Automated sleep stage identification system based on time–frequency analysis of a single EEG channel and random forest classifier

• Published in: Computer methods and programs in biomedicine Vol. 108; no. 1; pp. 10 - 19
• Main Authors: Fraiwan, Luay, Lweesy, Khaldon, Khasawneh, Natheer, Wenz, Heinrich, Dickhaus, Hartmut
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier Ireland Ltd 01.10.2012; Elsevier
• Subjects: Accuracy; Applied sciences; Automated sleep stage identification; Automation; Biological and medical sciences; Channels; Choi–Williams distribution (CWD); Classifiers; Coefficients; Computer science; control theory; systems; Continuous wavelet transform (CWT); Data processing. List processing. Character string processing; Electrodiagnosis. Electric activity recording; Electroencephalography; Entropy; Exact sciences and technology; Forests; Fundamental and applied biological sciences. Psychology; Hilbert–Huang Transform (HHT); Humans; Information, signal and communications theory; Internal Medicine; Investigative techniques, diagnostic techniques (general aspects); Medical sciences; Memory organisation. Data processing; Nervous system; Other; Polysomnography; Random forest classifier; Signal and communications theory; Signal representation. Spectral analysis; Signal, noise; Sleep; Sleep. Vigilance; Software; Telecommunications and information theory; Time-frequency analysis; Vertebrates: nervous system and sense organs; Continuous wavelet transform (CWT); Time–frequency analysis; Choi–Williams distribution (CWD); Hilbert–Huang Transform (HHT); Random forest classifier; Automated sleep stage identification; Time-frequency analysis; Empirical mode decomposition; Sleep stage; Time frequency domain method; Electroencephalography; Entropy; Choi-Williams distribution (CWD); Hilbert transformation; Classification; Instantaneous frequency; Time analysis; Medical application; Pattern extraction; Choi Williams distribution; Pattern recognition; Polysomnography; Signal representation; Random decision forests; Hilbert-Huang Transform (HHT); Sleep; Wavelet transformation; Signal processing; Feature extraction; Signal analysis; Information theory
• ISSN: 0169-2607; 1872-7565; 1872-7565
• DOI: 10.1016/j.cmpb.2011.11.005

► A new method for automated sleep scoring is proposed. ► A new technique based on time–frequency analysis of EEG signal is proposed. ► Random forest classifier has successfully classified sleep stages. In this work, an efficient automated new approach for sleep stage identification based on the new standard of the American academy of sleep medicine (AASM) is presented. The propose approach employs time–frequency analysis and entropy measures for feature extraction from a single electroencephalograph (EEG) channel. Three time–frequency techniques were deployed for the analysis of the EEG signal: Choi–Williams distribution (CWD), continuous wavelet transform (CWT), and Hilbert–Huang Transform (HHT). Polysomnographic recordings from sixteen subjects were used in this study and features were extracted from the time–frequency representation of the EEG signal using Renyi's entropy. The classification of the extracted features was done using random forest classifier. The performance of the new approach was tested by evaluating the accuracy and the kappa coefficient for the three time–frequency distributions: CWD, CWT, and HHT. The CWT time–frequency distribution outperformed the other two distributions and showed excellent performance with an accuracy of 0.83 and a kappa coefficient of 0.76.