Epileptic seizure detection on EEG signals using machine learning techniques and advanced preprocessing methods.
Identifieur interne : 000595 ( Main/Exploration ); précédent : 000594; suivant : 000596Epileptic seizure detection on EEG signals using machine learning techniques and advanced preprocessing methods.
Auteurs : Chahira Mahjoub [Tunisie] ; Régine Le Bouquin Jeannès [France] ; Tarek Lajnef [Canada] ; Abdennaceur Kachouri [Tunisie]Source :
- Biomedizinische Technik. Biomedical engineering [ 1862-278X ] ; 2020.
Descripteurs français
- KwdFr :
- Algorithmes (MeSH), Analyse en ondelettes (MeSH), Apprentissage machine (MeSH), Bases de données factuelles (MeSH), Collecte de données (MeSH), Crises épileptiques (diagnostic), Humains (MeSH), Machine à vecteur de support (MeSH), Sensibilité et spécificité (MeSH), Électroencéphalographie (méthodes).
- MESH :
English descriptors
- KwdEn :
- MESH :
- diagnosis : Seizures.
- methods : Electroencephalography.
- Algorithms, Data Collection, Databases, Factual, Humans, Machine Learning, Sensitivity and Specificity, Support Vector Machine, Wavelet Analysis.
Abstract
Electroencephalography (EEG) is a common tool used for the detection of epileptic seizures. However, the visual analysis of long-term EEG recordings is characterized by its subjectivity, time-consuming procedure and its erroneous detection. Various epileptic seizure detection algorithms have been proposed to deal with such issues. In this study, a novel automatic seizure-detection approach is proposed. Three different strategies are suggested to the user whereby he/she could choose the appropriate one for a given classification problem. Indeed, the feature extraction step, including both linear and nonlinear measures, is performed either directly from the EEG signals, or from the derived sub-bands of tunable-Q wavelet transform (TQWT), or even from the intrinsic mode functions (IMFs) of multivariate empirical mode decomposition (MEMD). The classification procedure is executed using a support vector machine (SVM). The performance of the proposed method is evaluated through a publicly available database from which six binary classification cases are formulated to discriminate between healthy, seizure and non-seizure EEG signals. Our results show high performance in terms of accuracy (ACC), sensitivity (SEN) and specificity (SPE) compared to the state-of-the-art approaches. Thus, the proposed approach for automatic seizure detection can be considered as a valuable alternative to existing methods, able to alleviate the overload of visual analysis and accelerate the seizure detection.
DOI: 10.1515/bmt-2019-0001
PubMed: 31469648
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream PubMed, to step Corpus: 000225
- to stream PubMed, to step Curation: 000224
- to stream PubMed, to step Checkpoint: 000149
- to stream Main, to step Merge: 000595
- to stream Main, to step Curation: 000595
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Epileptic seizure detection on EEG signals using machine learning techniques and advanced preprocessing methods.</title>
<author><name sortKey="Mahjoub, Chahira" sort="Mahjoub, Chahira" uniqKey="Mahjoub C" first="Chahira" last="Mahjoub">Chahira Mahjoub</name>
<affiliation wicri:level="1"><nlm:affiliation>LETI-ENIS, University of Sfax, Street of Soukra, 3038 Sfax, Tunisia.</nlm:affiliation>
<country xml:lang="fr">Tunisie</country>
<wicri:regionArea>LETI-ENIS, University of Sfax, Street of Soukra, 3038 Sfax</wicri:regionArea>
<wicri:noRegion>3038 Sfax</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Le Bouquin Jeannes, Regine" sort="Le Bouquin Jeannes, Regine" uniqKey="Le Bouquin Jeannes R" first="Régine" last="Le Bouquin Jeannès">Régine Le Bouquin Jeannès</name>
<affiliation wicri:level="3"><nlm:affiliation>Univ Rennes, INSERM, LTSI-UMR 1099, F-35000 Rennes, France.</nlm:affiliation>
<country xml:lang="fr">France</country>
<wicri:regionArea>Univ Rennes, INSERM, LTSI-UMR 1099, F-35000 Rennes</wicri:regionArea>
<placeName><region type="region" nuts="2">Région Bretagne</region>
<settlement type="city">Rennes</settlement>
</placeName>
</affiliation>
<affiliation wicri:level="3"><nlm:affiliation>Univ Rennes, INSERM, CRIBs, F-35000 Rennes, France.</nlm:affiliation>
<country xml:lang="fr">France</country>
<wicri:regionArea>Univ Rennes, INSERM, CRIBs, F-35000 Rennes</wicri:regionArea>
<placeName><region type="region" nuts="2">Région Bretagne</region>
<settlement type="city">Rennes</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Lajnef, Tarek" sort="Lajnef, Tarek" uniqKey="Lajnef T" first="Tarek" last="Lajnef">Tarek Lajnef</name>
<affiliation wicri:level="1"><nlm:affiliation>Psychology Department, University of Montreal, Montreal, QC, Canada.</nlm:affiliation>
<country xml:lang="fr">Canada</country>
<wicri:regionArea>Psychology Department, University of Montreal, Montreal, QC</wicri:regionArea>
<wicri:noRegion>QC</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Kachouri, Abdennaceur" sort="Kachouri, Abdennaceur" uniqKey="Kachouri A" first="Abdennaceur" last="Kachouri">Abdennaceur Kachouri</name>
<affiliation wicri:level="1"><nlm:affiliation>LETI-ENIS, University of Sfax, Street of Soukra, 3038 Sfax, Tunisia.</nlm:affiliation>
<country xml:lang="fr">Tunisie</country>
<wicri:regionArea>LETI-ENIS, University of Sfax, Street of Soukra, 3038 Sfax</wicri:regionArea>
<wicri:noRegion>3038 Sfax</wicri:noRegion>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">PubMed</idno>
<date when="2020">2020</date>
<idno type="RBID">pubmed:31469648</idno>
<idno type="pmid">31469648</idno>
<idno type="doi">10.1515/bmt-2019-0001</idno>
<idno type="wicri:Area/PubMed/Corpus">000225</idno>
<idno type="wicri:explorRef" wicri:stream="PubMed" wicri:step="Corpus" wicri:corpus="PubMed">000225</idno>
<idno type="wicri:Area/PubMed/Curation">000224</idno>
<idno type="wicri:explorRef" wicri:stream="PubMed" wicri:step="Curation">000224</idno>
<idno type="wicri:Area/PubMed/Checkpoint">000149</idno>
<idno type="wicri:explorRef" wicri:stream="Checkpoint" wicri:step="PubMed">000149</idno>
<idno type="wicri:Area/Main/Merge">000595</idno>
<idno type="wicri:Area/Main/Curation">000595</idno>
<idno type="wicri:Area/Main/Exploration">000595</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Epileptic seizure detection on EEG signals using machine learning techniques and advanced preprocessing methods.</title>
<author><name sortKey="Mahjoub, Chahira" sort="Mahjoub, Chahira" uniqKey="Mahjoub C" first="Chahira" last="Mahjoub">Chahira Mahjoub</name>
<affiliation wicri:level="1"><nlm:affiliation>LETI-ENIS, University of Sfax, Street of Soukra, 3038 Sfax, Tunisia.</nlm:affiliation>
<country xml:lang="fr">Tunisie</country>
<wicri:regionArea>LETI-ENIS, University of Sfax, Street of Soukra, 3038 Sfax</wicri:regionArea>
<wicri:noRegion>3038 Sfax</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Le Bouquin Jeannes, Regine" sort="Le Bouquin Jeannes, Regine" uniqKey="Le Bouquin Jeannes R" first="Régine" last="Le Bouquin Jeannès">Régine Le Bouquin Jeannès</name>
<affiliation wicri:level="3"><nlm:affiliation>Univ Rennes, INSERM, LTSI-UMR 1099, F-35000 Rennes, France.</nlm:affiliation>
<country xml:lang="fr">France</country>
<wicri:regionArea>Univ Rennes, INSERM, LTSI-UMR 1099, F-35000 Rennes</wicri:regionArea>
<placeName><region type="region" nuts="2">Région Bretagne</region>
<settlement type="city">Rennes</settlement>
</placeName>
</affiliation>
<affiliation wicri:level="3"><nlm:affiliation>Univ Rennes, INSERM, CRIBs, F-35000 Rennes, France.</nlm:affiliation>
<country xml:lang="fr">France</country>
<wicri:regionArea>Univ Rennes, INSERM, CRIBs, F-35000 Rennes</wicri:regionArea>
<placeName><region type="region" nuts="2">Région Bretagne</region>
<settlement type="city">Rennes</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Lajnef, Tarek" sort="Lajnef, Tarek" uniqKey="Lajnef T" first="Tarek" last="Lajnef">Tarek Lajnef</name>
<affiliation wicri:level="1"><nlm:affiliation>Psychology Department, University of Montreal, Montreal, QC, Canada.</nlm:affiliation>
<country xml:lang="fr">Canada</country>
<wicri:regionArea>Psychology Department, University of Montreal, Montreal, QC</wicri:regionArea>
<wicri:noRegion>QC</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Kachouri, Abdennaceur" sort="Kachouri, Abdennaceur" uniqKey="Kachouri A" first="Abdennaceur" last="Kachouri">Abdennaceur Kachouri</name>
<affiliation wicri:level="1"><nlm:affiliation>LETI-ENIS, University of Sfax, Street of Soukra, 3038 Sfax, Tunisia.</nlm:affiliation>
<country xml:lang="fr">Tunisie</country>
<wicri:regionArea>LETI-ENIS, University of Sfax, Street of Soukra, 3038 Sfax</wicri:regionArea>
<wicri:noRegion>3038 Sfax</wicri:noRegion>
</affiliation>
</author>
</analytic>
<series><title level="j">Biomedizinische Technik. Biomedical engineering</title>
<idno type="eISSN">1862-278X</idno>
<imprint><date when="2020" type="published">2020</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Algorithms (MeSH)</term>
<term>Data Collection (MeSH)</term>
<term>Databases, Factual (MeSH)</term>
<term>Electroencephalography (methods)</term>
<term>Humans (MeSH)</term>
<term>Machine Learning (MeSH)</term>
<term>Seizures (diagnosis)</term>
<term>Sensitivity and Specificity (MeSH)</term>
<term>Support Vector Machine (MeSH)</term>
<term>Wavelet Analysis (MeSH)</term>
</keywords>
<keywords scheme="KwdFr" xml:lang="fr"><term>Algorithmes (MeSH)</term>
<term>Analyse en ondelettes (MeSH)</term>
<term>Apprentissage machine (MeSH)</term>
<term>Bases de données factuelles (MeSH)</term>
<term>Collecte de données (MeSH)</term>
<term>Crises épileptiques (diagnostic)</term>
<term>Humains (MeSH)</term>
<term>Machine à vecteur de support (MeSH)</term>
<term>Sensibilité et spécificité (MeSH)</term>
<term>Électroencéphalographie (méthodes)</term>
</keywords>
<keywords scheme="MESH" qualifier="diagnosis" xml:lang="en"><term>Seizures</term>
</keywords>
<keywords scheme="MESH" qualifier="diagnostic" xml:lang="fr"><term>Crises épileptiques</term>
</keywords>
<keywords scheme="MESH" qualifier="methods" xml:lang="en"><term>Electroencephalography</term>
</keywords>
<keywords scheme="MESH" qualifier="méthodes" xml:lang="fr"><term>Électroencéphalographie</term>
</keywords>
<keywords scheme="MESH" xml:lang="en"><term>Algorithms</term>
<term>Data Collection</term>
<term>Databases, Factual</term>
<term>Humans</term>
<term>Machine Learning</term>
<term>Sensitivity and Specificity</term>
<term>Support Vector Machine</term>
<term>Wavelet Analysis</term>
</keywords>
<keywords scheme="MESH" xml:lang="fr"><term>Algorithmes</term>
<term>Analyse en ondelettes</term>
<term>Apprentissage machine</term>
<term>Bases de données factuelles</term>
<term>Collecte de données</term>
<term>Humains</term>
<term>Machine à vecteur de support</term>
<term>Sensibilité et spécificité</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Electroencephalography (EEG) is a common tool used for the detection of epileptic seizures. However, the visual analysis of long-term EEG recordings is characterized by its subjectivity, time-consuming procedure and its erroneous detection. Various epileptic seizure detection algorithms have been proposed to deal with such issues. In this study, a novel automatic seizure-detection approach is proposed. Three different strategies are suggested to the user whereby he/she could choose the appropriate one for a given classification problem. Indeed, the feature extraction step, including both linear and nonlinear measures, is performed either directly from the EEG signals, or from the derived sub-bands of tunable-Q wavelet transform (TQWT), or even from the intrinsic mode functions (IMFs) of multivariate empirical mode decomposition (MEMD). The classification procedure is executed using a support vector machine (SVM). The performance of the proposed method is evaluated through a publicly available database from which six binary classification cases are formulated to discriminate between healthy, seizure and non-seizure EEG signals. Our results show high performance in terms of accuracy (ACC), sensitivity (SEN) and specificity (SPE) compared to the state-of-the-art approaches. Thus, the proposed approach for automatic seizure detection can be considered as a valuable alternative to existing methods, able to alleviate the overload of visual analysis and accelerate the seizure detection.</div>
</front>
</TEI>
<affiliations><list><country><li>Canada</li>
<li>France</li>
<li>Tunisie</li>
</country>
<region><li>Région Bretagne</li>
</region>
<settlement><li>Rennes</li>
</settlement>
</list>
<tree><country name="Tunisie"><noRegion><name sortKey="Mahjoub, Chahira" sort="Mahjoub, Chahira" uniqKey="Mahjoub C" first="Chahira" last="Mahjoub">Chahira Mahjoub</name>
</noRegion>
<name sortKey="Kachouri, Abdennaceur" sort="Kachouri, Abdennaceur" uniqKey="Kachouri A" first="Abdennaceur" last="Kachouri">Abdennaceur Kachouri</name>
</country>
<country name="France"><region name="Région Bretagne"><name sortKey="Le Bouquin Jeannes, Regine" sort="Le Bouquin Jeannes, Regine" uniqKey="Le Bouquin Jeannes R" first="Régine" last="Le Bouquin Jeannès">Régine Le Bouquin Jeannès</name>
</region>
<name sortKey="Le Bouquin Jeannes, Regine" sort="Le Bouquin Jeannes, Regine" uniqKey="Le Bouquin Jeannes R" first="Régine" last="Le Bouquin Jeannès">Régine Le Bouquin Jeannès</name>
</country>
<country name="Canada"><noRegion><name sortKey="Lajnef, Tarek" sort="Lajnef, Tarek" uniqKey="Lajnef T" first="Tarek" last="Lajnef">Tarek Lajnef</name>
</noRegion>
</country>
</tree>
</affiliations>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Sante/explor/MaghrebDataLibMedV2/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000595 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000595 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Sante |area= MaghrebDataLibMedV2 |flux= Main |étape= Exploration |type= RBID |clé= pubmed:31469648 |texte= Epileptic seizure detection on EEG signals using machine learning techniques and advanced preprocessing methods. }}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/Main/Exploration/RBID.i -Sk "pubmed:31469648" \ | HfdSelect -Kh $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd \ | NlmPubMed2Wicri -a MaghrebDataLibMedV2
This area was generated with Dilib version V0.6.38. |