欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
由于EM算法不适合空间聚类对空间信息的要求,而邻域EM算法虽然结合了空间惩罚项,但是NEM在E-step步需要大量的迭代.为了既能满足空间信息的要求,又能避免过多的计算量,本文提出了EM与NEM二者相结合的混合递增NEM算法,算法首先在随机子样本中进行EM训练,直到似然判断条件下降,根据增量因子进行样本更新,然后样本转向NEM训练一次,如此进行循环递增的交叉训练,使得计算量降低,性能提高.实验结果显示,MNEM只需要较少的运算便可达到收敛,聚类质量结果优于NEM.
英文摘要：
EM algorithm is inappropriate for spatial clustering which requires consideration of spatial information.Although neighborhood EM algorithm incorporates a spatial penalty term,it needs more iterations in every E-step.To incorporate spatial information and avoid too much additional computation,this paper proposed mixed increasing NEM algorithm that combines EM and NEM.In MNEM,algorithm first train data based on random sub-sampling in EM till the likelihood-judgement condition begins to decrease,and update su...
同期刊论文项目
同项目期刊论文
3-D multi-step travel time tomography: Imaging the local, deep velocity structure of Rabaul volcano,
期刊信息
位置：