Fuzzy Integral Optimization with Deep Q-Network for EEG-Based Intention Recognition

  • Dalin ZhangEmail author
  • Lina Yao
  • Sen Wang
  • Kaixuan Chen
  • Zheng Yang
  • Boualem Benatallah
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10937)


Non-invasive brain-computer interface using electroencephalography (EEG) signals promises a convenient approach empowering humans to communicate with and even control the outside world only with intentions. Herein, we propose to analyze EEG signals using fuzzy integral with deep reinforcement learning optimization to aggregate two aspects of information contained within EEG signals, namely local spatio-temporal and global temporal information, and demonstrate its benefits in EEG-based human intention recognition tasks. The EEG signals are first transformed into a 3D format preserving both topological and temporal structures, followed by distinctive local spatio-temporal feature extraction by a 3D-CNN, as well as the global temporal feature extraction by an RNN. Next, a fuzzy integral with respect to the optimized fuzzy measures with deep reinforcement learning is utilized to integrate the two extracted information and makes a final decision. The proposed approach retains the topological and temporal structures of EEG signals and merges them in a more efficient way. Experiments on a public EEG-based movement intention dataset demonstrate the effectiveness and superior performance of our proposed method.


  1. 1.
    LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)CrossRefGoogle Scholar
  2. 2.
    Bashivan, P., Rish, I., Yeasin, M., Codella, N.: Learning representations from EEG with deep recurrent-convolutional neural networks. In: International Conference on Learning Representations (2016)Google Scholar
  3. 3.
    Zhang, X., Yao, L., Zhang, D., Wang, X., Sheng, Q., Gu, T.: Multi-person brain activity recognition via comprehensive EEG signal analysis. In: 14th International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services (2017)Google Scholar
  4. 4.
    Cecotti, H., Graser, A.: Convolutional neural networks for P300 detection with application to brain-computer interfaces. IEEE Trans. Pattern Anal. Mach. Intell. 33(3), 433–445 (2011)CrossRefGoogle Scholar
  5. 5.
    Cavrini, F., Bianchi, L., Quitadamo, L.R., Saggio, G.: A fuzzy integral ensemble method in visual P300 brain-computer interface. Comput. Intell. Neurosci. 2016, 49 (2016)CrossRefGoogle Scholar
  6. 6.
    Yoo, B.S., Kim, J.H.: Fuzzy integral-based gaze control of a robotic head for human robot interaction. IEEE Trans. Cybern. 45(9), 1769–1783 (2015)CrossRefGoogle Scholar
  7. 7.
    Yoo, J.K., Kim, J.H.: Fuzzy integral-based gaze control architecture incorporated with modified-univector field-based navigation for humanoid robots. IEEE Trans. Syst. Man Cybern. Part B (Cybern.) 42(1), 125–139 (2012)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Shoaie, Z., Esmaeeli, M., Shouraki, S.B.: Combination of multiple classifiers with fuzzy integral method for classifying the EEG signals in brain-computer interface. In: International Conference on Biomedical and Pharmaceutical Engineering, ICBPE 2006, pp. 157–161. IEEE (2006)Google Scholar
  9. 9.
    Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A.A., Veness, J., Bellemare, M.G., Graves, A., Riedmiller, M., Fidjeland, A.K., Ostrovski, G., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529–533 (2015)CrossRefGoogle Scholar
  10. 10.
    Silver, D., Huang, A., Maddison, C.J., Guez, A., Sifre, L., Van Den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484–489 (2016)CrossRefGoogle Scholar
  11. 11.
    Schalk, G., McFarland, D.J., Hinterberger, T., Birbaumer, N., Wolpaw, J.R.: BCI 2000: a general-purpose brain-computer interface (BCI) system. IEEE Trans. Biomed. Eng. 51(6), 1034–1043 (2004)CrossRefGoogle Scholar
  12. 12.
    Shenoy, H.V., Vinod, A.P., Guan, C.: Shrinkage estimator based regularization for EEG motor imagery classification. In: 2015 10th International Conference on Information, Communications and Signal Processing (ICICS), pp. 1–5. IEEE (2015)Google Scholar
  13. 13.
    Sita, J., Nair, G.: Feature extraction and classification of EEG signals for mapping motor area of the brain. In: 2013 International Conference on Control Communication and Computing (ICCC), pp. 463–468. IEEE (2013)Google Scholar
  14. 14.
    Schirrmeister, R.T., Springenberg, J.T., Fiederer, L.D.J., Glasstetter, M., Eggensperger, K., Tangermann, M., Hutter, F., Burgard, W., Ball, T.: Deep learning with convolutional neural networks for EEG decoding and visualization. Hum. Brain Mapp. 38(11), 5391–5420 (2017)CrossRefGoogle Scholar
  15. 15.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Dalin Zhang
    • 1
    Email author
  • Lina Yao
    • 1
  • Sen Wang
    • 2
  • Kaixuan Chen
    • 1
  • Zheng Yang
    • 3
  • Boualem Benatallah
    • 1
  1. 1.School of Computer Science and EngineeringUNSW SydneySydneyAustralia
  2. 2.School of Information and Communication TechnologyGriffith UniversityBrisbaneAustralia
  3. 3.School of SoftwareTsinghua UniversityBeijingChina

Personalised recommendations