AUTOMATIC EEG CLASSIFICATION USING DENSITY BASED ALGORITHMS DBSCAN AND DENCLUE
Electroencephalograph (EEG) is a commonly used method in neurological practice. Automatic classifiers (algorithms) highlight signal sections with interesting activity and assist an expert with record scoring. Algorithm K-means is one of the most commonly used methods for EEG inspection. In this pape...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
CTU Central Library
2019-11-01
|
| Series: | Acta Polytechnica |
| Subjects: | |
| Online Access: | https://ojs.cvut.cz/ojs/index.php/ap/article/view/5377 |
| _version_ | 1819160756224000000 |
|---|---|
| author | Marek Piorecký Jan Štrobl Vladimír Krajča |
| author_facet | Marek Piorecký Jan Štrobl Vladimír Krajča |
| author_sort | Marek Piorecký |
| collection | DOAJ |
| description | Electroencephalograph (EEG) is a commonly used method in neurological practice. Automatic classifiers (algorithms) highlight signal sections with interesting activity and assist an expert with record scoring. Algorithm K-means is one of the most commonly used methods for EEG inspection. In this paper, we propose/apply a method based on density-oriented algorithms DBSCAN and DENCLUE. DBSCAN and DENCLUE separate the nested clusters against K-means. All three algorithms were validated on a testing dataset and after that adapted for a real EEG records classification. 24 dimensions EEG feature space were classified into 5 classes (physiological, epileptic, EOG, electrode, and EMG artefact). Modified DBSCAN and DENCLUE create more than two homogeneous classes of the epileptic EEG data. The results offer an opportunity for the EEG scoring in clinical practice. The big advantage of the proposed algorithms is the high homogeneity of the epileptic class. |
| first_indexed | 2024-12-22T17:01:30Z |
| format | Article |
| id | doaj.art-71376f415dfc4c7d9fbe271140719cb1 |
| institution | Directory Open Access Journal |
| issn | 1210-2709 1805-2363 |
| language | English |
| last_indexed | 2024-12-22T17:01:30Z |
| publishDate | 2019-11-01 |
| publisher | CTU Central Library |
| record_format | Article |
| series | Acta Polytechnica |
| spelling | doaj.art-71376f415dfc4c7d9fbe271140719cb12022-12-21T18:19:19ZengCTU Central LibraryActa Polytechnica1210-27091805-23632019-11-0159549850910.14311/AP.2019.59.04984717AUTOMATIC EEG CLASSIFICATION USING DENSITY BASED ALGORITHMS DBSCAN AND DENCLUEMarek Piorecký0Jan Štrobl1Vladimír Krajča2Czech Technical University in Prague, Faculty of Biomedical Engineering, National Institute of Mental HealthCzech Technical University in Prague, Faculty of Biomedical Engineering, National Institute of Mental HealthCzech Technical University in Prague, Faculty of Biomedical Engineering, National Institute of Mental HealthElectroencephalograph (EEG) is a commonly used method in neurological practice. Automatic classifiers (algorithms) highlight signal sections with interesting activity and assist an expert with record scoring. Algorithm K-means is one of the most commonly used methods for EEG inspection. In this paper, we propose/apply a method based on density-oriented algorithms DBSCAN and DENCLUE. DBSCAN and DENCLUE separate the nested clusters against K-means. All three algorithms were validated on a testing dataset and after that adapted for a real EEG records classification. 24 dimensions EEG feature space were classified into 5 classes (physiological, epileptic, EOG, electrode, and EMG artefact). Modified DBSCAN and DENCLUE create more than two homogeneous classes of the epileptic EEG data. The results offer an opportunity for the EEG scoring in clinical practice. The big advantage of the proposed algorithms is the high homogeneity of the epileptic class.https://ojs.cvut.cz/ojs/index.php/ap/article/view/5377eeg, dbscan, denclue, automatic classification, epilepsy. |
| spellingShingle | Marek Piorecký Jan Štrobl Vladimír Krajča AUTOMATIC EEG CLASSIFICATION USING DENSITY BASED ALGORITHMS DBSCAN AND DENCLUE Acta Polytechnica eeg, dbscan, denclue, automatic classification, epilepsy. |
| title | AUTOMATIC EEG CLASSIFICATION USING DENSITY BASED ALGORITHMS DBSCAN AND DENCLUE |
| title_full | AUTOMATIC EEG CLASSIFICATION USING DENSITY BASED ALGORITHMS DBSCAN AND DENCLUE |
| title_fullStr | AUTOMATIC EEG CLASSIFICATION USING DENSITY BASED ALGORITHMS DBSCAN AND DENCLUE |
| title_full_unstemmed | AUTOMATIC EEG CLASSIFICATION USING DENSITY BASED ALGORITHMS DBSCAN AND DENCLUE |
| title_short | AUTOMATIC EEG CLASSIFICATION USING DENSITY BASED ALGORITHMS DBSCAN AND DENCLUE |
| title_sort | automatic eeg classification using density based algorithms dbscan and denclue |
| topic | eeg, dbscan, denclue, automatic classification, epilepsy. |
| url | https://ojs.cvut.cz/ojs/index.php/ap/article/view/5377 |
| work_keys_str_mv | AT marekpiorecky automaticeegclassificationusingdensitybasedalgorithmsdbscananddenclue AT janstrobl automaticeegclassificationusingdensitybasedalgorithmsdbscananddenclue AT vladimirkrajca automaticeegclassificationusingdensitybasedalgorithmsdbscananddenclue |