Source Separation for Nonlinear Mixtures: How and Why?
Event details
| Date | 03.10.2013 |
| Hour | 14:00 › 15:00 |
| Speaker |
Prof. Christian Jutten, University Joseph Fourier, Grenoble, France Bio: Christian Jutten is Professor of Statistical Signal Processing in the Engineering Department of University Joseph Fourier of Grenoble. From 1993 through to 2007, he served as director or deputy director of his laboratory. From 2007 to 2010, he was both director of the Signal and Image Processing Department (more than 100 academic, post-doc and PhD students) and deputy director of GIPSA-lab (about 300 academic, post-doc and PhD students, and engineering and administrative staffs). His main research contributions are in statistical signal processing, and is well known for his pioneer works in source separation since middle of 80's. He is author or co-author of more than 75 papers in international journals, 4 books, 25 keynote plenary talks and more than 150 communications in international conferences. He is currently Deputy Director in charge of Signal and Image Processing in National Institute of Information Sciences and its Interactions in the French National Center for Scientific Research (CNRS). He was member of IEEE Technical Committees : Blind Signal Processing of the Circuits and Systems Society (2000 to now) and Machine Learning for Signal Processing of the Signal Processing Society (2007 to 2012). He received the best paper award of Eurasip Signal Processing(1991) and IEEE Trans. on Geoscience and Remote Sensing (2012), the Medal Blondel from the French Electrical Engineering Society (SEE) in 1997), and has been elected as a Senior Member of Institut Universitaire de France and IEEE Fellow in 2008, and EURASIP fellow in 2013. In 2012, he was a recipient of an ERC Advanced Grant on challenges in extraction and separation of source (CHESS). |
| Location | |
| Category | Conferences - Seminars |
The problem of source separation has been addressed mainly for linear mixtures, either memoryless or convolutive. Methods for solving the problem are based on source assumptions like statistical independence (ICA), time properties (coloration or nonstationarity), positivity or sparsity. However, although linearity is very often a convenient approximation, there are some applications in which the mixing process is clearly nonlinear.
In this talk, in a first part, I explain basics on source separation and main results in the linear case before pointing out the main problems encountered by source separation in nonlinear mixtures and how they can be overcome.
Then, in a second part, I will consider actual strongly nonlinear problems: one in image processing and another one in chemical sensor array processing. For each problem, I will derive the nonlinear models, show how source separation can be applied and experiment results which can be achieved.
In this talk, in a first part, I explain basics on source separation and main results in the linear case before pointing out the main problems encountered by source separation in nonlinear mixtures and how they can be overcome.
Then, in a second part, I will consider actual strongly nonlinear problems: one in image processing and another one in chemical sensor array processing. For each problem, I will derive the nonlinear models, show how source separation can be applied and experiment results which can be achieved.
Practical information
- General public
- Free
Organizer
- EE Institute
Prof. Pierre Vandergheynst, [email protected]
Prof. Jean-Philippe Thiran, [email protected]
Contact
- Prof. Pierre Vandergheynst, [email protected]
Prof. Jean-Philippe Thiran, [email protected]