Collaborative Brain-Computer Interface for Aiding Decision-Making

Abstract

We look at the possibility of integrating the percepts from multiple non-communicating observers as a means of achieving better joint perception and better group decisions. Our approach involves the combination of a brain-computer interface with human behavioural responses. To test ideas in controlled conditions, we asked observers to perform a simple matching task involving the rapid sequential presentation of pairs of visual patterns and the subsequent decision as whether the two patterns in a pair were the same or different. We recorded the response times of observers as well as a neural feature which predicts incorrect decisions and, thus, indirectly indicates the confidence of the decisions made by the observers. We then built a composite neuro-behavioural feature which optimally combines the two measures. For group decisions, we uses a majority rule and three rules which weigh the decisions of each observer based on response times and our neural and neuro-behavioural features. Results indicate that the integration of behavioural responses and neural features can significantly improve accuracy when compared with the majority rule. An analysis of event-related potentials indicates that substantial differences are present in the proximity of the response for correct and incorrect trials, further corroborating the idea of using hybrids of brain-computer interfaces and traditional strategies for improving decision making.

Enhancement of Group Perception via a Collaborative Brain–Computer Interface

“…Studies and applications of cBCIs include systems for a movement planning task [27], visual discrimination between rapidly presented pictures of cars and faces [28], [29], detecting the onset of visual stimuli presented on a black background [30], joint 2-D cursor control [31], rapid discrimination of airplanes in aerial images of urban environments [32] and group decision-making for a simple visual-matching task [15].…”

“…In particular, in [15] participants had to decide whether or not two sets of 2-D shapes were identical. These were presented for a very short time, thus making individual (non-BCI) decisions difficult and often erroneous.…”

“…That is, while all previous cBCIs had been able to improve either speed or accuracy over single non-BCI users, for the first time, the system developed in [15] provably allowed cBCI-assisted groups to make more accurate decisions than groups performing the same tasks by traditional means.…”

“…Like the cBCI in [15], this is a hybrid system in that it uses both the responses of the users and EEG and physiological measurements in order to produce better group decisions. This paper extends the framework proposed in [15] along four main directions.…”

“…In previous research [15] we have suggested that, in circumstances where groups decisions are hampered, a system would be desirable that could provide the advantages of groups (e.g., pooling of information) while avoiding their pitfalls, many of which are caused by the direct interaction of the group members. We have, therefore, proposed and tested the idea that group decisions can be improved by estimating the confidence and combining the independent decisions of non-interacting members of a group.…”