Cooperative caching game based on social trust for D2D communication networks

Content sharing via device‐to‐device (D2D) communications has become a promising method to increase system throughput and reduce traffic load. Due to the characteristic of spectrum sharing in D2D network, confidentiality is becoming a key issue in content transmission. Secure communication in D2D networks is generally guaranteed by a physical‐layer security mechanism. However, this method sacrifices the system transmission rate while ensuring security. Since mobile devices are carried by humans, we can leverage their trust relations to enhance the security of communications. As much, considering the psychology structure and social attributes of mobile users, we build a multidimensional trust evaluation mechanism to evaluate the trust relationship between users, and we pick out the trusted users based on the decision‐theoretic rough sets. By sharing content only between trust users, we can enhance the security of content transmissions without relying on physical‐layer security measures. Meanwhile, content caching is now widely used to improve accessing efficiency and reduce traffic load on cellular networks. However, caching content for other users incurs additional cost, which results in selfish and noncooperative behavior in users. Considering such selfishness, we introduce a cooperative caching game based on multidimensional trust relations to motivate users to cache contents for other devices. In this game, the trust relations and physical distance between two users are considered to formulate the cost function. Furthermore, we introduce an incentive caching algorithm based on social trust to minimize the total cost in the D2D network.     

基于贪心扰动的社交网络隐私保护研究

在社交网络的数据挖掘隐私保护问题中,连接边的权重和权重的隐私保护问题是非常重要的.为此,提出一种贪心扰动的隐私保护算法,以保证社交网络初始的最短路径不变并使其长度与扰动后相接近.仿真模拟计算结果表明,这种扰乱策略符合预期的理论分析结果.     

基于SEIR的社交网络信息传播模型

结合传染病动力学的SEIR模型,本文建立了适用于社交网络的信息传播模型。该模型基于社交网络用户的行为特征,分析了社交网络的传播机理和网络参数对信息传播过程的影响,得出了动力学演化方程组,刻画了信息传播过程随时间的演化规律。仿真实验的结果表明,本文提出的模型能正确地反映社交网络上的信息传播的趋势,较为准确地描述信息传播过程。     

位置社交网络的潜在好友推荐模型研究

为了提高位置社交网络的服务便捷性和用户感受度,与位置相关的推荐服务越来越具有重要意义和应用需求.提出的潜在好友推荐模型主要是根据签到位置的相似度及好友相似度进行潜在用户推荐.通过用户的好友关系、签到特性及签到历史记录,计算用户在各个位置兴趣点的位置权重,再分别利用位置权重及好友关系计算用户的位置相似度和好友相似度,最后根据用户位置和好友关系的综合相似度进行潜在用户推荐.实验结果表明,提出的潜在好友推荐模型是切实有效的.     

基于协同矩阵分解的评分与信任联合预测

信息评分预测和信任预测是社交评价网络中的两大基本问题.为应对在提高两类基本问题预测准确性过程中遇到的评分数据与信任关系数据稀疏问题,本文提出了一种基于协同矩阵分解的信息评分与信任预测联合模型.该模型在将评分矩阵与信任关系矩阵进行协同分解时,既能保证被分解的两个矩阵分解过程共享用户潜在变量,又能兼顾两个矩阵分解过程中能够各自获得反映本领域知识相关性的表达.使用分解得到的多个相关低维潜在变量矩阵乘积即可做出评分与信任两个问题的预测.两个真实网络数据集上的实验验证了提出模型有效性和先进性.     

基于迁移学习的唐诗宋词情感分析

随着计算社会学的兴起,利用数据挖掘分析社会情感是近期的研究重点.当前的研究主要针对现代文本,对于古代诗歌这类短文本的情感分析相对较少.本文提出了一个基于短文本特征扩展的迁移学习模型CATL-PCO,通过分析诗歌情感对当时社会及文化进行进一步了解.该模型首先基于频繁词对对古文特征向量进行扩展,再通过迁移学习方式,建立三个分类器并投票得出最后的情感分析结果.CATL-PCO模型首先能够解决古文短文本特征稀疏的问题,在此基础上进一步解决由于现代译文信息匮乏所导致的古代诗歌情感分析困难问题,从而准确的分析古诗词情感倾向,从计算社会学的角度,增进对中国历史的认识.实验表明,当训练集为中国唐诗时,本文提出方法能够准确的对唐代诗歌进行情感分类,并能应用于唐代和宋代各个时期情感分析及代表流派分析.     

基于区域交互模型的SNS网络用户影响力评估

针对现有方法与模型未能准确体现不同距离用户之间真实交互行为的问题,提出了一种基于用户区域交互模型的用户影响力评估方法。区域交互模型利用影响力传递的不同方式,刻画不同距离之间用户的交互行为模式,能更为真实准确地反映在线社会网络用户之间的交互行为。通过计算用户对相邻用户的显性影响力与非相邻用户的隐性影响力,可有效识别在线社会网络中大影响力用户、僵尸粉用户等不同类型用户。基于新浪微博与人人网真实数据开展用户影响力评估以及相应的用户角色识别实验,结果显示,与现有方法相比,基于区域交互模型的识别方法可以准确有效地识别出在线社会网络中的大影响力用户、僵尸粉用户等各类型用户。     

Location privacy preservation approach towards to content sharing on mobile online social network

A privacy access control model for content sharing was presented to fine-grained control users' location infor-mation associated with sharing content in mobile social network. A k-anonymity privacy algorithm for privacy settings was given to protect against inference attack on a content sharing service provider server. To balance the privacy and quality of service, a location shifting method was presented. Finally experimental results demonstrate the validity and practicality of the proposed approach.     

A scheme of access service recommendation for the Social Internet of Things

The rapid increase in the complexity and the extent of personalization of services in the Internet of Things (IoT) has led to a greater demand for frequent collaboration among heterogeneous devices. Moreover, with the inseparable relations between human and devices, the paradigm of Social IoT (SIoT) is gaining popularity in recent years. How to effectively facilitate the access to quality services and credible devices in large‐scale networks via defining, establishing, and managing social architectures among things has become a critical issue. In this paper, a scheme of access service recommendation for the SIoT is presented with the understanding of inherent constraints and factors that influence the security and stability of IoT networks. In which, timeliness properties are considered in each transaction for dynamic performance enhancements. With the benefits of promoting service discovery and composition, social relationships among things are introduced in the proposed scheme. An energy‐aware mechanism is also utilized as a restrictive factor in trustworthiness evaluation. Finally, the recommendation is based not only on the past performance but also on the social relationship and the energy status of nodes. Simulation experiments demonstrate the effectiveness and benefits of our scheme from three aspects including rating accuracy, dynamic behavior, and network stability. Copyright © 2015 John Wiley & Sons, Ltd.     

广州市公园对比评价研究——基于社交媒体数据的文本分析

传统公园评价的研究大多集中在单个公园使用满意度方面,存在问卷样本量小、采集时间较集中等缺陷。大数据相关研究的快速发展为公园系统评价提供了新的契机。基于对社交媒体数据的文本分析,研究对比广州市 50 个公园的评价结果,同时探究公园评价与人口统计学特征、地理区位、评价时间以及公园属性之间的关系。研究发现, 1）公园正面评价主要集中在免费设施、环境和特色等方面,而负面评价多集中于公园卫生、交通成本、停车等管理服务方面,广州公园的管理服务水平亟待提升。 2）女性较男性更关注公园能否满足其对社交场所的需求,本地游客较外地游客更关注公园本身的服务质量而非公园的外部属性。 3）基干公园应更侧重其可达性和基本的服务功能,承担大众日常活动;特色公园应更注重满足特定人群的需求及特色打造;自然公园应更关注公园生态质量并能够承担需要较大场地的活动。 4） 2010—2018 年,人们越来越关注公园特色的打造,在公园中的活动类型也越来越多样,现代公园建设更应着力于文化服务质量的提升。研究突破传统公园研究方法的局限,将大数据的手段运用到多个公园的整体评价当中,有助于建立更普适、更有针对性的公园评价指标体系,具有较高的实践价值。