A Novel Automated Empirical Mode Decomposition (EMD) Based Method and Spectral Feature Extraction for Epilepsy EEG Signals Classification
The increasing incidence of epilepsy has led to the need for automatic systems that can provide accurate diagnoses in order to improve the life quality of people suffering from this neurological disorder. This paper proposes a method to automatically classify epilepsy types using EEG recordings from...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/9/1958 |
| _version_ | 1797602787072147456 |
|---|---|
| author | Mădălina-Giorgiana Murariu Florica-Ramona Dorobanțu Daniela Tărniceriu |
| author_facet | Mădălina-Giorgiana Murariu Florica-Ramona Dorobanțu Daniela Tărniceriu |
| author_sort | Mădălina-Giorgiana Murariu |
| collection | DOAJ |
| description | The increasing incidence of epilepsy has led to the need for automatic systems that can provide accurate diagnoses in order to improve the life quality of people suffering from this neurological disorder. This paper proposes a method to automatically classify epilepsy types using EEG recordings from two databases. This approach uses the spectral power density of intrinsic mode functions (IMFs) that are obtained through the empirical mode decomposition (EMD) of EEG signals. The spectral power density of IMFs has been applied as features for the classification of focal and non-focal, as well as of focal and generalized EEG signals. The data are then classified using K-nearest Neighbor (KNN) and Naïve Bayes (NB) classifiers. The focal and non-focal data were classified with high accuracy, with KNN and NB classifiers achieving a maximum classification rate of 99.90% and 99.80%, respectively. Focal and generalized epilepsy data were classified with high rates of accuracy during wakefulness and sleep stages, with KNN achieving a maximum rate of 99.49% and NB achieving 99.20%. This method shows significant improvements in the classification of EEG signals in epilepsy compared to previous studies. It could potentially aid clinical decisions for epilepsy patients. |
| first_indexed | 2024-03-11T04:21:25Z |
| format | Article |
| id | doaj.art-b0e11e16b1ad4e2fbc7d9075c580bc54 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-11T04:21:25Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-b0e11e16b1ad4e2fbc7d9075c580bc542023-11-17T22:46:47ZengMDPI AGElectronics2079-92922023-04-01129195810.3390/electronics12091958A Novel Automated Empirical Mode Decomposition (EMD) Based Method and Spectral Feature Extraction for Epilepsy EEG Signals ClassificationMădălina-Giorgiana Murariu0Florica-Ramona Dorobanțu1Daniela Tărniceriu2Department of Telecommunication and Information Technologies, Faculty of Electronics, Telecommunications and Information Technology, “Gheorghe Asachi” Technical University, Blvd. Carol I, No. 11 A, 700506 Iași, RomaniaDepartment of Medical Disciplines, Faculty of Medicine and Pharmacy, University of Oradea, 1 University Street, 410087 Oradea, RomaniaDepartment of Telecommunication and Information Technologies, Faculty of Electronics, Telecommunications and Information Technology, “Gheorghe Asachi” Technical University, Blvd. Carol I, No. 11 A, 700506 Iași, RomaniaThe increasing incidence of epilepsy has led to the need for automatic systems that can provide accurate diagnoses in order to improve the life quality of people suffering from this neurological disorder. This paper proposes a method to automatically classify epilepsy types using EEG recordings from two databases. This approach uses the spectral power density of intrinsic mode functions (IMFs) that are obtained through the empirical mode decomposition (EMD) of EEG signals. The spectral power density of IMFs has been applied as features for the classification of focal and non-focal, as well as of focal and generalized EEG signals. The data are then classified using K-nearest Neighbor (KNN) and Naïve Bayes (NB) classifiers. The focal and non-focal data were classified with high accuracy, with KNN and NB classifiers achieving a maximum classification rate of 99.90% and 99.80%, respectively. Focal and generalized epilepsy data were classified with high rates of accuracy during wakefulness and sleep stages, with KNN achieving a maximum rate of 99.49% and NB achieving 99.20%. This method shows significant improvements in the classification of EEG signals in epilepsy compared to previous studies. It could potentially aid clinical decisions for epilepsy patients.https://www.mdpi.com/2079-9292/12/9/1958epilepsyelectroencephalographyempirical mode decomposition methodEEG signalsfocal epilepsynon-focal epilepsy |
| spellingShingle | Mădălina-Giorgiana Murariu Florica-Ramona Dorobanțu Daniela Tărniceriu A Novel Automated Empirical Mode Decomposition (EMD) Based Method and Spectral Feature Extraction for Epilepsy EEG Signals Classification Electronics epilepsy electroencephalography empirical mode decomposition method EEG signals focal epilepsy non-focal epilepsy |
| title | A Novel Automated Empirical Mode Decomposition (EMD) Based Method and Spectral Feature Extraction for Epilepsy EEG Signals Classification |
| title_full | A Novel Automated Empirical Mode Decomposition (EMD) Based Method and Spectral Feature Extraction for Epilepsy EEG Signals Classification |
| title_fullStr | A Novel Automated Empirical Mode Decomposition (EMD) Based Method and Spectral Feature Extraction for Epilepsy EEG Signals Classification |
| title_full_unstemmed | A Novel Automated Empirical Mode Decomposition (EMD) Based Method and Spectral Feature Extraction for Epilepsy EEG Signals Classification |
| title_short | A Novel Automated Empirical Mode Decomposition (EMD) Based Method and Spectral Feature Extraction for Epilepsy EEG Signals Classification |
| title_sort | novel automated empirical mode decomposition emd based method and spectral feature extraction for epilepsy eeg signals classification |
| topic | epilepsy electroencephalography empirical mode decomposition method EEG signals focal epilepsy non-focal epilepsy |
| url | https://www.mdpi.com/2079-9292/12/9/1958 |
| work_keys_str_mv | AT madalinagiorgianamurariu anovelautomatedempiricalmodedecompositionemdbasedmethodandspectralfeatureextractionforepilepsyeegsignalsclassification AT floricaramonadorobantu anovelautomatedempiricalmodedecompositionemdbasedmethodandspectralfeatureextractionforepilepsyeegsignalsclassification AT danielatarniceriu anovelautomatedempiricalmodedecompositionemdbasedmethodandspectralfeatureextractionforepilepsyeegsignalsclassification AT madalinagiorgianamurariu novelautomatedempiricalmodedecompositionemdbasedmethodandspectralfeatureextractionforepilepsyeegsignalsclassification AT floricaramonadorobantu novelautomatedempiricalmodedecompositionemdbasedmethodandspectralfeatureextractionforepilepsyeegsignalsclassification AT danielatarniceriu novelautomatedempiricalmodedecompositionemdbasedmethodandspectralfeatureextractionforepilepsyeegsignalsclassification |