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：
鉴于参考独立分量分析定义了所谓的接近性度量函数和与之相关的不等式，并把它作为约束项引入到负熵对比度函数中，取得了很好的分离效果，但存在若阈值选取不当则算法不收敛的问题．提出一个改进算法，算法的优化函数为负熵对比度函数和参考独立分量分析算法中的接近性度量函数之积，巧妙地避开了这个难以确定的阈值参数．针对合成数据和实际ECG数据的仿真实验表明，改进算法收敛快、提取效果好．
英文摘要：
Independent component analysis with reference （ICA-R） defines a so-called closeness measure function and inequality concerned, incorporates it into the negentropy contrast as a constrained terms to achieve good separation results. However, theoretic analysis and experiments shows ICA-R even can＇t converge if the threshold parameter is improperly selected. An improved algorithm is presented, whose optimization function is the product of the negentropy contrast and the closeness measure function in ICA-R, and it can smartly avoid the threshold parameter difficult to determine. Experiments with synthetic signals and real exchange software generator （ECG） data demonstrate its quick convergence and good separation.
同期刊论文项目
同项目期刊论文
Performance improvement for monostatic clutter mitigation using space-time-range three dimensional a
Unambiguous Doppler centroid estimation approach for SAR data based upon compressed signal magnitude
期刊信息
位置：