Abstract
Technology has tremendously contributed to improving communication and facilitating daily activities. Brain-Computer Interface (BCI) study particularly emerged from the need to serve people with disabilities such as Amyotrophic Lateral Sclerosis (ALS). However, with the advancements in cost-effective electronics and computer interface equipment, the BCI study is flourishing, and the exploration of BCI applications for people without disabilities, to enhance normal functioning, is increasing. Particularly, the P300-based spellers are among the most promising applications of the BCI technology. In this context, the region-based paradigm for P300 BCI spellers was introduced in an effort to reduce the crowding effect and adjacency problem that might affect the detection of P300 peak. This study extends this line of research by investigating the effect, in terms of accuracy and usability, of the letters' distribution among the speller's regions. For this purpose, a clustering algorithm is proposed, and two region-based layouts were generated by redistributing the letters based on their dissimilarity or their similarity. A pilot usability evaluation was also conducted in order to assess the usability of the different layouts in terms of effectiveness, efficiency, and satisfaction. The results indicate that the distribution of the letters has an effect on the classification accuracy as well as the user experience. Particularly, when considering short-term accuracy and cognitive effort, the original region-based layout outperforms other layouts.