Transferring brain–computer interfaces beyond the laboratory: Successful application control for motor-disabled users

Abstract

Objectives: Brain-computer interfaces (BCIs) are no longer only used by healthy participants under controlled conditions in laboratory environments, but also by patients and end-users, controlling applications in their homes or clinics, without the BCI experts around. But are the technology and the field mature enough for this? Especially the successful operation of applications -like text entry systems or assistive mobility devices such as tele-presence robots-requires a good level of BCI control. How much training is needed to achieve such a level? Is it possible to train naïve end-users in 10 days to successfully control such applications?Materials and methods: In this work, we report our experiences of training 24 motor-disabled participants at rehabilitation clinics or at the end-users' homes, without BCI experts present. We also share the lessons that we have learned through transferring BCI technologies from the lab to the user's home or clinics.Results: The most important outcome is that fifty percent of the participants achieved good BCI performance and could successfully control the applications (tele-presence robot and text-entry system). In the case of the * Corresponding author. tele-presence robot the participants achieved an average performance ratio of 0.87 (max. 0.97) and for the text entry application a mean of 0.93 (max. 1.0). The lessons learned and the gathered user feedback range from pure BCI problems (technical and handling), to common communication issues among the different people involved, and issues encountered while controlling the applications. Conclusion:The points raised in this paper are very widely applicable and we anticipate that they might be faced similarly by other groups, if they move on to bringing the BCI technology to the end-user, to home environments and towards application prototype control.

The brain-computer interface researcher’s questionnaire: from research to application

“…To our knowledge these studies only involved the use of non-invasive BCIs by people with ALS or disabilities with other etiologies. Interestingly, the topics that can be extracted from these reports correspond largely with the issues identified in the current study, in that performance (accuracy, speed), sensor issues (discomfort and cumbersomeness of using wet electrodes), and system complexity (for both user and caregiver) are recurring themes [20][21][22][23][24]. A significant discrepancy between these studies and the current report, however, is the importance attributed to esthetics and user stigmatization.…”

The effect of multimodal and enriched feedback on SMR-BCI performance

“…For the classification of left versus right hand motor imagery trials Fisher's linear discriminant analysis (LDA) was applied. Three to six features were identified as optimal using the Canonical Discriminant Spatial Patterns (CDSP) method, which best discriminated between the two classification values (left versus right hand) within the motor imagery period (Leeb et al, 2013). A classifier was then built for each pair of MI tasks, with the selected MI pair (highest controllability), and the corresponding EEG channels and PSD features identified by the feature selection process, which were used online to control the BCI.…”

“…After the screening session, power spectral density (PSD) features were computed in 1-second sliding windows (Leeb et al, 2013;Polat and Güneß, 2007). EEG signals were first spatially filtered with a local Laplacian derivation and the PSD was estimated within 4-48 Hz with 2 Hz resolution, accounting for 23 frequency bands per channel.…”

Prediction of command delivery time for BCI

“…The runs consisted of 15 randomly organized trials of each mental task. As mentioned in the previous section, the command delivery time is not the same for all the online trials as the movement of the feedback bar is directly controlled by the classifier output [9].…”