Multivariate Bayesian classification of epilepsy EEG signals
- Resource Type
- Conference
- Authors
- Quintero-Rincon, Antonio; Prendes, Jorge; Pereyra, Marcelo; Batatia, Hadj; Risk, Marcelo
- Source
- 2016 IEEE 12th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP) Image, Video, and Multidimensional Signal Processing Workshop (IVMSP), 2016 IEEE 12th. :1-5 Jul, 2016
- Subject
- Computing and Processing
Signal Processing and Analysis
Electroencephalography
Bayes methods
Two dimensional displays
Epilepsy
Gaussian distribution
Sensitivity
Brain modeling
Bayesian classifiers
Multilevel 2D wavelet
Generalized Gaussian distribution
EEG
- Language
The classification of epileptic seizure events in EEG signals is an important problem in biomedical engineering. In this paper we propose a Bayesian classification method for multivariate EEG signals. The method is based on a multilevel 2D wavelet decomposition that captures the distribution of energy across the different brain rhythms and regions, coupled with a generalised Gaussian statistical representation and a multivariate Bayesian classification scheme. The proposed approach is demonstrated on a challenging paediatric dataset containing both epileptic events and normal brain function signals, where it outperforms a state-of-the-art method both in terms of classification sensitivity and specificity.