Performances Evaluation and Optimization of Brain Computer Interface Systems in a Copy Spelling Task

Abstract

The evaluation of the performances of brain-computer interface (BCI) systems could be difficult as a standard procedure does not exist. In fact, every research team creates its own experimental protocol (different input signals, different trial structure, different output devices, etc.) and this makes systems comparison difficult. Moreover, the great question is whether these experiments can be extrapolated to real world applications or not. To overcome some intrinsic limitations of the most used criteria a new efficiency indicator will be described and used. Its main advantages are that it can predict with a high accuracy the performances of a whole system, a fact that can be used to successfully improve its behavior. Finally, simulations were performed to illustrate that the best system is built by tuning the transducer (TR) and the control interface (CI), which are the two main components of a BCI system, so that the best TR and the best CI do not exist but just the best combination of them.

Introducing NPXLab 2010: A tool for the analysis and optimization of P300 based brain-computer interfaces

“…In this region one can select the classifiers to use (SWLDA and Support Vector Machine in the figure) and see their performances, according to the metric described in [11]. It is also possible to set some parameters relative to the various classifiers.…”

“…The accuracies of the classification are computed as well as the efficiency, by mean of the metric proposed in [11], where it has been demonstrated that this indicator is a reliable indicator of the performances of real BCI systems.…”

Describing Different Brain Computer Interface Systems Through a Unique Model: A UML Implementation

“…Control interface: it is the module responsible for the encoding as it deals with the translation of a LS or sequences Bianchi et al 2007a), in which the classification performances are stored and that must be updated as the experimental session goes on. Also, as the control interface knows the encoding strategies, it has to furnish to the other actors the maps for the translation of LSs into SSs.…”

Asynchronous gaze-independent event-related potential-based brain–computer interface

“…This approach was validated in healthy subjects [28] and potential end-users [29]. This system was also evaluated with regard to communication efficiency (as defined by Bianchi et al [30]), and the asynchronous system had greater efficiency in terms of communication speed and time to recover from errors compared with the synchronous version [31].…”