Extensions and Applications of Empirical Mode DecompositionDate: 2008-04-10 Add to Google Calendar
Time: 10:30 - 11:30
Location: Holmes 389
Speaker: Speaker: Dr. Danilo Mandic
Information “fusion” via signal “fission” is addressed in the framework of Empirical Mode Decomposition (EMD). In this way, a general nonlinear and nonstationary signal is first decomposed into its oscillatory components (fission); the components of interest are then combined in order to provide greater knowledge about a process in hand (fusion). Until recently, the majority of EMD-based fusion has been completed in an ad hoc fashion whereby the “correct” fission components are selected by visual inspection or empirically (by applying obinary weighting of fission components). To that end, we present several automatic fusion procedures. In particular, it is shown how EMD can be combined with machine learning to perform automatic data fusion, together with a reduction of its dependencies on parameter selection, which has proven an issue of concern in the past. Fusion algorithms are also entroduced for the recent extensions of EMD to the complex domain, to achieve feature extraction and fusion for multichannel data. The potential of these algorithms is demonstrated by applications on real world signals. Features of interest are extracted from different sets of biomedical signals ranging from data blood volume information to electroencephalogram (EEG) data. Additionally, it is shown that EMD has great potential in image processing. Examples on a variety of image processing problems from denoising through to the fusion of visual and thermal images support this analysis.
Dr Danilo Mandic (http://www.commsp.ee.ic.ac.uk/ mandic) is a Reader in Signal Processing at Imperial College London. He has been working in the area of nonlinear adaptive signal processing, nonlinear dynamics, and data/sensor fusion. His publication record includes two research monographs (Recurrent Neural Networks for Prediction, and Complex Valued Nonlinear Adaptive Filters) with Wiley, an edited book on Signal Processing for Information Fusion (Springer 2008), and more than 200 publications in Signal and Image Processing. He has been a Member of the IEEE Technical Committee on Machine Learning for Signal Processing, Associate Editor for the IEEE Transactions on Circuits and Systems II, IEEE Transactions on Signal Processing, and International Journal of Mathematical Modelling and Algorithms. Dr Mandic has produced award winning papers and products resulting from his collaboration with Industry. He is a Senior Member of the IEEE and Member of the London Mathematical Society. Dr Mandic has been a Guest Professor in KU Leuven Belgium, TUAT Tokyo, Japan and Westminster University UK, and Frontier Researcher in RIKEN Japan.