公开(公告)号：WO2003073064A3

公开(公告)日：2003-09-04

申请号：PCT/US2003/005265

申请日：2003-02-25

Applicant: THE CATHOLIC UNIVERSITY OF AMERICA ,  WANG, Yue, Joseph

Inventor： WANG, Yue, Joseph

IPC: G06K9/64

Abstract: The present invention describes a partial independent component (PICA) technique for blindly separating partially independent and/or gaussian-like sources from mixed observations over an informative index subspace, which allows various applications in independent component imaging. The present invention estimates a demixing matrix using only the independent and/or nongaussian portion of the observations. The present invention also demonstrates the principle of the approach on both controlled cases and real-world problems, and describes many extended applications of such a technique.

公开(公告)号：WO2003073064A2

公开(公告)日：2003-09-04

申请号：PCT/US2003/005265

申请日：2003-02-25

Applicant: THE CATHOLIC UNIVERSITY OF AMERICA ,  WANG, Yue, Joseph

Inventor： WANG, Yue, Joseph

IPC: G01N

CPC classification number: G06K9/0014 ,  G06K9/6232 ,  G06K9/6242 ,  G06T7/0012 ,  G06T2207/30072 ,  Y10S128/922

Abstract: The present invention describes a partial independent component analysis (PICA) technique for blindly separating partially independent and/or gaussian-like sources from mixed observations over an informative index subspace, which allows various applications in independent component imaging. The present invention estimates a demixing matrix using only the independent and/or nongaussian portion of the observations. Specifically, rather than using all the data points which give rise to a large separation error, a subset of the data points is identified such that the partial source profiles defined over such a subset are statistically independent and/or nongaussian. The present invention describes a complete implementation of such a technique, whose steps and parameters may be achieved and estimated using an information theoretic-based neural computational algorithm. The present invention also demonstrates the principle of the approach on both controlled cases and real-world problems, and describes many extended applications of such a technique.

Abstract translation: 本发明描述了一种用于在信息索引子空间上将部分独立和/或高斯状源从混合观察中盲目分离的部分独立分量分析（PICA）技术，其允许独立分量成像中的各种应用。 本发明仅使用观察值的独立和/或非整数部分来估计分类矩阵。 特别地，不是使用引起大的分离误差的所有数据点，而是识别数据点的子集，使得在这样的子集上定义的部分源简档是统计独立的和/或非泛素的。 本发明描述了这样的技术的完整实现，其技术的步骤和参数可以使用基于信息理论的神经计算算法来实现和估计。 本发明还演示了对控制案例和现实世界问题的方法的原理，并且描述了这种技术的许多扩展应用。

公开(公告)号：EP1479035A2

公开(公告)日：2004-11-24

申请号：EP03709232.7

申请日：2003-02-25

Applicant: THE CATHOLIC UNIVERSITY OF AMERICA

Inventor： WANG, Yue, Joseph

IPC: G06K9/64 ,  A61K9/127 ,  G06F15/00 ,  G10L15/06

CPC classification number: G06K9/0014 ,  G06K9/6232 ,  G06K9/6242 ,  G06T7/0012 ,  G06T2207/30072 ,  Y10S128/922

Abstract: The present invention describes a partial independent component (PICA) technique for blindly separating partially independent and/or gaussian-like sources from mixed observations over an informative index subspace, which allows various applications in independent component imaging. The present invention estimates a demixing matrix using only the independent and/or nongaussian portion of the observations. The present invention also demonstrates the principle of the approach on both controlled cases and real-world problems, and describes many extended applications of such a technique.