A Novel Matrix Representation of Discrete Biomedical Signals

TL;DR

This paper introduces a new matrix-based method to represent biomedical signals as images, enabling improved seizure detection and insights into brain activity through algebraic and geometric analysis.

Contribution

It presents a novel symmetric matrix representation of signals and demonstrates its application in automatic seizure detection outperforming traditional SVM methods.

Findings

Eigenvalue increases during seizures for certain patients

Proposed algorithm outperforms SVM-based detection

Matrix representation encodes brain activity effectively

Abstract

In this work we propose a novel symmetric square matrix representation of one or more digital signals of finite equal length. For appropriate window length and sliding paradigm this matrix contains useful information about the signals in a two dimensional image form. Then this representation can be treated either as an algebraic matrix or as a geometric image. We have shown applications of both on human multichannel intracranial electroencephalogram (iEEG). In the first application we have shown that for certain patients the highest eigenvalue of the matrix obtained from the epileptic focal channels goes up during a seizure. The focus of this paper is on an application of the second concept, by which we have come up with an automatic seizure detection algorithm on a publicly available benchmark data. Except for delay in detection in all other aspects the new algorithm outperformed the detection performance based on a support vector machine based algorithm. We have also indicated how this sparse random matrix representation of brain electrical signals can encode the activities of the brain.