Hostname: page-component-8448b6f56d-xtgtn Total loading time: 0 Render date: 2024-04-19T04:02:31.878Z Has data issue: false hasContentIssue false
  • English
  • Français

DETECTING K-COMPLEXES FOR SLEEP STAGE IDENTIFICATION USING NONSMOOTH OPTIMIZATION

Published online by Cambridge University Press:  20 March 2012

D. MOLONEY ,
N. SUKHORUKOVA ,
P. VAMPLEW ,
J. UGON ,
G. LI ,
G. BELIAKOV ,
C. PHILIPPE ,
H. AMIEL  and
A. UGON
D. MOLONEY
Affiliation:
University of Ballarat, P. O. Box 663, Ballarat, Victoria 3353, Australia (email: d.moloney@ballarat.edu.au, n.sukhorukova@ballarat.edu.au, p.vamplew@ballarat.edu.au, j.ugon@ballarat.edu.au)
N. SUKHORUKOVA*
Affiliation:
University of Ballarat, P. O. Box 663, Ballarat, Victoria 3353, Australia (email: d.moloney@ballarat.edu.au, n.sukhorukova@ballarat.edu.au, p.vamplew@ballarat.edu.au, j.ugon@ballarat.edu.au)
P. VAMPLEW
Affiliation:
University of Ballarat, P. O. Box 663, Ballarat, Victoria 3353, Australia (email: d.moloney@ballarat.edu.au, n.sukhorukova@ballarat.edu.au, p.vamplew@ballarat.edu.au, j.ugon@ballarat.edu.au)
J. UGON
Affiliation:
University of Ballarat, P. O. Box 663, Ballarat, Victoria 3353, Australia (email: d.moloney@ballarat.edu.au, n.sukhorukova@ballarat.edu.au, p.vamplew@ballarat.edu.au, j.ugon@ballarat.edu.au)
G. LI
Affiliation:
Deakin University, 221 Burwood Highway, Burwood, Victoria 3125, Australia (email: gang.li@deakin.edu.au, gleb.beliakov@deakin.edu.au)
G. BELIAKOV
Affiliation:
Deakin University, 221 Burwood Highway, Burwood, Victoria 3125, Australia (email: gang.li@deakin.edu.au, gleb.beliakov@deakin.edu.au)
C. PHILIPPE
Affiliation:
Hôpital Tenon, 4 rue de la Chine, 75970 Paris Cedex 20, France (email: carole.philippe@tnn.aphp.fr, amielhelene@gmail.com, adrien.ugon@tnn.aphp.fr)
H. AMIEL
Affiliation:
Hôpital Tenon, 4 rue de la Chine, 75970 Paris Cedex 20, France (email: carole.philippe@tnn.aphp.fr, amielhelene@gmail.com, adrien.ugon@tnn.aphp.fr)
A. UGON
Affiliation:
Hôpital Tenon, 4 rue de la Chine, 75970 Paris Cedex 20, France (email: carole.philippe@tnn.aphp.fr, amielhelene@gmail.com, adrien.ugon@tnn.aphp.fr)
*
✉For correspondence; e-mail: n.sukhorukova@ballarat.edu.au
Rights & Permissions [Opens in a new window]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.

The process of sleep stage identification is a labour-intensive task that involves the specialized interpretation of the polysomnographic signals captured from a patient’s overnight sleep session. Automating this task has proven to be challenging for data mining algorithms because of noise, complexity and the extreme size of data. In this paper we apply nonsmooth optimization to extract key features that lead to better accuracy. We develop a specific procedure for identifying K-complexes, a special type of brain wave crucial for distinguishing sleep stages. The procedure contains two steps. We first extract “easily classified” K-complexes, and then apply nonsmooth optimization methods to extract features from the remaining data and refine the results from the first step. Numerical experiments show that this procedure is efficient for detecting K-complexes. It is also found that most classification methods perform significantly better on the extracted features.

Keywords

K-complexesnonsmooth optimizationclassification

MSC classification

Secondary: 90C90: Applications of mathematical programming
Type
Research Article
Information
The ANZIAM Journal , Volume 52 , Issue 4 , April 2011 , pp. 319 - 332
Copyright
Copyright © Australian Mathematical Society 2012

References

[1]Bagirov, A., “A method for minimization of quasidifferentiable functions”, Optim. Methods Soft. 17 (2002) 31–60; doi:10.1080/10556780290027837.CrossRefGoogle Scholar
[2]Bagirov, A. and Rubinov, A., “Modified versions of the cutting angle method”, in: Convex analysis and global optimization, Volume 54 of Nonconvex Optimization and its Applications (eds Hadjisavvas, N. and Pardalos, P. M.), (Kluwer, Dordrecht, 2001) 245–268.CrossRefGoogle Scholar
[3]Bankman, I. N., Sigillito, V. G., Wise, R. A. and Smith, P. L., “Feature-based detection of the K-complex wave in the human electroencephalogram using neural networks”, IEEE Trans. Biomed. Eng. 39 (1992) 1305–1310; doi:10.1109/10.184707.CrossRefGoogle ScholarPubMed
[4]Beliakov, G., “Cutting angle method – a tool for constrained global optimization”, Optim. Methods Soft. 19 (2004) 137–151; doi:10.1080/10556780410001647177.CrossRefGoogle Scholar
[5]Beliakov, G. and Ugon, J., “Implementation of novel methods of global and nonsmooth optimization: GANSO programming library”, Optimization 56 (2007) 543–546; doi:10.1080/02331930701617429.CrossRefGoogle Scholar
[6]Carney, P. R., Berry, R. B. and Geyer (eds), J. D., Clinical sleep disorders (Lippincott Williams & Wilkins, Philadelphia, 2005).Google Scholar
[7]Frank, E. and Witten, I., Data mining: practical machine learning tools and techniques, 2nd edn (Morgan Kaufmann, Burlington, MA, 2005).Google Scholar
[8]Fuentealba, P., Timofeev, I., Bazhenov, M., Sejnowski, T. J. and Steriade, M., “Membrane bistability in thalamic reticular neurons during spindle oscillations”, J. Neurophysiology 93 (2005) 294–304; doi:10.1152/jn.00552.2004.CrossRefGoogle ScholarPubMed
[9]Iber, C., Ancoli-Israel, S., Chesson, A. and Quan, S., The AASM manual for the scoring of sleep and associated events: rules, technology and technical specifications (American Academy of Sleep Medicine, Westchester, IL, 2007).Google Scholar
[10]Kam, A., Cohen, A., Geva, A. B. and Tarasiuk, A., “Detection of K-complexes in Sleep EEG Using CD-HMM”, 26th Annual Int. Conf. of the IEEE EMBS 2 (2004) 33–36; doi:10.1109/IEMBS.2004.1403083.CrossRefGoogle Scholar
[11]Malinowska, U., Durka, P. J., Blinowska, K. J., Szelenberger, W. and Wakarow, A., “Micro- and Macrostructure of sleep EEG”, IEEE Eng. Med. Biol. Mag. 25 (2006) 26–31; doi:10.1109/MEMB.2006.1657784.CrossRefGoogle ScholarPubMed
[12]Mammadov, M. A. and Orsi, R., “H ∞ synthesis via a nonsmooth, nonconvex optimization approach”, Pac. J. Optim. 1 (2005) 405–420.Google Scholar
[13]Nürnberger, G., Approximation by spline functions (Springer, Berlin, 1989).CrossRefGoogle Scholar
[14]Rajeev, R. A. and Gotman, J., “Digital tools in polysomnography”, J. Clin. Neurophysiol. 19 (2002) 136–143.Google Scholar
[15]Rechtschaffen, A. and Kales (eds), A., A manual of standardized terminology, techniques, and scoring system for sleep stages of human subjects (US Government Printing Office, Washington, DC, 1968).Google Scholar
[16]Rubinov, A., Sukhorukova, N. and Ugon, J., “The choice of a similarity measure with respect to its sensitivity to outliers”, Dyn. Contin. Discrete Impuls. Syst. B 17 (2010) 709–721.Google Scholar
[17]Steriade, M., Wyzinski, P. and Oakson, G., “Activities in synaptic pathways between the motor cortex and ventrolateral thalamus underlying EEG spindle waves”, Int. J. Neurol. 8 (1971) 211–229.Google ScholarPubMed
[18]Tang, Z. and Ishii, N., “Detection of the K-complex using a new method of recognizing waveform based on the discrete wavelet transform”, IEICE Trans. Information Systems 78 (1995) 77–85.Google Scholar
[19] GANSO, http://guerin.ballarat.edu.au/ard/itms/CIAO/ganso/.Google Scholar
[20] Weka, http://www.cs.waikato.ac.nz/ml/weka/.Google Scholar
[21] Wikipedia, “Sleep spindle”, http://en.wikipedia.org/wiki/Sleep_spindle.Google Scholar