Skip to main content
SpringerLink
Log in

Recurrence quantification analysis of EEG signals for tactile roughness discrimination

  • Original Article
  • Published:
International Journal of Machine Learning and Cybernetics Aims and scope Submit manuscript

Abstract

Roughness recognition is an important function in the nervous system that facilitates our interactions with the environment. Previous studies have focused on the neuro-cognitive aspects and frequency-based changes in response to the roughness stimuli. In this study, we investigate the effect of different roughness levels on the nonlinear characteristics of EEG signals. Nine healthy subjects participated in the current research and touched three surfaces with different levels of roughness in a passive dynamical way. The experiment was repeated for both hands separately. During the experiment, the EEG signals were recorded. Next, three nonlinear features were extracted using the recurrence quantification analysis (RQA) method; and four classifiers were hired to distinguish six conditions, including three levels of roughness and the touching hand. The results showed that EEG nonlinear characteristics were significantly affected by the variation of surface roughness. The effects were different between touching by the left or the right hand. Moreover, it was observed that employing the RQA-based features leads to the higher accuracy of classification compared to the conventional frequency-based features. Additionally, we found that the brain representation of tactile roughness has a pseudo-random dynamic, and the amount of roughness can influence a network of brain channels. Finally, utilizing the weighted combination of different brain channels while considering the extracted nonlinear features, the LDA classification accuracy was reached 93%. Therefore, it can be suggested that not only temporal variations of brain signals but also their spatial distribution (brain channels) are important to recognize the surface roughness.

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

Access this article

Log in via an institution

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
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

References

  1. Acharya UR, Sree SV, Chattopadhyay S, Yu W, Ang PCA (2011) Application of recurrence quantification analysis for the automated identification of epileptic EEG signals. J Int J Neural Syst 21:199–211

    Article  Google Scholar 

  2. Balakrishnama S, Ganapathiraju A, Processing i (1998) Linear discriminant analysis-a brief tutorial. J Inst Signal 18:1–8

    Google Scholar 

  3. Ballesteros S, Munoz F, Sebastian M, Garcia B, Reales JM (2009) ERP evidence of tactile texture processing: Effects of roughness and movement. In: EuroHaptics conference, 2009 and Symposium on haptic interfaces for virtual environment and teleoperator systems. World Haptics 2009. Third Joint, IEEE, pp 166–171

  4. Callier T, Suresh AK, Bensmaia SJ (2019) Neural coding of contact events in somatosensory cortex. J Cerebral Cortex 29:4613–4627

    Article  Google Scholar 

  5. Ding S, Pan Y, Tong M, Zhao X (2017) Tactile perception of roughness and hardness to discriminate materials by friction-induced vibration. J Sensors 17:2748

    Article  Google Scholar 

  6. Duan K-B, Keerthi SS (2005) Which is the best multiclass SVM method? An empirical study. In: International workshop on multiple classifier systems. Springer, pp 278–285

  7. Fabretti A, Ausloos M (2005) Recurrence plot and recurrence quantification analysis techniques for detecting a critical regime. Examples from financial market inidices. Int J Modern Phys C 16:671–706

    Article  Google Scholar 

  8. Fujimoto S, Kon N (2016) Improvement of tactile roughness discrimination acuity correlates with perception of improved hand function in patients after hand surgery. J Phys Therapy Sci 28:1307–1311

    Article  Google Scholar 

  9. Genna C, Oddo C, Fanciullacci C, Chisari C, Micera S, Artoni F (2018) Bilateral cortical representation of tactile roughness. Brain Res 1699:79–88

    Article  Google Scholar 

  10. Kim J, Chung YG, Park J-Y, Chung S-C, Wallraven C, Bülthoff HH, Kim S-P (2015) Decoding accuracy in supplementary motor cortex correlates with perceptual sensitivity to tactile roughness. PLoS ONE 10:e0129777

    Article  Google Scholar 

  11. Kitada R et al (2005) Tactile estimation of the roughness of gratings yields a graded response in the human brain: an fMRI study. NeuroImage 25:90–100

    Article  Google Scholar 

  12. Korn H, Faure P (2003) Is there chaos in the brain? II Experimental evidence and related models. J Comptes Rend Biol 326:787–840

    Article  Google Scholar 

  13. Lieber JD, Bensmaia SJ (2019) High-dimensional representation of texture in somatosensory cortex of primates. J Proc Natl Acad Sci 116:3268–3277

    Article  Google Scholar 

  14. Marwan N, Wessel N, Meyerfeldt U, Schirdewan A, Kurths J (2002) Recurrence-plot-based measures of complexity and their application to heart-rate-variability data. Phys Rev E 66:026702

    Article  Google Scholar 

  15. Meng H-B, Song M-Y, Yu Y-F, Wu J-H (2016) Recurrence quantity analysis of the instantaneous pressure fluctuation signals in the novel tank with multi-horizontal submerged jets. Chem Biochem Eng Q 30:19–31

    Article  Google Scholar 

  16. Muñoz F, Reales JM, Sebastián MÁ, Ballesteros S (2014) An electrophysiological study of haptic roughness: effects of levels of texture and stimulus uncertainty in the P300. Brain Res 1562:59–68

    Article  Google Scholar 

  17. Muñoz F, Sebastián M, Reales JM, Ballesteros S (2010) Modulations in low-frequency EEG oscillations in the processing of tactile surfaces. In: International conference on human haptic sensing and touch enabled computer applications. Springer, pp 37–43

  18. Niknazar M, Mousavi S, Vahdat BV, Sayyah M (2013) A new framework based on recurrence quantification analysis for epileptic seizure detection. J IEEE J Biomed Health Informatics 17:572–578

    Article  Google Scholar 

  19. Oddo CM et al (2016) Intraneural stimulation elicits discrimination of textural features by artificial fingertip in intact and amputee humans. J Elife 5:e09148

    Article  Google Scholar 

  20. Ouyang G, Li X, Dang C, Richards DA (2008) Using recurrence plot for determinism analysis of EEG recordings in genetic absence epilepsy rats. Clin Neurophysiol 119:1747–1755

    Article  Google Scholar 

  21. Paluš M (1996) Nonlinearity in normal human EEG: cycles, temporal asymmetry, nonstationarity and randomness, not chaos. Biol Cybern 75:389–396

    Article  Google Scholar 

  22. Pijn JP, Van Neerven J, Noest A, da Silva FHL (1991) Chaos or noise in EEG signals; dependence on state and brain site. J Electroencephalogr Clin Neurophysiol 79:371–381

    Article  Google Scholar 

  23. Shabani H, Mikaili M, Noori SMR (2016) Assessment of recurrence quantification analysis (RQA) of EEG for development of a novel drowsiness detection system. J Biomed Eng Lett 6:196–204

    Article  Google Scholar 

  24. Sun K, Liu L, Qiu J, Feng G (2020) Fuzzy adaptive finite-time fault-tolerant control for strict-feedback nonlinear systems. IEEE Trans Fuzzy Sys. https://doi.org/10.1109/TFUZZ.2020.2965890

    Article  Google Scholar 

  25. Trulla L, Giuliani A, Zbilut J, Webber C Jr (1996) Recurrence quantification analysis of the logistic equation with transients. Phys Lett A 223:255–260

    Article  MathSciNet  Google Scholar 

  26. Wang X, Meng J, Tan G, Zou L (2010) Research on the relation of EEG signal chaos characteristics with high-level intelligence activity of human brain. J Nonlinear Biomed Phys 4:2

    Article  Google Scholar 

  27. Webber CL Jr, Zbilut JP, Ticnmftbs J (2005) Recurrence quantification analysis of nonlinear dynamical systems. Tutor Contemporary Nonlinear Methods Behavioral Sci 94:26–94

    Google Scholar 

  28. Yoshioka T, Craig JC, Beck GC, Hsiao SS (2011) Perceptual constancy of texture roughness in the tactile system. J Neurosci 31:17603–17611

    Article  Google Scholar 

Download references

Acknowledgements

The authors would like to thank the esteemed reviewers for their insightful and helpful comments. M.A, would like to thank Mr. Tirdad Seifi and Mrs. Fatemeh Zamanian for their valuable assistance during data collection. M.A, is also grateful for the contributions of the Iranian National Brain Mapping Laboratory (NBML), Tehran, Iran, for their data acquisition service. G.B and M.A were supported by the Iran National Science Foundation (INSF) and Kermanshah University of Medical Sciences, Kermanshah, Iran. This research has also received funding from the European Union’s Horizon 2020 Framework Program for Research and Innovation under the Specific Grant Agreements No. 785907 (Human Brain Project SGA2) and No. 945539 (Human Brain Project SGA3).

Author information

Authors and Affiliations

  1. Medical Biology Research Center, Kermanshah University of Medical Sciences, Kermanshah, Iran

    Golnaz Baghdadi

  2. Medical Technology Research Center, Kermanshah University of Medical Sciences, Parastar Ave, Kermanshah, Iran

    Mahmood Amiri

  3. The BioRobotics Institute, Scuola Superiore Sant’Anna, Pontedera, Italy

    Egidio Falotico & Cecilia Laschi

Authors
  1. Golnaz Baghdadi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mahmood Amiri
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Egidio Falotico
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Cecilia Laschi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mahmood Amiri.

Ethics declarations

Conflict of interest

The authors declare that there is no conflict of interest (financial or non-financial) concerning the publication of this manuscript.

Appendix

Appendix

1.1 Pseudocodes

The pseudocodes for the whole methodology and calculating each feature (RR, DET, and ENTR) are shown in Figs. 12, 13, 14, 15, 16, 17.

Fig. 12
figure 12

The pseudocode of the methodology for online detection of the roughness level of the touched surface by the left/right hand

Full size image
Fig. 13
figure 13

The pseudocode creating the matrix R from the filtered EEG signals

Full size image
Fig. 14
figure 14

The pseudocode detecting diagonal line from the matrix R

Full size image
Fig. 15
figure 15

The pseudocode calculating the RR value

Full size image
Fig. 16
figure 16

The pseudocode calculating the DET value

Full size image
Fig. 17
figure 17

The pseudocode calculating the ENTR value

Full size image

1.2 Results of statistical analysis

Results of ANOVA and post-test analyses (Tukey multiple comparisons test) for the “RR” feature have been summarized in Figs. 18, 19 and 20 show the results of ANOVA and post-test examinations for “DET” and “ENTR” features, respectively.

Fig. 18
figure 18

Results of ANOVA and post-hoc tests for the “RR” feature. In the horizontal axis, the results of ANOVA have been shown for each channel. The color of each cell in the image shows the results of the post-hoc test. Black cells indicate a condition where, according to the post-hoc test (Tukey multiple comparisons test), there is no significant difference between the two classes shown in the vertical axis. White cells show the condition with a significant difference. Channels with a higher number of detectable cases were bolded in the horizontal label

Full size image
Fig. 19
figure 19

Results of ANOVA and post-hoc tests for the “DET” feature. In the horizontal axis, the results of ANOVA were shown for each channel. The color of each cell in the image shows the results of the post-hoc test. Black cells indicate a condition where, according to the post-hoc test (Tukey multiple comparisons test), there is no significant difference between the two classes shown in the vertical axis. White cells show the condition with a significant difference. Channels with a higher number of detectable cases were bolded in the horizontal label

Full size image
Fig. 20
figure 20

Results of ANOVA and post-hoc tests for the “ENTR” feature. In the horizontal axis, the results of ANOVA have been shown for each channel. The color of each cell in the image shows the results of the post-hoc test. Black cells indicate a condition where, according to the post-hoc test (Tukey multiple comparisons test), there is no significant difference between the two classes shown in the vertical axis. White cells show the condition with a significant difference. Channels with a higher number of detectable cases were bolded in the horizontal label

Full size image

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Baghdadi, G., Amiri, M., Falotico, E. et al. Recurrence quantification analysis of EEG signals for tactile roughness discrimination. Int. J. Mach. Learn. & Cyber. 12, 1115–1136 (2021). https://doi.org/10.1007/s13042-020-01224-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13042-020-01224-1

Keywords

Search

Navigation