Control of an electrical prosthesis with an SSVEP-based BCI
Control of an electrical prosthesis with an SSVEP-based BCI
复制标题
DOI:
10.1109/tbme.2007.897815
复制
发表时间:
2008-01-01
影响因子:
4.6
通讯作者:
Pfurtscheller, Gert
中科院分区:
文献类型:
--
作者:
Mueller-Putz, Gernot R.;Pfurtscheller, Gert
Brain-computer interfaces (BCIs) are systems that establish a direct connection between the human brain and a computer, thus providing an additional communication channel. They are used in a broad field of applications nowadays. One important issue is the control of neuroprosthetic devices for the restoration of the grasp function in spinal-cord-injured people. In this communication, an asynchronous (self-paced) four-class BCI based on steady-state visual evoked potentials (SSVEPs) was used to control a two-axes electrical hand prosthesis. During training, four healthy participants reached an online classification accuracy between 44% and 88%. Controlling the prosthetic hand asynchronously, the participants reached a performance of 75.5 to 217.5 s to copy a series of movements, whereas the fastest possible duration determined by the setup was 64 s. The number of false negative (FN) decisions varied from 0 to 10 (the maximal possible decisions were 34). It can be stated that the SSVEP-based BCI, operating in an asynchronous mode, is feasible for the control of neuroprosthetic devices with the flickering lights mounted on its surface.