Estimation of autocorrelation space for classification of bio-medical signals

Authors:
Mihir Narayan Mohanty;Aurobinda Routray
Affiliations:
ITER, Siksha ‘O' Anusandhan University, Bhubaneswar, Odisha, India;Department of Electrical Engineering, IIT Kharagpur, WB, India
Venue:
SEMCCO'12 Proceedings of the Third international conference on Swarm, Evolutionary, and Memetic Computing
Year:
2012

Citing 4
Cited 0

The nature of statistical learning theory

The nature of statistical learning theory
An introduction to variable and feature selection

The Journal of Machine Learning Research
Building Support Vector Machines with Reduced Classifier Complexity

The Journal of Machine Learning Research
Optimisation of features using evolutionary algorithm for EEG signal classification

International Journal of Computational Vision and Robotics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Classification of biomedical signals is a complex task, but the analysis is very useful in medical diagnosis. In this paper we estimate the autocorrelation matrix of some brain signal by embedding the autocorrelation cone using Linear Matrix Inequalities (LMI). The minimum sample window has been chosen for the improved computational complexity. The partitioning of the space has been carried out using support vector machines. This method has been tested on different EEG signals recorded on subjects performing a multiplication, thought for composition of a song. The base signature has been recorded while the subject apparently was not doing anything.