Weighted extreme learning machine for P300 detection with application to brain computer interface

  • Wanzeng Kong
  • Shijie Guo
  • Yanfang Long
  • Yong Peng
  • Hong Zeng
  • Xinyu Zhang
  • Jianhai Zhang
Original Research


Brain–computer interface (BCI) is a communication system, which brain signals can be analyzed and transformed into commands of external devices. The P300-speller BCI utilizes the P300 evoked potentials, which generated in oddball paradigms, to spell characters. In order to eliminate the imbalance existed between target and non-target stimuli data in electroencephalogram (EEG) signals, we apply weighted extreme learning machine (WELM), which consequently improves the P300 detection accuracy. For starter, the raw EEG signals of all channels are divided into several segments by a given time window. Afterwards, features of each segment are extracted by principal component analysis. Then, WELM executes a classification for above features. Last, outputs of WELM classifier are used to recognize the target character in the P300 speller. Experiments were carried out based on the third BCI Competition Data Set II and achieved an average accuracy of 97%, and it still reached 85% with the first eight high sensitivity channels for P300 responses.


Brain–computer interface P300 speller Principal component analysis Weighted extreme learning machine 



This research was supported by National Natural Science Foundation of China (Grant nos. 61671193 and 61602140), Science and Technology Program of Zhejiang Province (2018C04012, 2017C33049), Science and technology Platform Construction Project of Fujian Science and Technology Department (2015Y2001).


  1. Bennett KP, Kunapuli G, Hu J, Pang J-S (2008) Bilevel optimization and machine learning. In: IEEE world congress on computational intelligence. Springer, pp 25–47Google Scholar
  2. Blankertz B, Muller KR, Krusienski DJ, Schalk G, Wolpaw JR, Schlogl A, Pfurtscheller G, Millan JR, Schroder M, Birbaumer N (2006) The BCI competition III: validating alternative approaches to actual BCI problems. IEEE Trans Neural Syst Rehabil Eng 14(2):153–159CrossRefGoogle Scholar
  3. Breiman L (1996) Bagging predictors. Mach Learn 24(2):123–140zbMATHGoogle Scholar
  4. 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
  5. Chen D, Chen X, Lin F, Kitzman H (2015) Systemize the probabilistic discrete event systems with moore-penrose generalized-inverse matrix theory for cross-sectional behavioral data. J Biom Biostat 6(219):2Google Scholar
  6. Elsawy AS, Eldawlatly S, Taher M, Aly GM (2013) A principal component analysis ensemble classifier for P300 speller applications. In: Image and signal processing and analysis (ISPA), 2013 8th international symposium on, IEEE, pp 444–449Google Scholar
  7. Farwell LA, Donchin E (1988) Talking off the top of your head: toward a mental prosthesis utilizing event-related brain potentials. Electroencephalogr Clin Neurophysiol 70(6):510–523CrossRefGoogle Scholar
  8. Fletcher R (1981) Practical methods of optimization: vol. 2: constrained optimization. Wiley, Somerset, p 224zbMATHGoogle Scholar
  9. Hoffmann U, Garcia G, Vesin JM, Diserens K, Ebrahimi T (2005) A boosting approach to P300 detection with application to brain–computer interfaces. In: Neural engineering, 2005. Conference proceedings. 2nd international IEEE EMBS conference on, IEEE, pp 97–100Google Scholar
  10. Hoffmann U, Vesin JM, Ebrahimi T, Diserens K (2008) An efficient P300-based brain–computer interface for disabled subjects. J Neurosci Methods 167(1):115–125CrossRefGoogle Scholar
  11. Huang GB, Zhu QY, Siew CK (2004) Extreme learning machine: a new learning scheme of feedforward neural networks. In: Neural networks, 2004. Proceedings. 2004 IEEE international joint conference on, IEEE, vol 2, pp 985–990Google Scholar
  12. Huang GB, Chen L, Siew CK et al (2006a) Universal approximation using incremental constructive feedforward networks with random hidden nodes. IEEE Trans Neural Netw 17(4):879–892CrossRefGoogle Scholar
  13. Huang GB, Zhu QY, Siew CK (2006b) Extreme learning machine: theory and applications. Neurocomputing 70(1–3):489–501CrossRefGoogle Scholar
  14. Huang GB, Zhou H, Ding X, Zhang R (2012) Extreme learning machine for regression and multiclass classification. IEEE Trans Syst Man Cybern Part B (Cybernetics) 42(2):513–529CrossRefGoogle Scholar
  15. Krusienski DJ, Sellers EW, McFarland DJ, Vaughan TM, Wolpaw JR (2008) Toward enhanced P300 speller performance. J Neurosci Methods 167(1):15–21CrossRefGoogle Scholar
  16. Liu Y, Zhou Z, Hu D, Dong G (2005) T-weighted approach for neural information processing in P300 based brain-computer interface. In: International conference on neural networks and brain, 2005. ICNN&B’05, vol 3. IEEE, pp 1535–1539Google Scholar
  17. Liu YH, Weng JT, Kang ZH, Teng JT, Huang HP (2010) An improved SVM-based real-time P300 speller for brain–computer interface. In: Systems man and cybernetics (SMC), 2010 IEEE international conference on, IEEE, pp 1748–1754Google Scholar
  18. Mirghasemi H, Fazel-Rezai R, Shamsollahi M (2006) Analysis of P300 classifiers in brain computer interface speller. In: Engineering in medicine and biology society, 2006. EMBS’06. 28th annual international conference of the IEEE, IEEE, pp 6205–6208Google Scholar
  19. Peng Y, Lu BL (2017) Discriminative extreme learning machine with supervised sparsity preserving for image classification. Neurocomputing 261:242–252CrossRefGoogle Scholar
  20. Qassim YT, Cutmore TR, James DA, Rowlands DD (2013) Wavelet coherence of EEG signals for a visual oddball task. Comput Biol Med 43(1):23–31CrossRefGoogle Scholar
  21. Rakotomamonjy A, Guigue V (2008) BCI competition III: dataset II-ensemble of SVMs for BCI P300 speller. IEEE Trans Biomed Eng 55(3):1147–1154CrossRefGoogle Scholar
  22. Schalk G, McFarland DJ, Hinterberger T, Birbaumer N, Wolpaw JR (2004) BCI 2000: a general-purpose brain–computer interface (BCI) system. IEEE Trans Biomed Eng 51(6):1034–1043CrossRefGoogle Scholar
  23. Selim AE, Wahed MA, Kadah YM (2014) Electrode reduction using ICA and PCA in P300 visual speller brain–computer interface system. In: Biomedical engineering (MECBME), 2014 middle east conference on, IEEE, pp 357–360Google Scholar
  24. Shi LC, Lu BL (2013) EEG-based vigilance estimation using extreme learning machines. Neurocomputing 102:135–143CrossRefGoogle Scholar
  25. Solis-Escalante T, Gentiletti GG, Yanez-Suarez O (2006) Single trial P300 detection based on the empirical mode decomposition. In: 28th Annual international conference of the IEEE engineering in medicine and biology society, 2006. EMBS'06. IEEE, pp 1157–1160Google Scholar
  26. Shi X, Xu G, Shen F, Zhao J (2015) Solving the data imbalance problem of P300 detection via random under-sampling bagging SVMs. In: Neural networks (IJCNN), 2015 international joint conference on, IEEE, pp 1–5Google Scholar
  27. Vaughan TM, Wolpaw JR (2006) The third international meeting on brain-computer interface technology: making a difference. IEEE Trans Neural Syst Rehabil Eng 14(2):126–127CrossRefGoogle Scholar
  28. Zhang JC, Xu YQ, Yao L (2007a) P300 detection using boosting neural networks with application to BCI. In: Complex medical engineering, 2007. CME 2007. IEEE/ICME international conference on, IEEE, pp 1526–1530Google Scholar
  29. Zhang R, Huang GB, Sundararajan N, Saratchandran P (2007b) Multicategory classification using an extreme learning machine for microarray gene expression cancer diagnosis. IEEE/ACM Trans Comput Biol Bioinform 4(3):485–495CrossRefGoogle Scholar
  30. Zong W, Huang GB, Chen Y (2013) Weighted extreme learning machine for imbalance learning. Neurocomputing 101:229–242CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  1. 1.College of Computer ScienceHangzhou Dianzi UniversityHangzhouChina
  2. 2.Fujian Key Laboratory of Rehabilitation TechnologyFuzhouChina

Personalised recommendations