网络社区作为新的资源发布和共享方式,其形成模式、 发现方式等是网络发展研究热点之一.由于聚类的随机性以及现有划分算法对个体和链接属性信息的语义利用不充分,社会网络的社区不能得到准确的分类.本文提出基于语义推理的网络社区发现模型,通过节点关系的拓扑结构和节点间的语义联系,抽取多层语义进行搜索并进行社区发现.在ego-Facebook数据集上的实验结果表明,当社区大小增长到1000以后,本算法更加稳定,更适用于节点包含丰富的语义且结构稀疏的网络.

This paper studied the information diffusion process in Microblog network in China. By empirical data collection we proposed a new diffusion model of concept based on mean-field assumption. The model is developed on BA model and under the mean-field assumption, by which we divide the users into three groups: "non-enlightened" group, "enlightened and committed" group and "enlightened yet non-committed" group. Experiments show that the lager the "enlightened yet non-committed" group to an opinion, the slower the diffusing process, and the more rational the network would be. And the transmission ways is insignificant referring the result.

In order to improve the speed and quality of color image segmentation, aiming at the limitation of the cuckoo algorithm, every time after the end of the Lévy flight, a new optimization seeking equation is proposed, and the discovery probability and the pace factor are respectively proposed a new operating equation. Based on this, proposed an enhanced cuckoo algorithm (ECS),and the ECS algorithm is based on the multi threshold segmentation of color image. Through the comparison of the proposed algorithm (ECS), the standard PSO algorithm and the standard CS algorithm,the ECS algorithm is the best of both subjective and objective results, fully able to be applied to the actual multi threshold segmentation.

针对推荐系统不能有效进行个性化推荐问题,在协同过滤过程中引入语义校验,通过对基于用户的协同过滤推荐结果进行语义校验,剔除概率较低的推荐结果,选择概率较高的结果推荐给用户,从而实现个性化语义推荐.在构建贝叶斯语义校验网络时,增加用户“喜好”偏好字段,通过问卷调查及信息反馈,确定用户对物品的喜好偏好值,确保贝叶斯语义校验网络的科学性.实验结果表明,本方法能剔除用户喜好度较低的物品,提高用户的满意度.

The behaviors of employed bees,onlooker bees in artificial bee colony algorithm are introduced into every time after the end of flight Levi of cuckoo search(CS)algorithm to optimized guiding,the discovery probability and the pace factor are also using the corresponding new variation factors,and change with cuckoo algorithm operation.Based on this,a hybrid artificial bee colony algorithm and cuckoo search algorithm (HACS)is proposed,and the HACS algorithm is used for color image segmentation.Experimental results show,the HACS algorithm can effectively solve the cuckoo algorithm long convergence time,lower accuracy.Good results have been achieved in the color image multi threshold segmentation.

随着遥感图像大数据的出现,常见的彩色遥感图像边缘检测方法运算量大、速度慢、效果差等缺点越来越明显。以四元数表示彩色像素为基础,改进人工蜂群算法的单一搜索方程,加大雇主蜂搜索范围,加入跟随蜂莱维飞行因子,提出了基于双搜索方程的人工蜂群算法。实验结果表明,该算法具有计算量小、去噪能力强、边缘检测效果好等优点。该算法能有效地应用于从遥感图像中获取识别目标。

为了进一步提高双聚类结果的性能,提出了一种基于变分贝叶斯的半监督双聚类算法.首先,在双聚类过程中引入了行和列的辅助信息,并提出了相应的联合分布概率模型;然后基于变分贝叶斯学习方法对联合概率分布中的参数进行估计;最后,通过合成数据集和真实的基因表达式数据集对提出的算法性能进行评估.实验表明,提出的算法在进行双聚类分析时,其归一化互信息量明显优于相关的双聚类算法.

针对传统的稀疏表示字典学习图像分类方法在大规模分布式环境下效率低下的问题,设计一种基于稀疏表示全局字典的图像学习方法.将传统的字典学习步骤分布到并行节点上,使用凸优化方法在节点上学习局部字典并实时更新全局字典,从而提高字典学习效率和大规模数据的分类效率.最后在MapReduce平台上进行并行化实验,结果显示该方法在不影响分类精度的情况下对大规模分布式数据的分类有明显的加速,可以更高效地运用于各种大规模图像分类任务中.

随着Web服务的广泛应用,服务发现成为服务请求者和服务提供者之间的重要环节,服务发现机制的优劣直接关系到整个服务应用的质量.为了向服务请求者提供高质量的Web服务,提出一种基于本体的多约束服务发现机制,该服务发现机制在语义层面从多个角度选择满足服务请求者需求的最佳服务,从而提供更准确的服务,提高服务的性能;最后实验数据表明基于本体的多约束服务发现机制能在很大程度上提高查准率,进而可以明显地提高服务系统质量.

This paper studies the network model in SLN by applying the methodology of social network to a widely accepted, real-life user interactive network scenario. The data and experiments are based on micro-blogging (Sina Weibo). Results show that the statistic properties of SLN are in close analogy with that of social network. Contrary to our normal understanding, some nodes with too much semantics (especially under one category) are in decreased chances of having links from newly added nodes.

微博作为一个基于用户关系的信息分享、传播以及获取平台,在重大突发公共事件中表现出了重要的信息发布、动态追踪和民情民意的展现等特点.该文研究突发社会公共事件下,微博舆论的形成和传播;提出了微博的舆论传播模型,该模型基于平均场(mean field)假设,将微博用户分为未获得信息无观点的人群、已获得信息且明确支持某观点的人群和已获得信息且不支持任何观点的人群,通过考察未发表观点者对观点的接受概率户来研究网络中观点的传播特性;最后通过系统仿真表明该方法可以很好地模拟微博网络的观点传播.

The instant information exchanging network of the Internet is interpreted as the consequences of invisible connection between humans. In the graph based studies the nodes are human beings and the edges represent various social relationships. The interactions among users can be interpreted via the formation and evolution of semantics. The interactive as well as intertwined behaviors are the foundation of network itself; at the same time, they shape the way how and where the network will evolve. This paper proposes a network growth model based on the semantic similarity as well as popularity of nodes. In our model, the nodes represent Sina Weibo blogs and are with semantics, the links are subscribing hyperlinks between nodes. The probability of link establishment between two nodes then calculated from the similarity between nodes. The data and experiments are based on Sina Weibo blogs, which are the continuous results of interactions by users. We collect data using WebCrawler from Sina API, obtaining a portion of the whole network. Results show that the statistic properties of Sina Weibo are in close analogy with that of social network and also the characteristic complex network. The studied network contains a number of very high-degree nodes; these nodes are the cores which small groups strongly clustered, and low-degree nodes at the fringes of the network. However, some nodes with too much semantics (especially under one category) are in decreased chances of having links from newly added nodes. The reason may lies in that the over-abundant semantics remains confusion for knowledge acquiring.

报表系统是呼叫中心信息化系统的重要部分.伴随着呼叫中心业务的不断拓展,传统报袁系统无法灵活、动态地满足呼叫业务需求.提出了基于SOA的报表服务模型以及报表服务应用的实现方式,从而确保呼叫报袁中数据源的一致性,同时为用户提供规范、统一的访问接口,实现各数据报表中数据的有效访问与共享.

The color of website has guiding function to influence consumer's purchase decision and to give consumption implication to consumer.In this paper,by combing the website examples and practice,from the angle of E-commerce website interface,researches into color's guiding functions.It's a valuable try in the research of guiding function of color emotion in E-commerce website interface.

Entrepreneurship education has increasingly attracted international interest and attention.This paper begins with a review of the emergence and growth of entrepreneurship education in the United States,including its entrepreneurship education system and supporting environment;followed by the discussion of entrepreneurial factors,as well as the stages in entrepreneurship education.It concludes with the reflections on the future of entrepreneurship education in China:1)The purpose of entrepreneurship education is not only to solve the employment problem,but also economic and social development need;2)entrepreneurship education from young people,including basic education,undergraduate education,graduate education and job training,with characteristics of entrepreneurship education system;3)entrepreneurship education is a lifelong learning process;4)innovation and entrepreneurship need;5)teachers are the key to the success of entrepreneurship education;6)to create a campus environment conducive to entrepreneurship.

Software dependability is one of the most important system property of a software system that user and developer concern. Software dependability evaluation is an important issue in the study of software system. The widely existing connections and uncertainty contained in the software dependability evaluation must be token into account simultaneously. In this paper, a linguistic bayesian network model has been proposed to solve this problem based on bayesian network and linguistic variable. Within this model, the ordered weighted average (OWA) operator is used to aggregate multiple experts' assessments to ensure the correctness of evaluation. The proposed model especially suitable for the evaluation in the uncertain environment. An illustrative example is given to show the effectiveness of the new model. Copyright © 2013 Binary Information Press.