No abstract

Since the brain-computer interface (BCI) speller was first proposed by Farwell and Donchin, there have been modifications in the visual aspects of P300 paradigms. Most of the changes are based on the original matrix format such as changes in the number of rows and columns, font size, flash/ blank time, and flash order. The improvement in the resulting accuracy and speed of such systems has always been the ultimate goal. In this study, we have compared several different speller paradigms including row-column, single character flashing, and two region-based paradigms which are not based on the matrix format. In the first region-based paradigm, at the first level, characters and symbols are distributed over seven regions alphabetically, while in the second region-based paradigm they are distributed in the most frequently used order. At the second level, each one of the regions is further subdivided into seven subsets. The experimental results showed that the average accuracy and user acceptability for two region-based paradigms were higher than those for traditional paradigms such as row/column and single character.

Abstract. The work presented here investigates how environmental features can be used to help select a task allocation mechanism from a portfolio in a multi-robot exploration scenario. In particular, we look at clusters of task locations and the positions of team members in relation to cluster centres. In a data-driven approach, we conduct experiments that use two different task allocation mechanisms on the same set of scenarios, providing comparative performance data. We then train a classifier on this data, giving us a method for choosing the best mechanism for a given scenario. We show that selecting a mechanism via this method, compared to using a single state-of-the-art mechanism only, can improve team performance in certain environments, according to our metrics.