Title :
Nonlinear signal classification using geometric statistical features in state space
Author_Institution :
Dept. of Comput. Sci. & Eng., Fudan Univ., Shanghai, China
fDate :
6/10/2004 12:00:00 AM
Abstract :
A new methodology in the framework of high-dimensional shape analysis in state space is proposed for nonlinear signal classification. The zero-crossing rate on a Poincare surface of a section is used as a feature. Experiments regarding oceanic signal classification show that the proposed methodology can provide some information not contained in spectra.
Keywords :
Poincare mapping; geophysical signal processing; oceanographic techniques; signal classification; signal reconstruction; state-space methods; Poincare surface; geometric statistical features; nonlinear signal classification; oceanic signal classification; shape analysis; state space; zero crossing rate;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:20040498
