Skip to main content

Advertisement

Log in

Detection of microsleep states from the EEG: a comparison of feature reduction methods

  • Original Article
  • Published:
Medical & Biological Engineering & Computing Aims and scope Submit manuscript

Abstract

Microsleeps are brief lapses in consciousness with complete suspension of performance. They are the cause of fatal accidents in many transport sectors requiring sustained attention, especially driving. A microsleep-warning device, using wireless EEG electrodes, could be used to rouse a user from an imminent microsleep. High-dimensional datasets, especially in EEG-based classification, present challenges as there are often a large number of potentially useful features for detecting the phenomenon of interest. Thus, it is often important to reduce the dimension of the original data prior to training the classifier. In this study, linear dimensionality reduction methods—principal component analysis (PCA) and probabilistic PCA (PPCA)—were compared with eight non-linear dimensionality reduction methods (kernel PCA, classical multi-dimensional scaling, isometric mapping, nearest neighbour estimation, stochastic neighbourhood embedding, autoencoder, stochastic proximity embedding, and Laplacian eigenmaps) on previously collected behavioural and EEG data from eight healthy non-sleep-deprived volunteers performing a 1D-visuomotor tracking task for 1 h. The effectiveness of the feature reduction algorithms was evaluated by visual inspection of class separation on 3D scatterplots, by trustworthiness scores, and by microsleep detection performance on a stacked-generalisation-based linear discriminant analysis (LDA) system estimating the microsleep/responsive state at 1 Hz based on the reduced features. On trustworthiness, PPCA outperformed PCA, but PCA outperformed all of the non-linear techniques. The trustworthiness score for each feature reduction method also correlated strongly with microsleep-state detection performance, providing strong validation of the ability of trustworthiness to estimate the relative effectiveness of feature reduction approaches, in terms of predicting performance, and ability to do so independently of the gold standard.

Proposed microsleep detection system.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

References

  1. Peiris MTR, Jones RD, Davidson PR, Carroll GJ, Bones PJ (2006) Frequent lapses of responsiveness during an extended visuomotor tracking task in non-sleep-deprived subjects. J Sleep Res 15:291–300

    Article  PubMed  Google Scholar 

  2. Innes CRH, Poudel GR, Jones RD (2013) Efficient and regular patterns of nighttime sleep are related to increased vulnerability to microsleeps following a single night of sleep restriction. Chronobiol Int 30:1187–1196

    Article  PubMed  Google Scholar 

  3. Poudel GR, Innes CRH, Bones PJ, Watts R, Jones RD (2014) Losing the struggle to stay awake: divergent thalamic and cortical activity during microsleeps. Hum Brain Mapp 35:257–269

    Article  PubMed  Google Scholar 

  4. Herrmann US, Hess CW, Guggisberg AG, Roth C, Gugger M, Mathis J (2010) Sleepiness is not always perceived before falling asleep in healthy, sleep-deprived subjects. Sleep Med 11:747–751

    Article  PubMed  Google Scholar 

  5. Akerstedt T (2000) Consensus statement: fatigue and accidents in transport operations. J Sleep Res 9:395

    Article  CAS  PubMed  Google Scholar 

  6. Dingus TA, Klauer SG, Neale VL, Petersen A, Lee SE, Sudweeks J, Perez MA, Hankey J, Ramsey D, Gupta S, Bucher C, Doerzaph ZR, Jermeland J, and Knipling RR (2006) The 100-car naturalistic driving study. Phase II - results of the 100-car field experiment.: National Highway Traffic Safety Administration (NHTSA), US Department of Transportation

  7. Peiris MTR, Davidson PR, Bones PJ, Jones RD (2011) Detection of lapses in responsiveness from the EEG. J Neural Eng 8(016003):1–15

    Google Scholar 

  8. Garrett D, Peterson DA, Anderson CW, Thaut MH (2003) Comparison of linear, nonlinear, and feature selection methods for EEG signal classification. IEEE Trans Neural Syst Rehab Eng 11:141–144

    Article  Google Scholar 

  9. Jimenez LO, Landgrebe DA (1998) Supervised classification in high-dimensional space: geometrical, statistical, and asymptotical properties of multivariate data. IEEE Trans Syst Man Cybern C Appl Rev 28:39–54

    Article  Google Scholar 

  10. Kohavi R, John GH (1997) Wrappers for feature subset selection. Artif Intell Med 97:273–324

    Article  Google Scholar 

  11. Guyon I, Elisseeff A (2003) An introduction to variable and feature selection. J Mach Learn Res 3:1157–1182

    Google Scholar 

  12. Domingos P (2012) A few useful things to know about machine learning. Commun ACM 55:78–87

    Article  Google Scholar 

  13. Freund Y, Schapire RE (1997) A decision-theoretic generalization of on-line learning and an application to boosting. J Comput Syst Sci 55:119–139

    Article  Google Scholar 

  14. Fukunaga K (1990) Introduction to statistical pattern recognition, 2nd edn. Academic Press, New York

    Google Scholar 

  15. Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning. Elements 1:337–387

    Google Scholar 

  16. Pearson K (1901) LIII. On lines and planes of closest fit to systems of points in space. The London, Edinburgh, and Dublin Philosophical Magazine Series 6 2: 559–572

  17. Hotelling H (1933) Analysis of a complex of statistical variables into principal components. J Edu Psychol 24:417–441

    Article  Google Scholar 

  18. Spearman C (1904) “General intelligence”, objectively determined and measured. Am J Psychol 15:201–292

    Article  Google Scholar 

  19. Burges CJC (2005) Geometric methods for feature extraction and dimensional reduction. In: Maimon O, Rokach L (eds) Data Mining and Knowledge Discovery Handbook, 2005. Springer, Boston, MA, pp 59–91

    Chapter  Google Scholar 

  20. Venna J (2007) Dimensionality reduction for visual exploration of similarity structures. PhD Thesis Computer Science and Engineering, Aalto University

  21. Saul L, Weinberger KQ, Ham JH, Sha F (2006) Spectral methods for dimensionality reduction. In: O. Chapelle, B. Scholkopf, and A. Zien, (Eds) Semi-supervised learning. MIT Press Scholarship Online 2006:293–306

    Google Scholar 

  22. Venna J, Kaski S (2006) Local multidimensional scaling. Neural Netw 19:889–899

    Article  PubMed  Google Scholar 

  23. Roweis ST (1998) EM algorithms for PCA and SPCA. Proc Conf Adv Neural Inf Process Syst 10:626–632

    Google Scholar 

  24. van der Maaten LJP, Postma EO, and van den Herik HJ (2008) Dimensionality reduction: a comparative review: Tilburg University Technical Report. p. 1-35

  25. Orsenigo C, Vercellis C (2013) Linear versus nonlinear dimensionality reduction for banks’ credit rating prediction. Knowl-Based Syst 47:14–22

    Article  Google Scholar 

  26. Sumithra VS, Surendran S (2015) A review of various linear and non linear dimensionality reduction techniques. Int J Comput Sci Inf Technol 6:2354–2360

    Google Scholar 

  27. Jolliffe IT (2002) Principal component analysis. J Am Stat Assoc 98:487

    Google Scholar 

  28. Davidson PR, Jones RD, Peiris MTR (2007) EEG-based lapse detection with high temporal resolution. IEEE Trans Biomed Eng 54:832–839

    Article  PubMed  Google Scholar 

  29. Ayyagari SSDP, Jones RD, Weddell S (2015) Optimized echo state networks with leaky integrator neurons for EEG-based microsleep detection. Conf Proc IEEE Eng Med Biol Soc 37:3775–3778

    Google Scholar 

  30. van der Maaten LJP (2009) Feature extraction from visual data. PhD Thesis, Tilburg University

  31. Tipping ME, Bishop CM (1999) Probabilistic principal component analysis. J R Stat Soc Ser B Stat Methodol 61:611–622

    Article  Google Scholar 

  32. Kung SY, Diamantaras KI, Taur JS (1994) Adaptive principal component extraction (APEX) and applications. IEEE Trans Sig Process 42:1202–1217

    Article  Google Scholar 

  33. Shawe-Taylor J, Cristianini N (2004) Kernel methods for pattern analysis. Cambridge University Press, New York, NY, USA

    Book  Google Scholar 

  34. Tagaris GA, Richter W, Kim S, Pellizer G, Andersen P, Ugurbil K, Georgopoulos AP (1998) Functional magnetic resonance imaging of mental rotation and memory scanning: a multidimensional scaling analysis of brain activation patterns. Brain Res Rev 26:106–112

    Article  CAS  PubMed  Google Scholar 

  35. Venkatarajan M, Braun W (2001) New quantitative descriptors of amino acids based on multidimensional scaling of a large number of physical-chemical properties. J Mol Model 7:445–453

    Article  CAS  Google Scholar 

  36. Wickelmaier F (2003) An introduction to MDS, reports from the sound quality research unit. Aalborg University, Denmark, Denmark, pp 1–26

    Google Scholar 

  37. Li JX (2004) Visualization of high-dimensional data with relational perspective map. Inf Vis 3:49–59

    Article  Google Scholar 

  38. Balasubramanian M, Schwartz EL (2002) The isomap algorithm and topological stability. Science 295:7–7

    Article  PubMed  Google Scholar 

  39. Dijkstra EW (1959) A note on two problems in connexion with graphs. Numer Math (Heidelb) 1:269–271

    Article  Google Scholar 

  40. Hinton GE, Roweis ST (2003) Stochastic neighbor embedding. In: Becker S, Thrun S, Obermayer K (eds) Advances in neural information processing systems, 2003. MIT Press, Cambridge, MA, USA, pp 833–840

    Google Scholar 

  41. Kullback S, Leibler RA (1951) On information and sufficiency. Ann Math Stat 22:79–86

    Article  Google Scholar 

  42. DeMers D, Cottrell GW (1993) Non-linear dimensionality reduction. In: Hanson SJ, Cowan JD, Giles CL (eds) Advances in neural information processing systems, vol 1993. Morgan-Kaufmann, pp 580–587

  43. Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 313:504–507

    Article  CAS  PubMed  Google Scholar 

  44. Belkin M, Niyogi P (2002) Laplacian Eigenmaps and spectral techniques for embedding and clustering. In: Dietterich TG, Becker S, Ghahramani Z (eds) Advances in neural information processing systems, vol 2002. MIT Press, pp 585–591

  45. Anderson WN, Morley TD (1985) Eigenvalues of the Laplacian of a graph. Linear Multilinear Algebra 18:141–145

    Article  Google Scholar 

  46. Naidu PS (1995) Modern spectrum analysis of time series. CRC Press, Boca Raton, Florida

    Google Scholar 

  47. Wolpert D (1992) Stacked generalization. Neural Netw 5:241–259

    Article  Google Scholar 

  48. Yang HH, Moody J (1999) Data visualization and feature selection: new algorithms for nongaussian data. Proc Adv Neural Info Proc Syst 12:687–693

    Google Scholar 

  49. Gisbrecht A, Schulz A, Hammer B (2015) Parametric nonlinear dimensionality reduction using kernel t-SNE. Neurocomputing 147:71–82

    Article  Google Scholar 

  50. Wilcoxon F (1945) Individual comparisons by ranking methods. Biometrics 1:80–83

    Article  Google Scholar 

  51. Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning: data mining, inference, and prediction, 2nd edn. Springer Series in Statistics, Springer, New York

    Book  Google Scholar 

  52. Buriro AB, Shoorangiz R, Weddell SJ, Jones RD (2018) Predicting microsleep states using EEG inter-channel dependencies. IEEE Trans Neural Syst Rehab Eng 26:2260–2269

    Article  Google Scholar 

  53. Weddell SJ, Ayyagari SSDP, Jones RD (2021) Reservoir-computing approaches to microsleep detection. J Neural Eng 18(046021):1–11

    Google Scholar 

  54. Krishnamoorthy V, Shoorangiz R, Weddell SJ, Beckert L, Jones RD (2019) Deep learning with convolutional neural network for detecting microsleep states from EEG: a comparison between the oversampling technique and cost-based learning. Conf Proc IEEE Eng Med Biol Soc 41:4152–4155

    Google Scholar 

  55. Zhang P, Wang X, Zhang W, Chen J (2019) Learning spatial-spectral-temporal EEG features with recurrent 3D convolutional neural networks for cross-task mental workload assessment. IEEE Trans Neural Syst Rehab Eng 27:31–42

    Article  Google Scholar 

  56. Sors A, Bonnet S, Mirek S, Vercueil L, Payen J-F (2018) A convolutional neural network for sleep stage scoring from raw single-channel EEG. Biomed Signal Process Control 42:107–114

    Article  Google Scholar 

  57. Chua KC, Chandran V, Aeharya R (2007) Higher order spectral (HOS) analysis of epileptic EEG signals. Conf Proc IEEE Eng Med Biol Soc 37:6495–6498

    Google Scholar 

  58. Levendowski DJ, St Louis EK, Strambi LF, Galbiati A, Westbrook P, Berka C (2018) Comparison of EMG power during sleep from the submental and frontalis muscles. Nat Sci Sleep 10:431–437

    Article  PubMed  PubMed Central  Google Scholar 

  59. Good R (1975) Frontalis muscle tension and sleep latency. Psychophysiol 12:465–467

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Richard D. Jones.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ayyagari, S.S.D.P., Jones, R.D. & Weddell, S.J. Detection of microsleep states from the EEG: a comparison of feature reduction methods. Med Biol Eng Comput 59, 1643–1657 (2021). https://doi.org/10.1007/s11517-021-02386-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-021-02386-y

Keywords

Navigation