EEG analysis via multiscale Lempel-Ziv complexity for seizure detection

Robust seizure detection and seizure prediction continues to be a challenge. Lempel-Ziv Complexity (LZC) is one of the features that has shown to be relevant in seizure detection. Recent work has shown that augmenting LZC can be beneficial to emphasize variations in amplitude or frequency when analy...

Full description

Saved in:
Bibliographic Details
Main Author: Artan, N. Sertac
Format: Conference Proceeding
Language:English
Subjects:
Biomedical engineering
Complexity theory
Conferences
Electroencephalography
Entropy
Feature extraction
Quantization (signal)
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Robust seizure detection and seizure prediction continues to be a challenge. Lempel-Ziv Complexity (LZC) is one of the features that has shown to be relevant in seizure detection. Recent work has shown that augmenting LZC can be beneficial to emphasize variations in amplitude or frequency when analyzing biomedical signals. In this paper, we present a first look into evaluating the feasibility of using a recently proposed feature stemmed from LZC, namely the Multiscale Lempel-Ziv Complexity (MLZC) for seizure detection. MLZC does not allow the high-frequency signal components to be overwhelmed by the low frequency signal components when calculating complexity values. We compare MLZC and LZC for identifying seizures for three cases and show MLZC can provide a clear separation between non-ictal and ictal periods for all three cases using a single threshold over 7 recordings and 7 seizures per patient, whereas LZC provided such a clear separation for only one of the patients.
ISSN:1557-170X
2694-0604
DOI:10.1109/EMBC.2016.7591736