Latency correction of event-related potentials between different experimental protocols

被引:40
作者
Iturrate, I. [1 ,2 ]
Chavarriaga, R. [3 ,4 ]
Montesano, L. [1 ,2 ]
Minguez, J. [1 ,2 ,5 ]
Millan, J. D. R. [3 ,4 ]
机构
[1] Inst Invest Ingn Aragon I3A, E-50018 Zaragoza, Spain
[2] Univ Zaragoza, Dept Informat & Ingn Sistemas DIIS, E-50018 Zaragoza, Spain
[3] Ecole Polytech Fed Lausanne, Ctr Neuroprosthet, Chair Noninvas Brain Machine Interface CNBI, CH-1015 Lausanne, Switzerland
[4] Ecole Polytech Fed Lausanne, Inst Bioengn, CH-1015 Lausanne, Switzerland
[5] Bit&Brain Technol SL, E-50018 Zaragoza, Spain
关键词
brain-computer interface; event-related potentials; transfer learning; COMPUTER INTERFACE BCI; P300; COMMUNICATION;
D O I
10.1088/1741-2560/11/3/036005
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
Objective. A fundamental issue in EEG event-related potentials (ERPs) studies is the amount of data required to have an accurate ERP model. This also impacts the time required to train a classifier for a brain-computer interface (BCI). This issue is mainly due to the poor signal-to-noise ratio and the large fluctuations of the EEG caused by several sources of variability. One of these sources is directly related to the experimental protocol or application designed, and may affect the amplitude or latency of ERPs. This usually prevents BCI classifiers from generalizing among different experimental protocols. In this paper, we analyze the effect of the amplitude and the latency variations among different experimental protocols based on the same type of ERP. Approach. We present a method to analyze and compensate for the latency variations in BCI applications. The algorithm has been tested on two widely used ERPs (P300 and observation error potentials), in three experimental protocols in each case. We report the ERP analysis and single-trial classification. Main results. The results obtained show that the designed experimental protocols significantly affect the latency of the recorded potentials but not the amplitudes. Significance. These results show how the use of latency-corrected data can be used to generalize the BCIs, reducing the calibration time when facing a new experimental protocol.
引用
收藏
页数:12
相关论文
共 43 条
  • [1] [Anonymous], 2012, Event-related potentials
  • [2] Arico P, 2013, P TOBI WORSH 4, P53
  • [3] Benjamini Y, 2001, ANN STAT, V29, P1165
  • [4] Berndt D. J., 1994, AAAIWS 94 P 3 INT C, P359
  • [5] Single-trial analysis and classification of ERP components - A tutorial
    Blankertz, Benjamin
    Lemm, Steven
    Treder, Matthias
    Haufe, Stefan
    Mueller, Klaus-Robert
    [J]. NEUROIMAGE, 2011, 56 (02) : 814 - 825
  • [6] The use of the area under the roc curve in the evaluation of machine learning algorithms
    Bradley, AP
    [J]. PATTERN RECOGNITION, 1997, 30 (07) : 1145 - 1159
  • [7] Dynamic time warping in the analysis of event-related potentials
    Casarotto, S
    Bianchi, AM
    Cerutti, S
    Chiarenza, GA
    [J]. IEEE ENGINEERING IN MEDICINE AND BIOLOGY MAGAZINE, 2005, 24 (01): : 68 - 77
  • [8] Chavarriaga R, 2012, IEEE ENG MED BIO, P6723, DOI 10.1109/EMBC.2012.6347537
  • [9] Learning From EEG Error-Related Potentials in Noninvasive Brain-Computer Interfaces
    Chavarriaga, Ricardo
    Millan, Jose del R.
    [J]. IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, 2010, 18 (04) : 381 - 388
  • [10] Development of error-monitoring event-related potentials in adolescents
    Davies, PL
    Segalowitz, SJ
    Gavin, WJ
    [J]. ADOLESCENT BRAIN DEVELOPMENT: VULNERABILITIES AND OPPORTUNITIES, 2004, 1021 : 324 - 328