Electrical Engineering-Systems Dept.

סמינר מחלקתי

You are invited to attend a lecture by

Dr. Koby Todros

(School of Electrical Engineering, TAU)

on the subject:

On Measure Transformed Independent Component Analysis

In this work we derive a new framework for independent component analysis (ICA), called measure-transformed ICA (MTICA), that is based on applying a structured transform to the probability distribution of the manifest vector, i.e., transformation of the probability measure defined on its observation space. By judicious choice of the transform we show that the separation matrix can be uniquely determined via diagonalization of some measure-transformed covariance matrices. In MTICA the separation matrix is estimated via approximate joint diagonalization of some empirical measure-transformed covariance matrices. Unlike kernel based ICA techniques where the transformation is applied repetitively to some affine mappings of the manifest vector, in MTICA the transformation is applied to its probability distribution only once. This results in performance advantages and reduced implementation complexity. The proposed approach is illustrated in extensive simulation examples that show its advantages as compared to other existing state-of-the-art methods for ICA. MTICA is also applied to automated detection and extraction of atrial fibrillation activity from non-invasive ECG signals.

BIO:Koby Todros was born in Ashkelon, Israel, in 1974. He received the B.Sc., M.Sc. (summa cum laude), and Ph.D. (summa cum laude) degrees in Electrical Engineering in 2000, 2006, and 2011, respectively from the Ben-Gurion University of the Negev, Beer-Sheva, Israel. He was a post-doctoral fellow with the Department of Electrical Engineering and Computer Science, University of Michigan, Ann-Arbor, MI, U.S.A, from 2010 to 2012. Currently, he is continuing his research as a post-doctoral fellow in the Department of Electrical Engineering, Tel-Aviv University, Tel-Aviv, Israel. His research interests include statistical signal processing and estimation theory with focus on association analysis, multivariate data analysis, uniformly optimal biased estimation in the non-Bayesian theory, performance bounds for parameter estimation, blind source separation, and biomedical signal processing. He is an IEEE member since 2012, and serves as an affiliate member of the Sensor Array and Multichannel (SAM) technical committee in the IEEE Signal Processing Society, since 2013. Koby Todros was awarded the Pharan and Lev-Zion fellowships for excellent doctoral students in 2007 and 2009, respectively.