Design of an Optimum Poincare Plane for Extracting Meaningful Samples From Eeg Signals Publisher Pubmed



Sharif B^{1, 2} ; Jafari AH^{1, 2} Show Affiliations
Source: Australasian Physical and Engineering Sciences in Medicine Published:2018

Abstract

Biosignals are considered as important sources of data for diagnosing and detecting abnormalities, and modeling dynamics in the body. These signals are usually analyzed using features taken from time and frequency domain. In theory‚ these dynamics can also be analyzed utilizing Poincare plane that intersects system’s trajectory. However‚ selecting an appropriate Poincare plane is a crucial part of extracting best Poincare samples. There is no unique way to choose a Poincare plane‚ because it is highly dependent to the system dynamics. In this study, a new algorithm is introduced that automatically selects an optimum Poincare plane able to transfer maximum information from EEG time series to a set of Poincare samples. In this algorithm‚ EEG time series are first embedded; then a parametric Poincare plane is designed and finally the parameters of the plane are optimized using genetic algorithm. The presented algorithm is tested on EEG signals and the optimum Poincare plane is obtained with more than 99% data information transferred. Results are compared with some typical method of creating Poinare samples and showed that the transferred information using with this method is higher. The generated samples can be used for feature extraction and further analysis. © 2017, Australasian College of Physical Scientists and Engineers in Medicine.