Automatic Classification of EEG graphoelements (workshop)
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21460%2F14%3A00222920" target="_blank" >RIV/68407700:21460/14:00222920 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Automatic Classification of EEG graphoelements (workshop)
Original language description
1. Motivation, why and which types of EEG graphoelements to classify automatically 2. Discriminative features extraction a. Multichannel adaptive segmentation of non-stationary signals b. Heuristic features extraction based on physician's point of view c. Extraction, selection, reduction and features standardization d. Application of PCA - Principal Component Analysis and ICA- Independent Component Analysis (artefacts rejection) 3. Supervised and non-supervised learning classical and fuzzy. a. Statistical pattern recognition, k-NN, k-means b. Artificial neural networks, multilayer perceptron c. Fuzzy sets for improving the homogeneity classes of EEG segments (fuzzy c-means, fuzzy k-NN) 4. Semi-automatic extraction of prototypes from original EEG recordings, pre-processing by cluster analysis in the learning phase (prototypes gathering), involving of expert into the process of etalons extraction 5. Graphic visualization of results a. Color identification of significant graphoelements b.
Czech name
—
Czech description
—
Classification
Type
O - Miscellaneous
CEP classification
JC - Computer hardware and software
OECD FORD branch
—
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2014
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů