无线网络中对于兴趣数据优化检测研究

发布时间：2018-04-10 11:01

本文选题：无线网络 + 特征提取　；参考：《计算机仿真》2016年11期

【摘要】：无线网络中兴趣数据的检测,可以改善用户的网络体验。对兴趣数据检测时,首先在一定尺度下对无线网络产生的数据进行分解,分解后将用户检索频率组分不同于其它大部分数据的数据作为兴趣数据。而传统的叶贝斯算法,没有明确的分解系数,只能对整体数据进行检索,导致兴趣数据检测精度差的问题。提出一种相关子空间的无线网络中兴趣数据优化检测方法。先计算局部数据属性维上数据稀疏程度,利用计算的结果对与兴趣数据相关子空间进行定义,映射所有局部数据集上的兴趣数据分布特征,并对兴趣数据序列样本进行多维空间构建,获取兴趣数据聚类间距距离,并作为依据实现无线网络中兴趣数据的优化检测。仿真结果表明,改进算法可以提高无线网络中兴趣数据检测效率,有效的提升兴趣数据检测的准确性。
[Abstract]:The detection of interest data in wireless networks can improve the network experience of users.In the detection of interest data, the data generated by wireless network is decomposed at a certain scale, and then the data which is different from most other data is used as interest data.However, the traditional Bayesian algorithm has no explicit decomposition coefficient and can only retrieve the whole data, which leads to the problem of poor detection accuracy of the interesting data.An optimal detection method of interest data in wireless networks based on correlation subspace is proposed.Firstly, the sparse degree of local data attribute dimension is calculated, then the subspace related to interest data is defined by the result of calculation, and the distribution characteristics of interest data on all local data sets are mapped.The interest data sequence samples are constructed in multi-dimensional space to obtain the distance between the interest data clustering and as the basis to realize the optimal detection of interest data in wireless networks.Simulation results show that the improved algorithm can improve the efficiency of interest data detection and improve the accuracy of interest data detection.
【作者单位】：广州大学华软软件学院;
【分类号】：TN92

【相似文献】