论文信息 - A Versatile Approach to Epilepsy Classification Using Approximate Entropy as Post Classifier

A Versatile Approach to Epilepsy Classification Using Approximate Entropy as Post Classifier

Abnormal transient behaviour of neurons in the cortical regions of the brain leads to a seizure which characterizes epilepsy. The physical and mental activity of the patient is totally dampened with this epileptic seizure. To detect such seizures, Electroencephalography (EEG) signals is used and it aids greatly to the clinical experts and it is used as an important tool for the analysis of brain disorders, especially epilepsy. This paper shows that Linear Graph Embedding (LGE) and Singular Value Decomposition (SVD) are as dimensionality reduction techniques followed by the usage of Approximate Entropy (ApEn) as Post Classifiers for the Classification of Epilepsy Risk Levels from EEG signals. The benchmark parameters assumed here are Performance Index (PI), Quality Values (QV), Specificity, Sensitivity, Time Delay and Accuracy.

Harikumar Rajaguru | Sunil Kumar Prabhakar

[1] Stiliyan Kalitzin,et al. Dynamical diseases of brain systems: different routes to epileptic seizures , 2003, IEEE Transactions on Biomedical Engineering.

[2] A. Liu,et al. Detection of neonatal seizures through computerized EEG analysis. , 1992, Electroencephalography and clinical neurophysiology.

[3] R. Harikumar,et al. Dimensionality Reduction with Linear Graph Embedding Technique for Electroencephalography Signals of an Epileptic Patient , 2015 .

[4] Daniel Rivero,et al. Epileptic seizure detection using multiwavelet transform based approximate entropy and artificial neural networks , 2010, Journal of Neuroscience Methods.