Display options
Cite
Rodríguez-Ugarte M, Iáñez E, Ortíz M, et al. Personalized Offline and Pseudo-Online BCI Models to Detect Pedaling Intent. Front Neuroinform. 2017;11:45doi: 10.3389/fninf.2017.00045.
Rodríguez-Ugarte, M., Iáñez, E., Ortíz, M., & Azorín, J. M. (2017). Personalized Offline and Pseudo-Online BCI Models to Detect Pedaling Intent. Frontiers in neuroinformatics, 1145. https://doi.org/10.3389/fninf.2017.00045
Rodríguez-Ugarte, Marisol, et al. "Personalized Offline and Pseudo-Online BCI Models to Detect Pedaling Intent." Frontiers in neuroinformatics vol. 11 (2017): 45. doi: https://doi.org/10.3389/fninf.2017.00045
Rodríguez-Ugarte M, Iáñez E, Ortíz M, Azorín JM. Personalized Offline and Pseudo-Online BCI Models to Detect Pedaling Intent. Front Neuroinform. 2017 Jul 11;11:45. doi: 10.3389/fninf.2017.00045. eCollection 2017. PMID: 28744212; PMCID: PMC5504298.
Copy Download .nbib Format: NLM
Share it on

Front Neuroinform. 2017 Jul 11;11:45. doi: 10.3389/fninf.2017.00045. eCollection 2017.

Personalized Offline and Pseudo-Online BCI Models to Detect Pedaling Intent.

Frontiers in neuroinformatics

Marisol Rodríguez-Ugarte, Eduardo Iáñez, Mario Ortíz, Jose M Azorín

Affiliations

  1. Brain-Machine Interface Systems Lab, Systems Engineering and Automation Department, Miguel Hernández University of ElcheElche, Spain.

PMID: 28744212 PMCID: PMC5504298 DOI: 10.3389/fninf.2017.00045

Abstract

The aim of this work was to design a personalized BCI model to detect pedaling intention through EEG signals. The approach sought to select the best among many possible BCI models for each subject. The choice was between different processing windows, feature extraction algorithms and electrode configurations. Moreover, data was analyzed offline and pseudo-online (in a way suitable for real-time applications), with a preference for the latter case. A process for selecting the best BCI model was described in detail. Results for the pseudo-online processing with the best BCI model of each subject were on average 76.7% of true positive rate, 4.94 false positives per minute and 55.1% of accuracy. The personalized BCI model approach was also found to be significantly advantageous when compared to the typical approach of using a fixed feature extraction algorithm and electrode configuration. The resulting approach could be used to more robustly interface with lower limb exoskeletons in the context of the rehabilitation of stroke patients.

Keywords: electrode configurations; feature extraction algorithms; offline; pedaling intention; personalized brain-computer interfaces; pseudo-online

References

  1. Electroencephalogr Clin Neurophysiol. 1997 Sep;103(3):386-94 - PubMed
  2. Clin Neurophysiol. 2011 Feb;122(2):364-72 - PubMed
  3. IEEE Trans Biomed Eng. 2008 Feb;55(2 Pt 1):713-20 - PubMed
  4. Biol Psychol. 1977 Mar;5(1):47-82 - PubMed
  5. Front Neurosci. 2014 Nov 25;8:376 - PubMed
  6. Conf Proc IEEE Eng Med Biol Soc. 2014;2014:4127-4130 - PubMed
  7. Front Neuroeng. 2012 Jul 12;5:13 - PubMed
  8. Lancet Neurol. 2008 Nov;7(11):1032-43 - PubMed
  9. J Neural Eng. 2017 Jun;14 (3):036004 - PubMed
  10. J Neuroeng Rehabil. 2014 Nov 15;11:153 - PubMed
  11. Artif Intell Med. 2013 Oct;59(2):133-42 - PubMed
  12. J Neuroeng Rehabil. 2012 Sep 07;9:65 - PubMed
  13. Conf Proc IEEE Eng Med Biol Soc. 2010;2010:4562-5 - PubMed
  14. Behav Neurosci. 2007 Oct;121(5):854-70 - PubMed
  15. J Neuroeng Rehabil. 2015 Dec 12;12 :113 - PubMed
  16. Sensors (Basel). 2014 Sep 29;14(10):18172-86 - PubMed
  17. Clin Neurophysiol. 2015 Jan;126(1):154-9 - PubMed
  18. Electroencephalogr Clin Neurophysiol. 1998 Aug;107(2):69-83 - PubMed
  19. Clin Neurophysiol. 2007 Dec;118(12):2637-55 - PubMed
  20. IEEE Trans Biomed Eng. 2014 Feb;61(2):288-96 - PubMed
  21. Conf Proc IEEE Eng Med Biol Soc. 2016 Aug;2016:1496-1499 - PubMed
  22. Neuroimage. 2006 May 15;31(1):153-9 - PubMed
  23. Clin Neurophysiol. 2011 Mar;122(3):567-77 - PubMed
  24. J Physiol. 2007 Mar 15;579(Pt 3):637-42 - PubMed

Publication Types