APPLICATION OF INTRINSIC TIME-SCALE DECOMPOSITION (ITD) TO EEG SIGNALS FOR AUTOMATED SEIZURE PREDICTION

Intrinsic time-scale decomposition (ITD) is a new nonlinear method of time-frequency representation which can decipher the minute changes in the nonlinear EEG signals. In this work, we have automatically classified normal, interictal and ictal EEG signals using the features derived from the ITD repr...

Full description

Saved in:
Bibliographic Details
Published in:International journal of neural systems 2013-10, Vol.23 (5), p.1350023-1-16
Main Authors: MARTIS, ROSHAN JOY, ACHARYA, U RAJENDRA, TAN, JEN HONG, PETZNICK, ANDREA, TONG, LOUIS, CHUA, CHUA KUANG, NG, EDDIE YIN KWEE
Format: Article
Language:English
Subjects:
Accuracy
Applied sciences
Biological and medical sciences
Classification
Convulsions & seizures
Decision theory. Utility theory
Decision Trees
Decomposition
Electrodiagnosis. Electric activity recording
Electroencephalography
Electroencephalography - methods
Entropy
Exact sciences and technology
Fractals
Headache. Facial pains. Syncopes. Epilepsia. Intracranial hypertension. Brain oedema. Cerebral palsy
Humans
Inference from stochastic processes
time series analysis
Investigative techniques, diagnostic techniques (general aspects)
Mathematics
Medical sciences
Nervous system
Nervous system (semeiology, syndromes)
Neurology
Nonlinear Dynamics
Nonlinearity
Operational research and scientific management
Operational research. Management science
Probability and statistics
Representations
Sciences and techniques of general use
Seizing
Seizures - diagnosis
Sensitivity and Specificity
Signal Processing, Computer-Assisted
Statistics
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:Intrinsic time-scale decomposition (ITD) is a new nonlinear method of time-frequency representation which can decipher the minute changes in the nonlinear EEG signals. In this work, we have automatically classified normal, interictal and ictal EEG signals using the features derived from the ITD representation. The energy, fractal dimension and sample entropy features computed on ITD representation coupled with decision tree classifier has yielded an average classification accuracy of 95.67%, sensitivity and specificity of 99% and 99.5%, respectively using 10-fold cross validation scheme. With application of the nonlinear ITD representation, along with conceptual advancement and improvement of the accuracy, the developed system is clinically ready for mass screening in resource constrained and emerging economy scenarios.
ISSN:0129-0657
1793-6462
DOI:10.1142/S0129065713500238