Limits...
Exploiting Task Constraints for Self-Calibrated Brain-Machine Interface Control Using Error-Related Potentials.

Iturrate I, Grizou J, Omedes J, Oudeyer PY, Lopes M, Montesano L - PLoS ONE (2015)

Bottom Line: This paper presents a new approach for self-calibration BCI for reaching tasks using error-related potentials.The results show that it is possible to have a usable BCI control from the beginning of the experiment without any prior calibration.Furthermore, comparisons with simulations and previous results obtained using standard calibration hint that both the quality of recorded signals and the performance of the system were comparable to those obtained with a standard calibration approach.

View Article: PubMed Central - PubMed

Affiliation: Chair in Brain-Machine Interface (CNBI) and Center for Neuroprosthetics (CNP), École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland; Instituto de Investigación en Ingeniería de Sistemas (I3A), Universidad de Zaragoza, Zaragoza, Spain.

ABSTRACT
This paper presents a new approach for self-calibration BCI for reaching tasks using error-related potentials. The proposed method exploits task constraints to simultaneously calibrate the decoder and control the device, by using a robust likelihood function and an ad-hoc planner to cope with the large uncertainty resulting from the unknown task and decoder. The method has been evaluated in closed-loop online experiments with 8 users using a previously proposed BCI protocol for reaching tasks over a grid. The results show that it is possible to have a usable BCI control from the beginning of the experiment without any prior calibration. Furthermore, comparisons with simulations and previous results obtained using standard calibration hint that both the quality of recorded signals and the performance of the system were comparable to those obtained with a standard calibration approach.

No MeSH data available.


Related in: MedlinePlus

Signal and accuracy comparison with standard calibration.(a) Difference average (error minus correct grand averages) at channel FCz for the 3 subjects that performed the standard calibration and self-calibration protocols. (b) Online mean classification accuracy (± std) of the three subjects after following each calibration procedure, together with the number of calibration trials used for training in the standard calibration approach.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4488878&req=5

pone.0131491.g005: Signal and accuracy comparison with standard calibration.(a) Difference average (error minus correct grand averages) at channel FCz for the 3 subjects that performed the standard calibration and self-calibration protocols. (b) Online mean classification accuracy (± std) of the three subjects after following each calibration procedure, together with the number of calibration trials used for training in the standard calibration approach.

Mentions: Fig 5 shows the comparison with the results obtained in our previous work (see [18]) in terms of EEG signal and classification performance, based on the subjects that followed both calibration approaches (standard calibration and self-calibration). Regarding the grand-averaged signals (Fig 5a), no substantial differences were found on the difference potential, with only slight variations in the amplitude of the peaks. Despite small variations of around 20 ms were found in the peak latencies, these values are below our current event synchronization resolution of 62.50 ms, and thus were mainly due to noise.


Exploiting Task Constraints for Self-Calibrated Brain-Machine Interface Control Using Error-Related Potentials.

Iturrate I, Grizou J, Omedes J, Oudeyer PY, Lopes M, Montesano L - PLoS ONE (2015)

Signal and accuracy comparison with standard calibration.(a) Difference average (error minus correct grand averages) at channel FCz for the 3 subjects that performed the standard calibration and self-calibration protocols. (b) Online mean classification accuracy (± std) of the three subjects after following each calibration procedure, together with the number of calibration trials used for training in the standard calibration approach.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4488878&req=5

pone.0131491.g005: Signal and accuracy comparison with standard calibration.(a) Difference average (error minus correct grand averages) at channel FCz for the 3 subjects that performed the standard calibration and self-calibration protocols. (b) Online mean classification accuracy (± std) of the three subjects after following each calibration procedure, together with the number of calibration trials used for training in the standard calibration approach.
Mentions: Fig 5 shows the comparison with the results obtained in our previous work (see [18]) in terms of EEG signal and classification performance, based on the subjects that followed both calibration approaches (standard calibration and self-calibration). Regarding the grand-averaged signals (Fig 5a), no substantial differences were found on the difference potential, with only slight variations in the amplitude of the peaks. Despite small variations of around 20 ms were found in the peak latencies, these values are below our current event synchronization resolution of 62.50 ms, and thus were mainly due to noise.

Bottom Line: This paper presents a new approach for self-calibration BCI for reaching tasks using error-related potentials.The results show that it is possible to have a usable BCI control from the beginning of the experiment without any prior calibration.Furthermore, comparisons with simulations and previous results obtained using standard calibration hint that both the quality of recorded signals and the performance of the system were comparable to those obtained with a standard calibration approach.

View Article: PubMed Central - PubMed

Affiliation: Chair in Brain-Machine Interface (CNBI) and Center for Neuroprosthetics (CNP), École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland; Instituto de Investigación en Ingeniería de Sistemas (I3A), Universidad de Zaragoza, Zaragoza, Spain.

ABSTRACT
This paper presents a new approach for self-calibration BCI for reaching tasks using error-related potentials. The proposed method exploits task constraints to simultaneously calibrate the decoder and control the device, by using a robust likelihood function and an ad-hoc planner to cope with the large uncertainty resulting from the unknown task and decoder. The method has been evaluated in closed-loop online experiments with 8 users using a previously proposed BCI protocol for reaching tasks over a grid. The results show that it is possible to have a usable BCI control from the beginning of the experiment without any prior calibration. Furthermore, comparisons with simulations and previous results obtained using standard calibration hint that both the quality of recorded signals and the performance of the system were comparable to those obtained with a standard calibration approach.

No MeSH data available.


Related in: MedlinePlus