The following information was submitted:
Transactions: INTERNATIONAL JOURNAL of CIRCUITS, SYSTEMS and SIGNAL PROCESSING
Transactions ID Number: 19-382
Full Name: Damjan Zazula
Position: Professor
Age: ON
Sex: Male
Address: University of Maribor, Faculty of EE and CS, Smetanova 17, 2000 Maribor
Country: SLOVENIA
Tel: +386 2 220 74 80
Tel prefix:
Fax: +386 2 220 72 72
E-mail address: zazula@uni-mb.si
Other E-mails: uelzaz01n@gmail.com
Title of the Paper: Segmentation of Compound Signals Using Higher-Order Activity Indexes
Authors as they appear in the Paper: Damjan Zazula, Rok Isteniè
Email addresses of all the authors: zazula@uni-mb.si, rok.istenic@uni-mb.si
Number of paper pages: 9
Abstract: The so called activity index is defined on the second-order statistics. In multiple-input multiple-output (MIMO) models, it estimates the level of activity of individual input sources. In this paper, we study an extended definition of activity index, which deploys higher-order statistics instead of the second-order. Experiments with synthetic models show that noise resistance at higher even orders increases. In spite of the fact that the level of superimpositions of source activity also increases, which is disturbing, a difference of the 4th- and 2nd-order activity indexes proves to be a reliable relative measure of the number of simultaneously active input sources. The measure is not influenced either by the properties of sources, or by the level of additive random Gaussian noise, or the over- or underdeterminancy of the model output observations. This can be of considerable help when analysing and, in particular, decomposing compound MIMO output signals.
Keywords: Activity index, Compound signal segmentation, Higher-order moments, MIMO models, Sparse signal sources
EXTENSION of the file: .pdf
Special (Invited) Session: Properties of Activity Index Extended by Higher-Order Moments
Organizer of the Session: 102-312
How Did you learn about congress:
IP ADDRESS: 94.140.69.175
