%0 Journal Article
%T 一种选择特征的稀疏在线学习算法<br>A sparse online learning algorithm for feature selection
%A 魏波
%A 张文生
%A 李元香
%A 夏学文
%A 吕敬钦&lt
%A br&gt
%A WEI Bo
%A ZHANG Wensheng
%A LI Yuanxiang
%A XIA Xuewen
%A LYU Jingqin
%J 山东大学学报（工学版）
%D 2017
%R 10.6040/j.issn.1672-3961.1.2016.060
%X 摘要： 为了有效处理海量、高维、稀疏的大数据,提高对数据的分类效率,提出一种基于L1准则稀疏性原理的在线学习算法(a sparse online learning algorithm for selection feature, SFSOL)。运用在线机器学习算法框架,对高维流式数据的特征进行新颖的“取整”处理,加大数据特征稀疏性的同时增强了阀值范围内部分特征的值,极大地提高了对稀疏数据分类的效果。利用公开的数据集对SFSOL算法的性能进行分析,并将该算法与其它3种稀疏在线学习算法的性能进行比较,试验结果表明提出的SFSOL算法对高维稀疏数据分类的准确性更高。<br>Abstract: In order to effectively deal with mass, high dimensional and sparse big data and improve the efficiency of data classification, an online learning algorithm based on the sparsity principle of L1 norm was proposed. The feature of high dimensional streaming data were novel “Integer” processed by using the online machine learning algorithm framework increased the sparsity of data feature, meanwhile enhanced the partial feature value within the scope of the threshold value and greatly improved the effect of sparse data classification. The performance of SFSOL algorithm was analyzed by using public data sets. The algorithm and the performance of the other three sparse online learning algorithms were compared. The experimental results showed that SFSOL algorithm was more suitable to accurately classify for high-dimensional sparse data
%K 大数据
%K 机器学习
%K 在线学习
%K 稀疏性
%K &lt
%K i&gt
%K L&lt
%K /i&gt
%K &lt
%K sub&gt
%K 1&lt
%K /sub&gt
%K 准则
%K &lt
%K br&gt
%K &lt
%K i&gt
%K L&lt
%K /i&gt
%K &lt
%K sub&gt
%K 1&lt
%K /sub&gt
%K norm
%K big data
%K machine learning
%K online learning
%K sparsity
%U http://gxbwk.njournal.sdu.edu.cn/CN/10.6040/j.issn.1672-3961.1.2016.060