An automated detection of epileptic seizures EEG using CNN classifier based on feature fusion with high accuracy.
Convolutional neural networks
Epilepsy detection
Epileptic EEG signal classification
Feature selection
Random forest
Journal
BMC medical informatics and decision making
ISSN: 1472-6947
Titre abrégé: BMC Med Inform Decis Mak
Pays: England
ID NLM: 101088682
Informations de publication
Date de publication:
22 05 2023
22 05 2023
Historique:
received:
06
01
2023
accepted:
21
04
2023
medline:
24
5
2023
pubmed:
23
5
2023
entrez:
22
5
2023
Statut:
epublish
Résumé
Epilepsy is a neurological disorder that is usually detected by electroencephalogram (EEG) signals. Since manual examination of epilepsy seizures is a laborious and time-consuming process, lots of automatic epilepsy detection algorithms have been proposed. However, most of the available classification algorithms for epilepsy EEG signals adopted a single feature extraction, in turn to result in low classification accuracy. Although a small account of studies have carried out feature fusion, the computational efficiency is reduced due to too many features, because there are also some poor features that interfere with the classification results. In order to solve the above problems, an automatic recognition method of epilepsy EEG signals based on feature fusion and selection is proposed in this paper. Firstly, the Approximate Entropy (ApEn), Fuzzy Entropy (FuzzyEn), Sample Entropy (SampEn), and Standard Deviation (STD) mixed features of the subband obtained by the Discrete Wavelet Transform (DWT) decomposition of EEG signals are extracted. Secondly, the random forest algorithm is used for feature selection. Finally, the Convolutional Neural Network (CNN) is used to classify epilepsy EEG signals. The empirical evaluation of the presented algorithm is performed on the benchmark Bonn EEG datasets and New Delhi datasets. In the interictal and ictal classification tasks of Bonn datasets, the proposed model achieves an accuracy of 99.9%, a sensitivity of 100%, a precision of 99.81%, and a specificity of 99.8%. For the interictal-ictal case of New Delhi datasets, the proposed model achieves a classification accuracy of 100%, a sensitivity of 100%, a specificity of 100%, and a precision of 100%. The proposed model can effectively realize the high-precision automatic detection and classification of epilepsy EEG signals. This model can provide high-precision automatic detection capability for clinical epilepsy EEG detection. We hope to provide positive implications for the prediction of seizure EEG.
Sections du résumé
BACKGROUND
Epilepsy is a neurological disorder that is usually detected by electroencephalogram (EEG) signals. Since manual examination of epilepsy seizures is a laborious and time-consuming process, lots of automatic epilepsy detection algorithms have been proposed. However, most of the available classification algorithms for epilepsy EEG signals adopted a single feature extraction, in turn to result in low classification accuracy. Although a small account of studies have carried out feature fusion, the computational efficiency is reduced due to too many features, because there are also some poor features that interfere with the classification results.
METHODS
In order to solve the above problems, an automatic recognition method of epilepsy EEG signals based on feature fusion and selection is proposed in this paper. Firstly, the Approximate Entropy (ApEn), Fuzzy Entropy (FuzzyEn), Sample Entropy (SampEn), and Standard Deviation (STD) mixed features of the subband obtained by the Discrete Wavelet Transform (DWT) decomposition of EEG signals are extracted. Secondly, the random forest algorithm is used for feature selection. Finally, the Convolutional Neural Network (CNN) is used to classify epilepsy EEG signals.
RESULTS
The empirical evaluation of the presented algorithm is performed on the benchmark Bonn EEG datasets and New Delhi datasets. In the interictal and ictal classification tasks of Bonn datasets, the proposed model achieves an accuracy of 99.9%, a sensitivity of 100%, a precision of 99.81%, and a specificity of 99.8%. For the interictal-ictal case of New Delhi datasets, the proposed model achieves a classification accuracy of 100%, a sensitivity of 100%, a specificity of 100%, and a precision of 100%.
CONCLUSION
The proposed model can effectively realize the high-precision automatic detection and classification of epilepsy EEG signals. This model can provide high-precision automatic detection capability for clinical epilepsy EEG detection. We hope to provide positive implications for the prediction of seizure EEG.
Identifiants
pubmed: 37217878
doi: 10.1186/s12911-023-02180-w
pii: 10.1186/s12911-023-02180-w
pmc: PMC10201805
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
96Informations de copyright
© 2023. The Author(s).
Références
Diagnostics (Basel). 2021 Dec 29;12(1):
pubmed: 35054242
Front Hum Neurosci. 2019 Feb 21;13:52
pubmed: 30846934
BMC Med Inform Decis Mak. 2018 Dec 7;18(Suppl 5):111
pubmed: 30526571
Annu Int Conf IEEE Eng Med Biol Soc. 2021 Nov;2021:1082-1085
pubmed: 34891475
Australas Phys Eng Sci Med. 2018 Dec;41(4):1047-1055
pubmed: 30338494
IEEE Trans Neural Syst Rehabil Eng. 2022;30:957-966
pubmed: 35404819
Neurosurg Clin N Am. 2011 Oct;22(4):489-506, vi
pubmed: 21939848
IEEE Trans Biomed Eng. 2003 May;50(5):549-58
pubmed: 12769431
Cogn Neurodyn. 2017 Feb;11(1):51-66
pubmed: 28174612
Front Neurol. 2022 Jun 29;13:915385
pubmed: 35847218
Oncotarget. 2016 Jan 5;7(1):342-50
pubmed: 26586477
Front Physiol. 2020 Jun 25;11:607
pubmed: 32670082
Front Neurol. 2020 May 22;11:375
pubmed: 32528398
Australas Phys Eng Sci Med. 2018 Mar;41(1):81-94
pubmed: 29264792
J Healthc Eng. 2022 Sep 6;2022:7654666
pubmed: 36110984
BMC Med Inform Decis Mak. 2021 Jul 30;21(Suppl 2):100
pubmed: 34330248
IEEE Trans Neural Syst Rehabil Eng. 2017 Dec;25(12):2270-2284
pubmed: 28880184
Methods Enzymol. 2004;384:172-84
pubmed: 15081687
Comput Biol Med. 2021 Jun;133:104434
pubmed: 33946023
Phys Rev E Stat Nonlin Soft Matter Phys. 2001 Dec;64(6 Pt 1):061907
pubmed: 11736210
Proc Natl Acad Sci U S A. 1991 Mar 15;88(6):2297-301
pubmed: 11607165
Annu Int Conf IEEE Eng Med Biol Soc. 2007;2007:1953-6
pubmed: 18002366
IEEE Trans Neural Syst Rehabil Eng. 2016 Jan;24(1):28-35
pubmed: 26068546
IEEE Trans Biomed Circuits Syst. 2019 Oct;13(5):804-813
pubmed: 31331897
Technol Health Care. 2018;26(S1):337-346
pubmed: 29710759