Testing for nonlinearity in time series: the method of surrogate data
Conference proceedings on Interpretation of time series from nonlinear mechanical systems
Nonlinear time series analysis
Nonlinear time series analysis
Journal of Medical Systems
Automatic seizure detection based on time-frequency analysis and artificial neural networks
Computational Intelligence and Neuroscience - Regular issue
Epileptic seizure detection in EEGs using time-frequency analysis
IEEE Transactions on Information Technology in Biomedicine - Special section on computational intelligence in medical systems
Entropies based detection of epileptic seizures with artificial neural network classifiers
Expert Systems with Applications: An International Journal
Mining Local Correlation Patterns in Sets of Sequences
DS '09 Proceedings of the 12th International Conference on Discovery Science
Evolving simple feed-forward and recurrent ANNs for signal classification: a comparison
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Application of Higher Order Spectra to Identify Epileptic EEG
Journal of Medical Systems
Expert Systems with Applications: An International Journal
Time-frequency distributions in the classification of epilepsy from EEG signals
Expert Systems with Applications: An International Journal
Classification of Epilepsy Using High-Order Spectra Features and Principle Component Analysis
Journal of Medical Systems
Automated EEG analysis of epilepsy: A review
Knowledge-Based Systems
| Hi-index | 0.00 |
The Electroencephalogram (EEG) is a representative signal containing information about the condition of the brain. The shape of the wave may contain useful information about the state of the brain. However, the human observer cannot directly monitor these subtle details. Besides, since bio-signals are highly subjective, the symptoms may appear at random in the time scale. Therefore, the EEG signal parameters, extracted and analyzed using computers, are highly useful in diagnostics. Chaotic measures like correlation dimension (CD), largest Lyapunov exponent (LLE), Hurst exponent (H) and entropy are used to characterize the signal. Results indicate that these nonlinear measures are good discriminators of normal and epileptic EEG signals. These measures distinguish epileptic EEG and alcoholic from normal EEG with an accuracy of more than 90%. The dynamical behavior is less random for alcoholic and epileptic compared to normal. This indicates less of information processing in the brain due to the hyper-synchronization of the EEG. Hence, the application of nonlinear time series analysis to EEG signals offers insight into the dynamical nature and variability of the brain signals. As a pre-analysis step, the EEG data is tested for nonlinearity using surrogate data analysis and the results exhibited a significant difference in the correlation dimension measure of the actual data and the surrogate data.