%0 Journal Article
%T Research of the improved robust twinned SOM based on Voronoi distance<br>基于Voronoi距离的鲁棒的双自组织特征映射网络
%A XIA Wen-wen
%A WANG Shi-tong
%A <br>夏文文
%A 王士同
%J 计算机应用
%D 2007
%I 
%X An improved twinned Self-Organizing Maps(SOM) based on Voronoi distance was presented in this paper.The traditional SOM is extended by using two related neuron networks simultaneously in order to enhance the robustness.Euclidean distance was replaced by the distance to the Vorinoi cell in the proposed SOM.We illustrated the prediction power of the proposed SOM on a real financial time series and artificial data sets.Results demonstrate the effectiveness and robustness of the proposed SOM.
%K Self-Organizing Maps(SOM)
%K robustness
%K Voronoi diagram<br>自组织映射网络
%K 鲁棒
%K Voronoi图
%K Voronoi
%K 欧式距离
%K 鲁棒性
%K 组织特征映射网络
%K distance
%K based
%K robust
%K improved
%K 结果
%K 实验
%K 预测
%K 金融时间序列
%K 改进
%K 增强
%K 离来
%K cell
%K 影响
%K 高噪声
%K 神经网络
%K 自组织
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=831E194C147C78FAAFCC50BC7ADD1732&aid=14E16CBD27430512B38F7FFDDCE4A975&yid=A732AF04DDA03BB3&vid=DB817633AA4F79B9&iid=94C357A881DFC066&sid=8DABBEB130EFF191&eid=1AA557EFF1C6B447&journal_id=1001-9081&journal_name=计算机应用&referenced_num=1&reference_num=11