A study on feature selection using multi-domain feature extraction for automated k-complex detection.
detection
electroencephalography (EEG)
feature selection
k-complex
multi-domain features
Journal
Frontiers in neuroscience
ISSN: 1662-4548
Titre abrégé: Front Neurosci
Pays: Switzerland
ID NLM: 101478481
Informations de publication
Date de publication:
2023
2023
Historique:
received:
18
05
2023
accepted:
21
08
2023
medline:
25
9
2023
pubmed:
25
9
2023
entrez:
25
9
2023
Statut:
epublish
Résumé
K-complex detection plays a significant role in the field of sleep research. However, manual annotation for electroencephalography (EEG) recordings by visual inspection from experts is time-consuming and subjective. Therefore, there is a necessity to implement automatic detection methods based on classical machine learning algorithms. However, due to the complexity of EEG signal, current feature extraction methods always produce low relevance to k-complex detection, which leads to a great performance loss for the detection. Hence, finding compact yet effective integrated feature vectors becomes a crucially core task in k-complex detection. In this paper, we first extract multi-domain features based on time, spectral analysis, and chaotic theory. Those features are extracted from a 0.5-s EEG segment, which is obtained using the sliding window technique. As a result, a vector containing twenty-two features is obtained to represent each segment. Next, we explore several feature selection methods and compare their performance in detecting k-complex. Based on the analysis of the selected features, we identify compact features which are fewer than twenty-two features and deemed as relevant and proceeded to the next step. Additionally, three classical classifiers are employed to evaluate the performance of the feature selection models. The results demonstrate that combining different features significantly improved the k-complex detection performance. The best performance is achieved by applying the feature selection method, which results in an accuracy of 93.03% The proposed method in this study can serve as an efficient tool for the automatic detection of k-complex, which is useful for neurologists or doctors in the diagnosis of sleep research.
Sections du résumé
Background
UNASSIGNED
K-complex detection plays a significant role in the field of sleep research. However, manual annotation for electroencephalography (EEG) recordings by visual inspection from experts is time-consuming and subjective. Therefore, there is a necessity to implement automatic detection methods based on classical machine learning algorithms. However, due to the complexity of EEG signal, current feature extraction methods always produce low relevance to k-complex detection, which leads to a great performance loss for the detection. Hence, finding compact yet effective integrated feature vectors becomes a crucially core task in k-complex detection.
Method
UNASSIGNED
In this paper, we first extract multi-domain features based on time, spectral analysis, and chaotic theory. Those features are extracted from a 0.5-s EEG segment, which is obtained using the sliding window technique. As a result, a vector containing twenty-two features is obtained to represent each segment. Next, we explore several feature selection methods and compare their performance in detecting k-complex. Based on the analysis of the selected features, we identify compact features which are fewer than twenty-two features and deemed as relevant and proceeded to the next step. Additionally, three classical classifiers are employed to evaluate the performance of the feature selection models.
Results
UNASSIGNED
The results demonstrate that combining different features significantly improved the k-complex detection performance. The best performance is achieved by applying the feature selection method, which results in an accuracy of 93.03%
Conclusion
UNASSIGNED
The proposed method in this study can serve as an efficient tool for the automatic detection of k-complex, which is useful for neurologists or doctors in the diagnosis of sleep research.
Identifiants
pubmed: 37746152
doi: 10.3389/fnins.2023.1224784
pmc: PMC10514364
doi:
Types de publication
Journal Article
Langues
eng
Pagination
1224784Informations de copyright
Copyright © 2023 Li, Dong, Song, Bai, Li and Karray.
Déclaration de conflit d'intérêts
The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Références
Annu Int Conf IEEE Eng Med Biol Soc. 2013;2013:5801-4
pubmed: 24111057
Sci Rep. 2022 Jul 27;12(1):12799
pubmed: 35896616
Neurosci Res. 2021 Nov;172:26-40
pubmed: 33965451
Annu Int Conf IEEE Eng Med Biol Soc. 2010;2010:4658-61
pubmed: 21096240
Comput Methods Programs Biomed. 2016 Nov;136:65-77
pubmed: 27686704
J Neurosci Methods. 2022 Jan 15;366:109421
pubmed: 34822945
Sensors (Basel). 2021 Oct 30;21(21):
pubmed: 34770537
Front Neurosci. 2023 Mar 14;17:1108059
pubmed: 36998730
J Neurosci Methods. 2015 Aug 15;251:37-46
pubmed: 25956566
J Neurosci Methods. 2016 Sep 15;271:107-18
pubmed: 27456762
Neuroimage. 2020 Jun;213:116748
pubmed: 32194281
Neurosci Res. 2023 Mar;188:51-67
pubmed: 36152918
Neuroscience. 2019 Dec 1;422:119-133
pubmed: 31682947
BMC Med Inform Decis Mak. 2022 Nov 17;22(1):297
pubmed: 36397034
Annu Int Conf IEEE Eng Med Biol Soc. 2014;2014:5450-3
pubmed: 25571227
Comput Math Methods Med. 2016;2016:6450126
pubmed: 27516806
Front Neuroinform. 2019 Jun 28;13:45
pubmed: 31316365
Front Hum Neurosci. 2015 Jul 28;9:414
pubmed: 26283943