移动互联网中特征数据准确提取仿真研究

发布时间：2018-05-29 03:50

本文选题：移动互联网 + 特征数据　；参考：《计算机仿真》2017年02期

【摘要】：对移动互联网中特征数据准确提取,可减少移动互联网的运行负荷。进行特征数据提取时,应分析不同数据属性的区分能力,对移动互联网数据进行属性约简,减少特征数据提取的工作量,但是传统方法是通过获取移动互联网数据集合的模糊粗糙近似,构造移动互联网特征数据属性集提取的目标函数,但是不能有效对移动互联网数据进行属性约简,导致特征数据提取耗时长,效率低下的问题。提出一种基于粒计算与区分能力的移动互联网中特征数据准确提取方法。首先利用统计学中的分层抽样技术将移动互联网初始数据集拆分为多个样本子集(粒),并计算出每个粒上数据属性的区分能力,融合于小生境免疫优化理论,引入属性集合的分类近似标准作为数据属性约简免疫优化的亲和度,然后生成小生境免疫共享机制,对移动互联网数据属性约简,最终建立移动互联网中特征数据准确提取模型。仿真结果表明,所提方法移动互联网中特征数据提取精确度高,为更好地提升移动互联网服务质量奠定了坚实的基础。
[Abstract]:Accurate extraction of feature data in mobile Internet can reduce the running load of mobile Internet. In order to reduce the workload of feature data extraction, we should analyze the distinguishing ability of different data attributes and reduce the attribute reduction of mobile Internet data. But the traditional method is to obtain fuzzy rough approximation of mobile Internet data set, and construct objective function of mobile Internet feature data attribute set extraction, but it can not effectively reduce mobile Internet data attribute. It leads to the problem of long time consuming and low efficiency of feature data extraction. This paper presents an accurate feature extraction method for mobile Internet based on granular computing and distinguishing ability. Firstly, the initial data set of mobile Internet is divided into several sample subsets by using stratified sampling technique in statistics, and the ability of distinguishing the attributes of each data on the grain is calculated, which is fused to the niche immune optimization theory. The classification approximation standard of attribute set is introduced as the affinity of data attribute reduction and immune optimization, and then the niche immune sharing mechanism is generated to reduce the attributes of mobile Internet data. Finally, an accurate model of feature data extraction in mobile Internet is established. The simulation results show that the proposed method has high accuracy of feature data extraction in mobile Internet, which lays a solid foundation for improving the QoS of mobile Internet.
【作者单位】：内蒙古财经大学计算机系;
【分类号】：TP393.01;TN929.5

【相似文献】