Persistent Homology based Classification of Chaotic Multi-variate Time Series with Application to EEG Data

Martina Flammer, Knut Hüper

2022

Abstract

An application of persistent homology for detection of epileptic events in EEG data is presented. Given point cloud data, persistent homology is a tool from topological data analysis to describe the structure of the underlying space on which the data was sampled by utilizing topological invariants and tracking their behavior on several spatial scales. As a preprocessing step, a novel method called Dynamical Component Analysis is used that reduces the dimension of a multi-variate time series by incorporating information about the dynamics of the system. The results show that our proposed method is appropriate to detect the occurence of petit-mal epileptic seizures in EEG signals.

Download


Paper Citation


in Harvard Style

Flammer M. and Hüper K. (2022). Persistent Homology based Classification of Chaotic Multi-variate Time Series with Application to EEG Data. In Proceedings of the 19th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO, ISBN 978-989-758-585-2, pages 595-604. DOI: 10.5220/0011144800003271


in Bibtex Style

@conference{icinco22,
author={Martina Flammer and Knut Hüper},
title={Persistent Homology based Classification of Chaotic Multi-variate Time Series with Application to EEG Data},
booktitle={Proceedings of the 19th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,},
year={2022},
pages={595-604},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011144800003271},
isbn={978-989-758-585-2},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,
TI - Persistent Homology based Classification of Chaotic Multi-variate Time Series with Application to EEG Data
SN - 978-989-758-585-2
AU - Flammer M.
AU - Hüper K.
PY - 2022
SP - 595
EP - 604
DO - 10.5220/0011144800003271