In this paper we propose a new similarity measures in order to overcome some problems in [1],and proposethe idea for similarity direction of vague sets by which to describe which one is more accurate between vague set...In this paper we propose a new similarity measures in order to overcome some problems in [1],and proposethe idea for similarity direction of vague sets by which to describe which one is more accurate between vague sets. Atsame time we propose a method to determine the similarity direction. Based on above,we present a new bidirectionalapproximate reasoning approach on vague set that fully uses the message accuracy of vague set. So this improves theaccruacy and applicability of approximate reasoning. This provides a useful tool for approximate reasoning in intelli-gence system.展开更多
在线社交网络是移动互联网时代最成功的服务之一,好友的可信任程度成为用户首要关注的问题,针对如何避免个人信息被恶意用户窃取和泄露,提出了一种双向的计算局部信任值的算法TWIT(Two-Way algorithm to Infer Trust),从可信任用户与恶...在线社交网络是移动互联网时代最成功的服务之一,好友的可信任程度成为用户首要关注的问题,针对如何避免个人信息被恶意用户窃取和泄露,提出了一种双向的计算局部信任值的算法TWIT(Two-Way algorithm to Infer Trust),从可信任用户与恶意用户两个方向综合推断用户间的信任值,并且考虑到朋友关系的可传递性,进一步结合机器学习中的分类算法提出了改进算法MTWIT,消除了必须存在网络路径这一前提限制,并且在信任值的推断正确率方面取得了一定的优势,同时确保了算法能够适应社交网络拓扑结构动态变化的特点。在新浪微博数据集上的实验结果充分说明了这一结论。展开更多
文摘In this paper we propose a new similarity measures in order to overcome some problems in [1],and proposethe idea for similarity direction of vague sets by which to describe which one is more accurate between vague sets. Atsame time we propose a method to determine the similarity direction. Based on above,we present a new bidirectionalapproximate reasoning approach on vague set that fully uses the message accuracy of vague set. So this improves theaccruacy and applicability of approximate reasoning. This provides a useful tool for approximate reasoning in intelli-gence system.
文摘在线社交网络是移动互联网时代最成功的服务之一,好友的可信任程度成为用户首要关注的问题,针对如何避免个人信息被恶意用户窃取和泄露,提出了一种双向的计算局部信任值的算法TWIT(Two-Way algorithm to Infer Trust),从可信任用户与恶意用户两个方向综合推断用户间的信任值,并且考虑到朋友关系的可传递性,进一步结合机器学习中的分类算法提出了改进算法MTWIT,消除了必须存在网络路径这一前提限制,并且在信任值的推断正确率方面取得了一定的优势,同时确保了算法能够适应社交网络拓扑结构动态变化的特点。在新浪微博数据集上的实验结果充分说明了这一结论。