| Paper: | ITT-P2.1 | ||
| Session: | Emerging DSP Applications | ||
| Time: | Thursday, May 18, 10:00 - 12:00 | ||
| Presentation: | Poster | ||
| Topic: | Industry Technology Track: Biomedical | ||
| Title: | A FILTERING APPROACH TO UNDERDETERMINED BLIND SOURCE SEPARATION WITH APPLICATION TO TEMPOROMANDIBULAR DISORDERS | ||
| Authors: | Clive Cheong Took, Saeid Sanei, Jonathon Chambers, Cardiff University, United Kingdom | ||
| Abstract: | This paper addresses the underdetermined blind source separation problem, using a filtering approach. We have developed an extension of the FastICA algorithm which exploits the disparity in the kurtoses of the underlying sources to estimate the mixing matrix and thereafter achieve the recovery of the sources by employing the L1-norm algorithm. Also, we demonstrate how promising FastICA can be to extract the sources, without utilizing the L1-norm algorithm. This proposed algorithm exploits the sparsity of two highly super-Gaussian sources and the relative low amplitude and kurtosis of the third super-Gaussian source. Furthermore, we illustrate how this scenario is particularly suitable to the separation of the temporomandibular joint sounds, crucial in the diagnosis of temporomandibular disorders. | ||
©2018 Conference Management Services, Inc. -||- email: webmaster@icassp2006.org -||- Last updated Friday, August 17, 2012