Phase synchronisation between different neural groups is considered an important source of information to understand the underlying mechanisms of brain cognition. This Letter investigated phase-synchronisation patterns from electroencephalogram (EEG) signals recorded from ten healthy participants performing motor imagery (MI) tasks using schematic emotional faces as stimuli. These phase-synchronised states, named synchrostates, are specific for each cognitive task performed by the user. The maximum and minimum number of occurrence states were selected for each subject and task to extract the connectivity network measures based on graph theory to feed a set of classification algorithms. Two MI tasks were successfully classified with the highest accuracy of 85% with corresponding sensitivity and specificity of 85%. In this work, not only the performance of different supervised learning techniques was studied, as well as the optimal subset of features to obtain the best discrimination rates. The robustness of this classification method for MI tasks indicates the possibility of expanding its use for online classification of the brain–computer interface (BCI) systems.

References

1. 1)
  - 1. Chou, W.-C., Duann, J.-R., She, H.-C., et al: ‘Explore the functional connectivity between brain regions during a chemistry working memory task’, PLoS One, 2015, 10, (6), p. e0129019 (doi: 10.1371/journal.pone.0129019).
2. 2)
  - 18. Rahman, T., Ghosh, A.K., Shuvo, M.H., et al: ‘Mental stress recognition using K-nearest neighbor (KNN) classifier on EEG signals’. Int. Conf. Materials, Electronics & Information Engineering (ICMEIE), 2015, pp. 1–4.
3. 3)
  - 3. Gallego-Jutglà, E., Solé-Casals, J., Vialatte, F.-B., et al: ‘A hybrid feature selection approach for the early diagnosis of Alzheimer's disease’, J. Neural Eng., 2015, 12, (1), p. 16018 (doi: 10.1088/1741-2560/12/1/016018).
4. 4)
  - 15. Hassan, M., Shamas, M., Khalil, M., et al: ‘EEGNET: An open source tool for analyzing and visualizing M/EEG connectome’, PLoS One, 2015, 10, p. 9.
5. 5)
  - 6. Park, C., Looney, D., Ahrabian, A., et al: ‘Classification of motor imagery BCI using multivariate empirical mode decomposition’, 2013, 21, (1), pp. 10–22.
6. 6)
  - 18. Arvaneh, M., Guan, C., Ang, K.K., et al: ‘Optimizing the channel selection and classification accuracy in EEG-based BCI’, IEEE Trans. Biomed. Eng., 2011, 58, (6), pp. 1865–1873 (doi: 10.1109/TBME.2011.2131142).
7. 7)
  - 4. Jamal, W., Das, S., Maharatna, K., et al: ‘On the existence of synchrostates in multichannel EEG signals during face-perception tasks’, Phys. Eng. Express, 2015, 1, (1), pp. 1–30.
8. 8)
  - 17. Rogers, S., Girolami, M.: ‘A first course in machine learning’, Finance (Chapman & Hall/CRC, Boca Raton, FL, USA, 2011), p. 427.
9. 9)
  - 11. Williams, N.J., Nasuto, S.J., Saddy, J.D.: ‘Method for exploratory cluster analysis and visualisation of single-trial ERP ensembles’, J. Neurosci. Methods, 2014, 250, pp. 22–33 (doi: 10.1016/j.jneumeth.2015.02.007).
10. 10)
  - 17. Rubinov, M., Sporns, O.: ‘Complex network measures of brain connectivity: uses and interpretations’, Neuroimage, 2010, 52, (3), pp. 1059–1069 (doi: 10.1016/j.neuroimage.2009.10.003).
11. 11)
  - 16. Kropotov, J.D.: ‘Quantitative EEG, event-related potentials and neurotherapy’ (Academic Press, San Diego, CA, USA, 2009, 1st edn.).
12. 12)
  - 12. Jamal, W., Das, S., Oprescu, I.-A., et al: ‘Classification of autism spectrum disorder using supervised learning of brain connectivity measures extracted from synchrostates’, J. Neural Eng., 2014, 11, (4), p. 46019 (doi: 10.1088/1741-2560/11/4/046019).
13. 13)
  - 9. Santamaria, L., James, C.: ‘Use of graph metrics to classify motor imagery based BCI’. 2016 Int. Conf. for Students on Applied Engineering (ISCAE), 2016, pp. 469–474.
14. 14)
  - 2. Jamal, W., Das, S., Maharatna, K., et al: ‘Brain connectivity analysis from EEG signals using stable phase-synchronized states during face perception tasks’, Phys. A Stat. Mech. Appl., 2015, 434, pp. 273–295 (doi: 10.1016/j.physa.2015.03.087).
15. 15)
  - 22. Bashashati, H., Ward, R.K., Birch, G.E., et al: ‘Comparing different classifiers in sensory motor brain computer interfaces’, PLoS One, 2015, 10, (6), pp. 1–17 (doi: 10.1371/journal.pone.0129435).
16. 16)
  - 21. Witten, I.H., Frank, E., Hall, M.A.: ‘Data mining: practical techniques management’ (Morgan Kaufmann Publishers, San Francisco, CA, USA, 2011, 3rd edn.).
17. 17)
  - 7. Perseh, B., Sharafat, A.R.: ‘An efficient P300-based BCI using wavelet features and IBPSO-based channel selection’, J. Med. Signals Sens., 2012, 2, (3), pp. 128–143.
18. 18)
  - 19. Van der Heijden, F., Duin, R.P.W., de Ridder, D., et al: ‘Classification, parameter estimation and state estimation’ (Wiley, Chichester, UK, 2004, 1st edn.).
19. 19)
  - 8. Asensio-Cubero, J., Gan, J.Q., Palaniappan, R.: ‘Multiresolution analysis over graphs for a motor imagery based online BCI game’, Comput. Biol. Med., 2016, 68, pp. 21–26 (doi: 10.1016/j.compbiomed.2015.10.016).
20. 20)
  - 23. Aldea, R., Fira, M.: ‘Classifications of motor imagery tasks in brain computer interface using linear discriminant analysis’, Int. J. Adv. Res. Artif. Intell., 2014, 3, (7), pp. 5–9 (doi: 10.14569/IJARAI.2014.030702).
21. 21)
  - 13. Vecchio, F., Miraglia, F., Quaranta, D., et al: ‘Cortical connectivity and memory performance in cognitive decline: a study via graph theory from EEG data’, Neuroscience, 2016, 316, pp. 143–150 (doi: 10.1016/j.neuroscience.2015.12.036).
22. 22)
  - 10. Santamaria, L., James, C.: ‘Classification in emotional BCI using phase information from the EEG’. Proc. Annual Int. Conf. IEEE Engineering in Medicine and Biology Society, 2016, pp. 371–374.
23. 23)
  - 5. Shan, H., Xu, H., Zhu, S., et al: ‘A novel channel selection method for optimal classification in different motor imagery BCI paradigms’, Biomed. Eng. Online, 2015, 14, (1), p. 93 (doi: 10.1186/s12938-015-0087-4).

Using brain connectivity metrics from synchrostates to perform motor imagery classification in EEG-based BCI systems

References

Related content