Advertisement

EEG-based biometric identification with convolutional neural network

  • J. X. ChenEmail author
  • Z. J. Mao
  • W. X. Yao
  • Y. F. Huang
Article
  • 37 Downloads

Abstract

Although more interest arising in biometric identification with electroencephalogram (EEG) signals, there is still a lack of simple and robust models that can be applied in real applications. This work proposes a new convolutional neural network with global spatial and local temporal filter called (GSLT-CNN), which works directly with raw EEG data, not requiring the need for engineering features. We investigate the performance of the GSLT-CNN model on datasets of 157 subjects collected from 4 different experiments that measure endogenous brain states (driving fatigue and emotion) as well as time-locked artificially induced brain responses such as rapid serial visual response (RSVP). We evaluate the GSLT-CNN model against the comparable SVM, Bagging Tree and LDA models with effective feature selection method. The results show the GSLT-CNN model is highly efficient and robust in training more than 279 K epochs within less than 0.5 h and achieves 96% accuracy in identifying 157 subjects, which is 3% better than the best accuracy of SVM on selected PSD feature, 10% better than that of SVM on selected AR feature and 23% better than that of normal CV-CNN model on raw EEG feature. It demonstrates the potential of deep learning solutions for real-life EEG-based biometric identification. We also show that the cross-session identification accuracy from time-locked RSVP data (99%) is slightly higher than that from single-session non-time-locked driving fatigue data (97%) and much higher than that from epochs measuring random brain states (90%), which implies RSVP could be a more beneficial design to achieve high identification accuracy with EEG and our GSLT-CNN model is robust for cross-session identification in RSVP experiment.

Keywords

Biometric identification Electroencephalogram (EEG) Convolutional neural networks Deconvolutional networks Brain-computer interface 

Notes

Funding

This work was supported by the National Natural Science Foundation of China Projects under the Project Agreement Number 61806118 and 61806144.

References

  1. 1.
    Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C et al (2016) Tensorflow: large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467Google Scholar
  2. 2.
    Bigdely-Shamlo N, Mullen T, Kothe C, Su KM, Robbins KA (2015) The PREP pipeline: standardized preprocessing for large-scale EEG analysis. Front Neuroinform 9(16):16Google Scholar
  3. 3.
    Brigham K, Kumar BVKV (2010) Subject identification from electroencephalogram (EEG) signals during imagined speech. In: Fourth IEEE International conference on biometrics: theory applications & systems. IEEEGoogle Scholar
  4. 4.
    Campisi P, La Rocca D (2014) Brain waves for automatic biometric-based user recognition. IEEE Trans Inf Forensic Secur 9(5):782–800CrossRefGoogle Scholar
  5. 5.
    Cecotti H, Gräser A (2011) Convolutional neural networks for P300 detection with application to brain-computer interfaces. IEEE Trans Pattern Anal Mach Intell 33(3):433–445CrossRefGoogle Scholar
  6. 6.
    Cecotti H, Eckstein MP, Giesbrecht B (2014) Single-trial classification of event-related potentials in rapid serial visual presentation tasks using supervised spatial filtering. IEEE Trans Neural Netw Learn Syst 25(11):2030–2042CrossRefGoogle Scholar
  7. 7.
    Chen Y, Atnafu AD, Schlattner I et al (2017) A high-security EEG-based login system with RSVP stimuli and dry electrodes. IEEE Trans Inf Forensic Secur 11(12):2635–2647CrossRefGoogle Scholar
  8. 8.
    Davis H, Davis PA (1936) Action potentials of the brain: in normal persons and in normal states of cerebral activity. Arch Neurol Psychiatr 36:1214–1224CrossRefGoogle Scholar
  9. 9.
    Delorme A, Makeig S (2004) EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis. J Neurosci Methods 134(1):9–21CrossRefGoogle Scholar
  10. 10.
    DelPozo-Banos M, Travieso CM, Weidemann CT, Alonso JB (2015) EEG biometric identification: a thorough exploration of the time-frequency domain. J Neural Eng 12(5):056019CrossRefGoogle Scholar
  11. 11.
    Dinesh Jackson Samuel R, Rajesh Kanna B (2018) Tuberculosis (TB) detection system using deep neural networks. Neural Comput Applic.  https://doi.org/10.1007/s00521-018-3564-4
  12. 12.
    Dinesh Jackson Samuel R, Rajesh Kanna B (2018) Cybernetic microbial detection system using transfer learning. Multimed Tools Appl.  https://doi.org/10.1007/s11042-018-6356-z
  13. 13.
    Glorot X, Bordes A, Bengio Y (2011) Deep sparse rectifier neural networks. In: International conference on artificial intelligence and statistics, vol 15, pp 315–323Google Scholar
  14. 14.
    Hinton G (2012) A practical guide to training restricted Boltzmann machines. Momentum 9(1):599–619Google Scholar
  15. 15.
    Koelstra S, Muhl C, Soleymani M, Lee JS, Yazdani A, Ebrahimi T et al (2012) Deap: a database for emotion analysis; using physiological signals. IEEE Trans Affect Comput 3:18–31CrossRefGoogle Scholar
  16. 16.
    Lance BJ, Kerick SE, Ries AJ, Oie KS, McDowell K (2012) Brain–computer interface technologies in the coming decades. Proc IEEE 100:1585–1599CrossRefGoogle Scholar
  17. 17.
    Lee Y, Huang Y (2018) Generating target/nontarget images of an RSVP experiment from brain signals in by conditional generative adversarial network. In: 2018 IEEE EMBS international conference on Biomedical & Health Informatics (BHI)Google Scholar
  18. 18.
    Lin YP, Wang CH, Jung TP, Wu TL, Jeng SK, Duann JR et al (2010) EEG-based emotion recognition in music listening. IEEE Trans Biomed Eng 57:1798–1806CrossRefGoogle Scholar
  19. 19.
    Maaten L v d, Hinton G (2008) Visualizing data using t-SNE. J Mach Learn Res 9(2605):2579–2605zbMATHGoogle Scholar
  20. 20.
    Maiorana E, La Rocca D, Campisi P (2016) Eigenbrains and Eigentensorbrains: parsimonious bases for EEG biometrics. Neurocomputing 171:638–648CrossRefGoogle Scholar
  21. 21.
    Mao Z, Jung T-P, Lin C-T, Huang Y (2016) Predicting EEG sample size required for classification calibration. In: International conference on augmented cognition, pp 57–68Google Scholar
  22. 22.
    Mao Z, Yao W, Huang Y (2017) EEG-based biometric identification with deep learning. In: The 2017 8th international IEEE/EMBS conference on neural engineering (NER)Google Scholar
  23. 23.
    Mao Z, Yao W, Huang Y (2017) Design of deep convolutional networks for prediction of image rapid serial visual presentation events. In: The 39th annual international conference of the IEEE engineering in medicine and biology society (EMBC 2017), Jeju Island, pp 2035–2038Google Scholar
  24. 24.
    McCallum A, Nigam K (1998) A comparison of event models for naive bayes text classification. In: AAAI-98 workshop on learning for text categorization, pp 41–48Google Scholar
  25. 25.
    Mohammadi G, Shoushtari P, Molaee Ardekani B, Shamsollahi MB (2006) Person identification by using AR model for EEG signals. In: Proceeding of World Academy of Science, Engineering and Technology, pp 281–285Google Scholar
  26. 26.
    Palaniappan R (2005) Identifying individuality using mental task based brain computer interface. In: 2005 3rd international conference on intelligent sensing and information processing, pp 238–242Google Scholar
  27. 27.
    Roselin V, Waghmare LM, Chirchi ER (2013) Iris biometric recognition for person identification in security systems. Int J Comput Appl 24(9):1–6Google Scholar
  28. 28.
    Ruiz-Blondet MV, Jin Z, Laszlo S (2016) CEREBRE: a novel method for very high accuracy event-related potential biometric identification. IEEE Trans Inf Forensic Secur 11(7):1618–1629CrossRefGoogle Scholar
  29. 29.
    Scholkopft B, Mullert K-R (1999) Fisher discriminant analysis with kernels. In: Neural networks for signal processing IX, vol 1, p 1Google Scholar
  30. 30.
    Sharma K, Monga H (2014) Efficient biometric Iris recognition using Hough transform. Int J Engineer Sci Res Tech 3(7):866–873Google Scholar
  31. 31.
    Singhal GK, RamKumar P (2008) Person identification using evoked potentials and peak matching. In: Biometrics symposium, vol 74, pp 1–6Google Scholar
  32. 32.
    Touryan J, Apker G, Lance BJ, Kerick SE, Ries AJ, McDowell K (2014) Estimating endogenous changes in task performance from EEG. Front Neurosci 8(8):155Google Scholar
  33. 33.
    Touryan J, Lance BJ, Kerick SE, Ries AJ, McDowell K (2016) Common EEG features for behavioral estimation in disparate, real-world tasks. Biol Psychol 114:93–107CrossRefGoogle Scholar
  34. 34.
    Ververidis D, Kotropoulos C (2008) Fast and accurate feature subset selection applied into speech emotion recognition. Els Signal Process 88(12):2956–2970CrossRefGoogle Scholar
  35. 35.
    Ververidis D, Kotropoulos C (2009) Information loss of the Mahalanobis distance in high dimensions: application to feature selection. IEEE Trans Pattern Anal Mach Intell 31(12):2275–2281CrossRefGoogle Scholar
  36. 36.
    Wolpaw JR (2007) Brain–computer interfaces as new brain output pathways. J Physiol 579:613–619CrossRefGoogle Scholar
  37. 37.
    Yeom SK, Suk HI, Lee SW (2013) Person authentication from neural activity of face-specific visual self-representation. Pattern Recogn 46(4):1159–1169CrossRefGoogle Scholar
  38. 38.
    Zeiler MD, Fergus R (2014) Visualizing and understanding convolutional networks. In: European conference on computer vision, vol 8689, pp 818–833Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.College of Electronical and Information EngineeringShaanxi University of Science and TechnologyXi’anChina
  2. 2.Department of Electrical and Computer EngineeringUniversity of Texas at San AntonioSan AntonioUSA
  3. 3.Department of KinesiologyUniversity of Texas at San AntonioSan AntonioUSA
  4. 4.Department of Epidemiology and BiostatisticsUniversity of Texas Health Science Center at San AntonioSan AntonioUSA

Personalised recommendations