| Paper: | MLSP-P6.6 | ||
| Session: | Learning Theory and Models | ||
| Time: | Thursday, May 20, 15:30 - 17:30 | ||
| Presentation: | Poster | ||
| Topic: | Machine Learning for Signal Processing: Learning Theory and Modeling | ||
| Title: | QUALITY ASSESSMENT OF HYBRID NONLINEAR FILTERS | ||
| Authors: | Mo Chen; Imperial College, London | ||
| Danilo Mandic; Imperial College, London | |||
| Abstract: | Adaptive signal processing research has been directed towardsdesigning adaptive filters with high performance in terms of someperformance measure, however, little is known about how suchfilters influence the nature of the processed signal. Based uponsome recently introduced results on dealing with nonlinearitywithin a signal in hand (DVV method), we provide a criticalassessment of the qualitative performance of common linear andnonlinear filters and their combinations. Therefore, an insightinto the performance of the so called hybrid filters is provided,which is achieved for combinations of standard nonlinear (neural)and linear filters. It is shown that depending on the application,it is important not only to look for best filter performance interms of some quantitative measure of error but also for a filterthat will not change the character of a signal. Simulation resultssupport the analysis. | ||
| Back | |||
Home -||-
Organizing Committee -||-
Technical Committee -||-
Technical Program -||-
Plenaries
Paper Submission -||-
Special Sessions -||-
ITT -||-
Paper Review -||-
Exhibits -||-
Tutorials
Information -||-
Registration -||-
Travel Insurance -||-
Housing -||-
Workshops