scholarly journals On the implementation and improvement of automatic EEG spike detection algorithm

2015 ◽  
Vol 56 ◽  
Author(s):  
Andrius Vytautas Misiukas Misiūnas ◽  
Tadas Meškauskas ◽  
Algimantas Juozapavičius
Keyword(s):  
Parallel Computing ◽  
Brain Activity ◽  
Detection Algorithm ◽  
Personal Computers ◽  
Spike Detection ◽  
Morphological Filters ◽  
Computing Support

The algorithm of automatic EEG spike detection and its implementation is described in this article. The algorithm implemented is based on mathematical morphological filters which distinguishes background brain activity from EEG spikes. The implementation of the algorithm is system independent, it can be deployed on both personal computers and clusters with MPI parallel computing support.

Cluster-based spike detection algorithm adapts to interpatient and intrapatient variation in spike morphology

2012 ◽  
Vol 210 (2) ◽  
pp. 259-265 ◽  
Author(s):  
Antoine Nonclercq ◽  
Martine Foulon ◽  
Denis Verheulpen ◽  
Cathy De Cock ◽  
Marga Buzatu ◽  
...  
Keyword(s):  
Detection Algorithm ◽  
Spike Detection ◽  
Spike Morphology

scholarly journals EEG analysis – automatic spike detection

2012 ◽  
Vol 16 (4) ◽  
pp. 375-386 ◽  
Author(s):  
Algimantas Juozapavičius ◽  
Gytis Bacevičius ◽  
Dmitrijus Bugelskis ◽  
Rūta Samaitienė
Keyword(s):  
Data Mining ◽  
Visual Inspection ◽  
Automatic Extraction ◽  
Eeg Analysis ◽  
Spike Detection ◽  
Morphological Filters ◽  
Data Accessibility ◽  
Data Mining Algorithms ◽  
Using Data ◽  
Mining Algorithms

In the diagnosis and treatment of epilepsy, an electroencephalography (EEG) is one of the main tools. However visual inspection of EEG is very time consuming. Automatic extraction of important EEG features saves not only a lot of time for neurologist, but also enables a whole new level for EEG analysis, by using data mining methods. In this work we present and analyse methods to extract some of these features of EEG – drowsiness score and centrotemporal spikes. For spike detection, a method based on morphological filters is used. Also a database design is proposed in order to allow easy EEG analysis and provide data accessibility for data mining algorithms developed in the future.

Sign in / Sign up

Export Citation Format

Share Document