Time-Frequency Feature Extraction of Newborn EEG Seizure Using SVD-Based Techniques

Abstract

<p/> <p>The nonstationary and multicomponent nature of newborn EEG seizures tends to increase the complexity of the seizure detection problem. In dealing with this type of problems, time-frequency-based techniques were shown to outperform classical techniques. This paper presents a new time-frequency-based EEG seizure detection technique. The technique uses an estimate of the distribution function of the singular vectors associated with the time-frequency distribution of an EEG epoch to characterise the patterns embedded in the signal. The estimated distribution functions related to seizure and nonseizure epochs were used to train a neural network to discriminate between seizure and nonseizure patterns.</p

Feature Extraction for Systolic Heart Murmur Classification

“…U and V are generally called left and right eigenvectors, or in this particular case eigentime and eigenfrequency, respectively. To create a compact representation, a distribution function was extracted for eigentimes and eigenfrequencies corresponding to the two largest eigenvalues (since eigenvectors are orthonormal, their squared elements can be considered as density functions 10 ). A histogram (10 bins) was computed for each distribution function leading to 40 new features (Eigenfrequency 1 1-10, Eigenfrequency 2 1-10, Eigentime 1 1-10 and Eigentime 2 1-10).…”

A robust heart sounds segmentation module based on S-transform

“…In [22], authors extracted the eigenvalues of the time-frequency matrix. In [23], authors extended the method to also incorporate information from the eigenvectors to classify EEG seizures. In [24], the last technique is applied on the S-matrix in the aim to extract features for systolic heart murmur classification.…”

Phonocardiogram Signal Processing Module for Auto-Diagnosis and Telemedicine Applications

“…In [19] authors extracted the eigenvalues of the time-frequency matrix. In [20] authors extended the method to also incorporate information from the eigenvectors to classify EEG seizures. In [21] the last technique is applied on the S-matrix in the aim to extract features for systolic heart murmur classification.…”

“…Where U(M×M) and V(N×N) are orthonormal matrices so their squared elements can be considered as density function [20], …”