Classification of Sleep Stages Using Multi-wavelet Time Frequency Entropy and LDA

Summary

Background: The process of automatic sleep stage scoring consists of two major parts: feature extraction and classification. Features are normally extracted from the polysomno-graphic recordings, mainly electroencephalograph (EEG) signals. The EEG is considered a non-stationary signal which increases the complexity of the detection of different waves in it.

Objectives: This work presents a new technique for automatic sleep stage scoring based on employing continuous wavelet transform (CWT) and linear discriminant analysis (LDA) using different mother wavelets to detect different waves embedded in the EEG signal.

Methods: The use of different mother wave-lets increases the ability to detect waves in the EEG signal. The extracted features were formed based on CWT time frequency entropy using three mother wavelets, and the classification was performed using the linear discriminant analysis. Thirty-two data sets from the MIT-BIH database were used to evaluate the performance of the proposed method.

Results: Features of a single EEG signal were extracted successfully based on the time frequency entropy using the continuous wavelet transform with three mother wavelets. The proposed method has shown to outperform the classification based on a CWT using a single mother wavelet. The accuracy was found to be 0.84, while the kappa coefficient was 0.78.

Conclusions: This work has shown that wavelet time frequency entropy provides a powerful tool for feature extraction for the non-stationary EEG signal; the accuracy of the classification procedure improved when using multiple wavelets compared to the use of single wavelet time frequency entropy.

Keywords

Sleep stage scoring - multi-wavelets - time frequency entropy - linear discriminant analysis

• References

• 1 Šušmáková K.. Human Sleep. Measurement Science Review 2004; 4–2, Section 2: 59-74.
• 2 Rechtschaffen A, Kales A. A manual of standardized terminology, techniques and scoring system for sleep stages of human subjects. Public Health Service 1968. U. S. Government Printing Office; Washington DC.:
• 3 Penzel T, Hirshkowitz M, Harsh J, Chervin R, Butkov N, Kryger M, Malow B, Vitiello M, Silber M, Kushida C, Chesson A. Digital analysis and technical specifications. Journal of Clinical Sleep Medicine 2007; 3 (02) 109-120.
• 4 Hae-Jeong P, Jung-Su O, Do-Un J, Kwang-Suk P. Automated sleep stage scoring using hybrid rule and case-based reasoning. Computers and Biomedical Research 2000; 33: 330-349.
• 5 Kubat M, Pfurtscheller G, Flotzinger D. AI-based approach to automatic sleep classification. Biological Cybernetics 1994; 70 (05) 443-448.
• 6 Shimada T, Shiina T, Saito Y. Sleep stage diagnosis system with neural network analysis. Engineering in Medicine and Biology Society 1998; 4 (29) 2074-2047.
• 7 Wang B, Xingyu W, Junzhong Z, Fusae K, Masatoshi N. Automatic determination of sleep stage through bio-neurological signals contaminated with artifacts by conditional probability of a knowledge base. Artif Life Robotics 2008; 12: 270-275.
• 8 Fell J, Röschke J, Mann K, Schäffner C. Discrimination of sleep stages: a comparison between spectral and nonlinear EEG measures. Electroencephalography and Clinical Neurophysiology 1996; 98 (05) 401-410.
• 9 Zhouyan F, Fei G. Power spectral analysis of recovery sleep of sleep deprivation and hypnotic drug induced sleep. Proceedings of the 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference, Shanghai, China 2005 pp 1-4.
• 10 Agarwal R, Gotman J. Computer-assisted sleep staging. IEEE Transactions on Biomedical Engineering 2001; 48 (12) 1412-1423.
• 11 Shimada T, Shiina T. Autodetection of characteristics of sleep EEG with integration of multichannel information by neural networks and fuzzy rules. Systems and Computers in Japan 1999; 30 (04) 1-10.
• 12 Pinero P, Garcia P, Arco L, Alvarezc A, Garc M, Bonal R. Sleep stage classification using fuzzy sets and machine learning techniques. Neurocomputing 2004; 58: 1137-1143.
• 13 Jansen B, Hasman A, Lenten R. Piece-wise EEG analysis: An objective evaluation. International Journal of Bio-Medical Computing 1981; 12 (01) 17-27.
• 14 Bodenstein G, Praetorius H. Feature extraction from the EEG by adaptive segmentation. Proc IEEE 1977; 65: 642-653.
• 15 Robert C, Guilpin C, Limoge A. Review of neural network applications in sleep research. Journal of Neuroscience Methods 1998; 79: 187-193.
• 16 Schwab K, Eiselt M, Schelenz C, Witte H. Time-variant Parametric Estimation of Transient Quadratic Phase Couplings during Electroencephalographic Burst Activity. Methods Inf Med 2005; 44 (03) 374-383.
• 17 Wei-Yen H, Chou-Ching L, Min-Shaung J, YungNein S. Wavelet-based fractal features with active segment selection: Application to single-trial EEG data. Journal of Neuroscience Methods 2007; 163: 145-160.
• 18 Bang-hua Y, Guo-zheng Y, Ting W, Rong-guo Y. Subject-based feature extraction using fuzzy wave-let packet in brain-computer interfaces. Signal Processing 2007; 87: 1569-1574.
• 19 Bang-hua Y, Guo-zheng Y, Rong-guo Y, Ting W. Feature extraction for EEG-based brain-computer interfaces by wavelet packet best basis decomposition. Journal of Neural Engineering 2006; 3: 251-256.
• 20 Walnut D. Wavelet Analysis. Birkhauser: 2002. ISBN 0-8176-3962-4.
• 21 Krzanowski WJ. Principles of Multivariate Analysis. Oxford University Press; 1988
• 22 Sing TZE Bow.. Pattern Recognition and Image Processing. 2nd edition. Basel, Switzerland: Marcel Dekker; 2002
• 23 PhysioNet 2009.. Research Resource for Complex Physiologic Signals. Available online at: http://www.physionet.org.
• 24 Orfanidis J. Introduction to Signal Processing. Englewood Cliffs, NJ: Prentice-Hall; 1996
• 25 Subasi A, Ercelebi E. Classification of EEG signals using neural network and logistic regression. Computer Methods and Programs in Biomedicine 2005; 78: 87-99.
• 26 Sim J, Wrigth C. The Kappa statistics in reliability studies: use, interpretation, and sample size requirements. Physical Therapy 2005; 85 (03) 257-268.
• 27 Cohen J. A coefficient of agreement for nominal scales. Education and Psychological Measurements 1960; 20: 37-46.
• 28 Hanaoka M, Kobayashi M, Yamazaki H. Automatic sleep stage scoring based on waveform recognition method and decision tree. Systems and Computers in Japan 2002; 33 (11) 2672-2683.
• 29 Tagluk M, Sezgin N, Akin M. Estimation of sleep stages by an artificial neural network employing EEG, EMG and EOG. Journal of Medical Systems 2009. Published online April 2009
• 30 Park H, Oh J, Jeong D, Park S. Automated sleep stage scoring using hybrid rule and cased based reasoning. Computers and Biomedical Research 2000; 33: 330-349.
• 31 Anderer P, Gruber G, Parapatics S, Woertz M, Miazhynskaia T, Klösch G, Saletu B, Zeitlhofer J, Barbanoj M, Danker-Hopfe H, Kemp B, Penzel T, Grözinger M, Kunz D, Rappelsberger P, Schlögl A, Dorffne G. An E-Health solution for automatic sleep classification according to Rechtschaffen and Kales: validation study of the Somnolyzer 24 × 7 utilizing the Siesta database. Neuropsychobiology 2005; 51: 115-133.