Comparison of fractal dimension estimation algorithms for epileptic seizure onset detection

Polychronaki, GE; Ktonas, PY; Gatzonis, S; Siatouni, A; Asvestas, PA; Tsekou, H; Sakas, D; Nikita, KS

dc.contributor.author	Polychronaki, GE	en
dc.contributor.author	Ktonas, PY	en
dc.contributor.author	Gatzonis, S	en
dc.contributor.author	Siatouni, A	en
dc.contributor.author	Asvestas, PA	en
dc.contributor.author	Tsekou, H	en
dc.contributor.author	Sakas, D	en
dc.contributor.author	Nikita, KS	en
dc.date.accessioned	2014-03-01T01:33:02Z
dc.date.available	2014-03-01T01:33:02Z
dc.date.issued	2010	en
dc.identifier.issn	1741-2560	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/20283
dc.subject	Epileptic Seizure	en
dc.subject	Estimation Algorithm	en
dc.subject	Fractal Dimension	en
dc.subject	Onset Detection	en
dc.subject.classification	Engineering, Biomedical	en
dc.subject.classification	Neurosciences	en
dc.subject.other	Epileptic seizures	en
dc.subject.other	Estimation algorithm	en
dc.subject.other	False positive rates	en
dc.subject.other	Fractal dimension estimation	en
dc.subject.other	Higuchi's algorithms	en
dc.subject.other	K-nearest neighbour (k-NN)	en
dc.subject.other	k-NN algorithm	en
dc.subject.other	Natural measure	en
dc.subject.other	Seizure detection	en
dc.subject.other	Seizure onset	en
dc.subject.other	Synthetic signals	en
dc.subject.other	Testing data	en
dc.subject.other	Training data sets	en
dc.subject.other	Wave forms	en
dc.subject.other	Drops	en
dc.subject.other	Electroencephalography	en
dc.subject.other	Estimation	en
dc.subject.other	Finite difference method	en
dc.subject.other	Fractal dimension	en
dc.subject.other	Partial discharges	en
dc.subject.other	Statistical tests	en
dc.subject.other	Algorithms	en
dc.subject.other	adult	en
dc.subject.other	algorithm	en
dc.subject.other	article	en
dc.subject.other	clinical article	en
dc.subject.other	comparative study	en
dc.subject.other	diagnostic accuracy	en
dc.subject.other	electroencephalogram	en
dc.subject.other	female	en
dc.subject.other	fractal dimension	en
dc.subject.other	human	en
dc.subject.other	male	en
dc.subject.other	mathematical computing	en
dc.subject.other	priority journal	en
dc.subject.other	scalp	en
dc.subject.other	seizure	en
dc.subject.other	spectral sensitivity	en
dc.subject.other	waveform	en
dc.title	Comparison of fractal dimension estimation algorithms for epileptic seizure onset detection	en
heal.type	journalArticle	en
heal.identifier.primary	10.1088/1741-2560/7/4/046007	en
heal.identifier.secondary	http://dx.doi.org/10.1088/1741-2560/7/4/046007	en
heal.identifier.secondary	46007	en
heal.language	English	en
heal.publicationDate	2010	en
heal.abstract	Fractal dimension (FD) is a natural measure of the irregularity of a curve. In this study the performances of three waveform FD estimation algorithms (i.e. Katz's, Higuchi's and the k-nearest neighbour (k-NN) algorithm) were compared in terms of their ability to detect the onset of epileptic seizures in scalp electroencephalogram (EEG). The selection of parameters involved in FD estimation, evaluation of the accuracy of the different algorithms and assessment of their robustness in the presence of noise were performed based on synthetic signals of known FD. When applied to scalp EEG data, Katz's and Higuchi's algorithms were found to be incapable of producing consistent changes of a single type (either a drop or an increase) during seizures. On the other hand, the k-NN algorithm produced a drop, starting close to the seizure onset, in most seizures of all patients. The k-NN algorithm outperformed both Katz's and Higuchi's algorithms in terms of robustness in the presence of noise and seizure onset detection ability. The seizure detection methodology, based on the k-NN algorithm, yielded in the training data set a sensitivity of 100% with 10.10 s mean detection delay and a false positive rate of 0.27 h-1, while the corresponding values in the testing data set were 100%, 8.82 s and 0.42 h-1, respectively. The above detection results compare favourably to those of other seizure onset detection methodologies applied to scalp EEG in the literature. The methodology described, based on the k-NN algorithm, appears to be promising for the detection of the onset of epileptic seizures based on scalp EEG. © 2010 IOP Publishing Ltd.	en
heal.publisher	IOP PUBLISHING LTD	en
heal.journalName	Journal of Neural Engineering	en
dc.identifier.doi	10.1088/1741-2560/7/4/046007	en
dc.identifier.isi	ISI:000280038600011	en
dc.identifier.volume	7	en
dc.identifier.issue	4	en