In this paper, we compare the performance of brain-computer interfaces (BCIs) when different feedback modalities are used. In particular, we study the effects of auditory or vibrotactile feedback when presented to reinforce the users' performance (positive feedback) or to correct a poor achievement in controlling the BCI (negative feedback). Then, the performance of different possible combinations of feedback modalities (positive/negative auditory/vibrotactile feedback) is compared against the traditional visual feedback for the case of users operating a BCI based on electroencephalographic (EEG) measurements of motor imaginery tasks. In our experiments, six subjects were trained to operate the BCI and the performance was evaluated throughout several sessions. Our results show that the feedback modality that provides the best overall performance varies among subjects, so it must be personalized. Therefore, we present a selection procedure based on analysis of variance (ANOVA) tests performed at the end of each session in order to find a significant efficiency improvement when operating the BCI and associate such improvement with a learning process. Our results suggest that, at the fourth training session, it can be already established if a feedback modality is in fact helping the person to learn or if a different feedback modality should be tried. Hence, our selection method has the potential to determine the feedback modality that provides the most efficient operation of the BCI for each subject without performing an unnecessary number of training sessions.
|Number of pages||8|
|Publication status||Published - 1 Jan 2014|
|Event||CONIELECOMP 2014 - 24th International Conference on Electronics, Communications and Computers - |
Duration: 1 Jan 2014 → …
|Conference||CONIELECOMP 2014 - 24th International Conference on Electronics, Communications and Computers|
|Period||1/1/14 → …|
Copyright 2014 Elsevier B.V., All rights reserved.
All Science Journal Classification (ASJC) codes
- Computer Networks and Communications
- Electrical and Electronic Engineering