Automatic sleep staging: A computer assisted approach for optimal combination of features and polysomnographic channels

• Published in: Expert systems with applications Vol. 40; no. 17; pp. 7046 - 7059
• Main Authors: Khalighi, Sirvan, Sousa, Teresa, Pires, Gabriel, Nunes, Urbano
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier Ltd 01.12.2013; Elsevier
• Subjects: Applied sciences; Artificial intelligence; Automatic sleep staging; Biological and medical sciences; Channels; Computer science; control theory; systems; Data processing. List processing. Character string processing; EEC; Electrodiagnosis. Electric activity recording; Exact sciences and technology; Eye movements; Feature extraction; Features selection; Fundamental and applied biological sciences. Psychology; Invariants; Investigative techniques, diagnostic techniques (general aspects); Medical sciences; Memory organisation. Data processing; Nervous system; Patients; Pattern recognition. Digital image processing. Computational geometry; Polysomnographic signals; Sleep; Sleep dataset; Sleep. Vigilance; Software; Support vector machines; The maximum overlap discrete wavelet transform; Vertebrates: nervous system and sense organs; Wavelet transforms; Features selection; Sleep dataset; Automatic sleep staging; Polysomnographic signals; The maximum overlap discrete wavelet transform; Performance evaluation; Invariant; Histogram; Time frequency domain method; Expert; Electroencephalography; Overlap; Modeling; Eye movement; Vector support machine; Selection criterion; Electromyography; Hospital; Overlay; Pattern extraction; Frequency domain method; Pattern recognition; Discrete wavelet transforms; Polysomnography; Wake; Time domain method; Sleep; Wavelet transformation; Extreme value; Feature extraction; Automatic analysis

•A subject-independent automatic sleep staging method with application in sleep–wake detection and in multiclass sleep staging.•An extensive dataset with 40 polysomnographic (PSG) recording.•A time–frequency based feature extraction method using maximum overlap discrete wavelet transform (MODWT).•A...