New Applications of Late Fusion Methods for EEG Signal Processing

Abstract

Decision fusion consists in the combination of the outputs of multiple classifiers into a common decision that is more precise or stable. In most cases, however, only classical fusion techniques are considered. This work compares the performance of several state-of-the-art fusion methods on new applications of automatic stage classification of several neuropsychological tests. The tests were staged into three classes: stimulus display, retention interval, and subject response. The considered late fusion methods were: alpha integration; copulas; Dempster-Shafer combination; independent component analysis mixture models; and behavior knowledge space. Late fusion was able to improve the performance for the task, with alpha integration yielding the most stable result.