Automatic EEG Blink Detection Using Dynamic Time Warping Score Clustering

  • Omid Dehzangi
  • Alexander Melville
  • Mojtaba TaherisadrEmail author
Conference paper
Part of the Internet of Things book series (ITTCC)


The electroencephalograph (EEG) is a powerful tool, involving multiple electrodes placed on the scalp, with the intention of measuring brain activity through the scalp. One significant application for EEG is to analyze the mental state of a subject. One of the challenges involved in using the EEG for identifying mental state in practical settings is ocular artifacts e.g. eye blinking. Eye blinks cause high amplitude noise in electroencephalograms (EEGs), the noise from these blinks can cause interference in several very important frequency bands and confuse predictive modeling e.g. introduce false positives. Prior works have employed independent component analysis (ICA) to decompose the noisy EEG signals into constituting sources and identify the eye blink sources. However, ICA requires off-line signal processing and is not suitable for online applications. More recently, time domain autoregressive features were used to model eye blink related segments in the recorded EEG data. While the autoregressive method showed high identification accuracy in isolated short trials, the goal of this work is to create a more advanced system capable of identifying and filtering blink noise in continuous trials during long and complex tasks. The proposed method detailed in this paper conducts automatic detection of eye blink noise using dynamic time warping (DTW) score clustering during wearable EEG-based cognitive workload assessment tests. The proposed eye blink detection system only uses EEG data for training and identification and does not require electrooculogram (EOG) data, which is particularly important for wearable systems. Our experimental results demonstrated the effectiveness of the proposed blink detection methodology by achieving 96.42% average accuracy of blink detection in the recorded EEG dynamics during a continuous workload assessment task.


EEG-based monitoring Ocular artifacts Dynamic time warping Clustering Eye blink detection 


  1. 1.
    Yin, Z., Zhang, J.: Cross-session classification of mental workload levels using EEG and an adaptive deep learning model. Biomed. Signal Process. Control 33, 30–47 (2017)CrossRefGoogle Scholar
  2. 2.
    Ke, Y., et al.: Towards an effective cross-task mental workload recognition model using electroencephalography based on feature selection and support vector machine regression. Int. J. Psychophysiol. 98(2), 157–166 (2015)CrossRefGoogle Scholar
  3. 3.
    Yin, Z., Zhang, J.: Operator functional state classification using least-square support vector machine based recursive feature elimination technique. Comput. Methods Prog. Biomed. 113(1), 101–115 (2014)CrossRefGoogle Scholar
  4. 4.
    Wang, Z., et al.: Cross-subject workload classification with a hierarchical Bayes model. NeuroImage 59(1), 64–69 (2012)CrossRefGoogle Scholar
  5. 5.
    Urigen, J.A., Garcia-Zapirain, B.: EEG artifact removalstate-of-the-art and guidelines. J. Neural Eng. 12(3), 031001 (2015)CrossRefGoogle Scholar
  6. 6.
    Rana, A.Q., Ghouse, A.T., Govindarajan, R.: Basics of electroencephalography (EEG). In: Neurophysiology in Clinical Practice, pp. 3–9. Springer International Publishing (2017)Google Scholar
  7. 7.
    Taherisadr, M., Dehzangi, O., Parsaei, H.: Single channel EEG artifact identification using two-dimensional multi-resolution analysis. Sensors 17(12), 2895 (2017)CrossRefGoogle Scholar
  8. 8.
    Winkler, I., Haufe, S., Tangermann, M.: Automatic classification of artifactual ICA-components for artifact removal in EEG signals. Behav. Brain Funct. 7(1), 30 (2011)CrossRefGoogle Scholar
  9. 9.
    Croft, R.J., Barry, R.J.: EOG correction: a new perspective. Electroencephalogr. Clin. Neurophys. 107(6), 387–394 (1998)CrossRefGoogle Scholar
  10. 10.
    He, P., et al.: Removal of ocular artifacts from EEG: a comparison of adaptive filtering method and regression method using simulated data. In: 27th Annual International Conference of the Engineering in Medicine and Biology Society, 2005. IEEE-EMBS 2005. IEEE (2006)Google Scholar
  11. 11.
    Schlgl, A., et al.: A fully automated correction method of EOG artifacts in EEG recordings. Clin. Neurophysiol. 118(1), 98–104 (2007)CrossRefGoogle Scholar
  12. 12.
    Cheok, N.S., Raveendran, P.: Removal of EOG artifacts using ICA regression method. In: 4th Kuala Lumpur International Conference on Biomedical Engineering 2008. Springer, Berlin, Heidelberg (2008)Google Scholar
  13. 13.
    Makeig, S., et al.: Independent component analysis of electroencephalographic data. In: Advances in Neural Information Processing Systems (1996)Google Scholar
  14. 14.
    Wang, Z., et al.: Robust removal of ocular artifacts by combining independent component analysis and system identification. Biomed. Signal Process. Control 10, 250–259 (2014)CrossRefGoogle Scholar
  15. 15.
    Mahajan, R., Morshed, B.I.: Unsupervised eye blink artifact denoising of EEG data with modified multiscale sample entropy, kurtosis, and Wavelet-ICA. IEEE J. Biomed. Health Inform. 19(1), 158–165 (2015)CrossRefGoogle Scholar
  16. 16.
    Ghandeharion, H., Erfanian, A.: A fully automatic ocular artifact suppression from EEG data using higher order statistics: improved performance by wavelet analysis. Med. Eng. Phys. 32(7), 720–729 (2010)CrossRefGoogle Scholar
  17. 17.
    Kong, W., et al.: Automatic and direct identification of blink components from scalp EEG. Sensors 13(8), 10783–10801 (2013)CrossRefGoogle Scholar
  18. 18.
    Kanungo, T., et al.: An efficient k-means clustering algorithm: analysis and implementation. IEEE Trans. Pattern Anal. Mach. Intell. 24(7), 881–892 (2002)CrossRefGoogle Scholar
  19. 19.
    Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995)zbMATHGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Omid Dehzangi
    • 1
  • Alexander Melville
    • 2
  • Mojtaba Taherisadr
    • 2
    Email author
  1. 1.Rockefeller Neuroscience Institute, West Virginia UniversityMorgantownUSA
  2. 2.University of MichiganDearbornUSA

Personalised recommendations