| fMRI信号盲分离的一种独立成分分析算法 |
| |
| 引用本文： | 潘丽丽,史振威,唐焕文,唐一源,张伟伟.fMRI信号盲分离的一种独立成分分析算法[J].大连理工大学学报,2005,45(4):607-611. |
| |
| 作者姓名： | 潘丽丽 史振威 唐焕文 唐一源 张伟伟 |
| |
| 作者单位： | 大连理工大学,计算生物学和生物信息学研究所,辽宁,大连,116024;大连理工大学,神经信息学研究所,辽宁,大连,116024 |
| |
| 基金项目： | 科技部国际科技合作项目;教育部科学技术研究项目;国家自然科学基金 |
| |
| 摘 要： | 建立了独立成分分析(independentcomponentanalysis,ICA)的一个优化模型,在此基础上,给出了一个新的梯度算法,称之为Orth-ExtBS算法.该算法结合了ExtBS算法和FastICA算法,兼顾两者的优点,形式简单,易于应用,能有效地盲分离具有超高斯和亚高斯分布源的混合信号,获得更准确的分离效果和较快的收敛速度.将新的算法与其他两个算法(FastICA和ExtBS)分别应用到大型fMRI数据中,通过比较发现,新算法在估计激活的时间动力学准确性上要优于其他两个算法.
|
| 关 键 词： | 独立成分分析 盲源分离 梯度算法 功能磁共振成像 |
| 文章编号： | 1000-8608（2005）04-0607-05 |
| 收稿时间： | 2004-03-26 |
| 修稿时间： | 2004-03-26 |
An independent component analysis algorithm for blind separation of fMRI signals |
| |
| PAN Li-li,SHI Zhen-wei,TANG Huan-wen,TANG Yi-yuan,ZHANG Wei-wei.An independent component analysis algorithm for blind separation of fMRI signals[J].Journal of Dalian University of Technology,2005,45(4):607-611. |
| |
| Authors: | PAN Li-li SHI Zhen-wei TANG Huan-wen TANG Yi-yuan ZHANG Wei-wei |
| |
| Abstract: | An optimization model for independent component analysis (ICA) is built. A new gradient algorithm based on the model is presented, which is called Orth-ExtBS algorithm. This algorithm combines the advantages of the FastICA and ExtBS algorithms, which is easy to use in simple form and is able to separate blindly mixed signals with sub-Gaussian and super-Gaussian source distributions. The accuracy of the Orth-ExtBS algorithm is high and its convergence speed is fast. Applying the Orth-ExtBS algorithm and two other algorithms (FastICA and ExtBS) to fMRI data, the results show that the new algorithm is superior to the other two on accuracy of estimating the temporal dynamics of activations by comparison. |
| |
| Keywords: | independent component analysis blind source separation gradient algorithm functional magnetic resonance imaging |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
