Extraction of Single-Trail N400 Event-Related Potentials Based on Dynamic Independent Component Analysis

  • Wen-Juan Li
  • Xiao-Pei Wu
Conference paper


The Independent Component Analysis (ICA) method has a good application in EEG. But ICA algorithm is mostly a combination of static model and batch optimization algorithm. Considering the non-stationary characteristics of event-related potentials, the Dynamic Independent Component Analysis (DICA) based on kurtosis maximization was proposed to single-trail extract the event-related potential N400 which is induced by the Chinese idioms whose last word is incorrect. The DICA method achieved satisfactory results.


Event-related potential (ERP) EEG signal-trail extraction dynamic independent component analysis (DICA) 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Pan YF.: Evoked potentials in medical practice. 2nd edn. Beijing: People’s Medical Publishing House (2000): 579–622.Google Scholar
  2. 2.
    Kutas M, et al.: Event-related potentials symmetries during the reading sentences. Electroencephalography and Clinical Neurophysiology (1988) 69: 23–218.CrossRefGoogle Scholar
  3. 3.
    Hyvarinen, A., Karhunen, J., Oja, E.: Independent component analysis[M]. New York, A Wily-Interscience Publication (2001): 165–178.CrossRefGoogle Scholar
  4. 4.
    Makeig, S., Bell, A.J., Jung, T., & Sejnowski, T.J. Scott Making: Independent Component Analysis of Electroencephalographic Data. Advances in Neural Information Processing Systems [J] (1996) 8: 145–151.Google Scholar
  5. 5.
    Xiao-Pei Wu, Zhong-Fu Ye, Xiao-Jing Guo, Dao-Xin Zhang, Ren-Jun Hu: Independent Component Analysis Based on Sliding Window[J]. Journal of Computer Research and Development (2007) 44(1): 185–191.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Wen-Juan Li
    • 1
  • Xiao-Pei Wu
  1. 1.The Key Laboratory of Intelligent Computing & Signal Processing of Ministry of EducationAnhui UniversityChina

Personalised recommendations