Methods for robust clustering of epileptic EEG spikes

The authors investigate algorithms for clustering of epileptic electroencephalogram (EEG) spikes. Such a method is useful prior to averaging and inverse computations since the spikes of a patient often belong to a few distinct classes. Data sets often contain outliers, which makes algorithms with ro...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on biomedical engineering 2000-07, Vol.47 (7), p.857-868
Main Authors: Wahlberg, P., Lantz, G.
Format: Article
Language:English
Subjects:
Algorithms
Biological and medical sciences
Biomedical Engineering
Brain modeling
Cluster Analysis
Clustering algorithms
Computer Simulation
Contamination
Database systems
Electrodes
Electroencephalography
Electroencephalography - statistics & numerical data
Epilepsy
Epilepsy - physiopathology
Errors
Feature extraction
Fuzzy sets
Graph theory
Headache. Facial pains. Syncopes. Epilepsia. Intracranial hypertension. Brain oedema. Cerebral palsy
Humans
Medical sciences
Methods
Nervous system (semeiology, syndromes)
Neurology
Patient monitoring
Pollution measurement
Robustness
Signal processing
Signal processing algorithms
Studies
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The authors investigate algorithms for clustering of epileptic electroencephalogram (EEG) spikes. Such a method is useful prior to averaging and inverse computations since the spikes of a patient often belong to a few distinct classes. Data sets often contain outliers, which makes algorithms with robust performance desirable. The authors compare the fuzzy C-means (FCM) algorithm and a graph-theoretic algorithm. They give criteria for determination of the correct level of outlier contamination. The performance is then studied by aid of simulations, which show good results for a range of circumstances, for both algorithms. The graph-theoretic method gave better results than FCM for simulated signals. Also, when evaluating the methods on seven real-life data sets, the graph-theoretic method was the better method, in terms of closeness to the manual assessment by a neurophysiologist. However, there was some discrepancy between manual and automatic clustering and the authors suggest as an alternative method a human choice among a limited set of automatically obtained clusterings. Furthermore, the authors evaluate geometrically weighted feature extraction and conclude that it is useful as a supplementary dimension for clustering.
ISSN:0018-9294
1558-2531
DOI:10.1109/10.846679