-interval weight and dissimilarity is put forward. Firstly, weighted complex software behavior network model is built. DFS is adopted for the network to obtain paths. Secondly, Path-Length-Constraint is designed to prune some useless paths. Time-interval-Constraint is devised to prune some weak relation between software behaviors. Strong-Path-Checking is developed to prune weighted key sub-paths. Thirdly, KPath-Mine is designed to mine weighted key paths. Fourthly, definitions of dissimilar paths and path dissimilarity are provided and Dissimilar-Path-Mine is devised to find dissimilar paths. Experimental results show Graph-Dissimilar-Detect algorithm has a good scalability in detecting dissimilar paths in complex software behavior network. Furthermore, considering time-interval and path dissimilarity, more interesting and accurate key paths and dissimilar paths can be found. 1553-9105/Copyright © 2015 Binary information Press

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Road network information based edge bundling

引用

Journal of information and Computational Science 2015年第13期12卷 4909-4918页

作者： Nie, Junlan Zhang, Jikai Xin, Shuyue Guo, Dongliang College of Information Science and Engineering Yanshan University Qinhuangdao China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao China

To solve edge confusion problems in the geo-related graph visualization, here we present an edge bundling algorithm based on the road network information. First, the improved Dijkstra shortest path algorithm is employed to calculate the related path of original edges, and slicing quadratic Bezier curves are fitted out to replace original edges according to these path information. And then, the curve segments that satisfy conditions are merged together according to the control point consolidation strategy and thickened according to their weights, which simplifies the bundling result and also effectively shows the heat of each path;Finally, for the interested curves in the human-computer interaction, highlighted transition colors are introduced to character their directivity, and the effect is intuitive. The experimental results show that, our algorithm can effectively bundle original edges, which reduces the confusion degree of the graph. Meanwhile, the bundling result is more close to the original path, which improves the readability and understandability of the graph effectively. ©, 2015, Journal of information and Computational Science. All right reserved.

关键词： Human computer interaction

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：