New Applications of Late Fusion Methods for EEG Signal Processing

• Published in: 2019 International Conference on Computational Science and Computational Intelligence (CSCI) pp. 617 - 621
• Main Authors: Safont, Gonzalo, Salazar, Addisson, Vergara, Luis
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.12.2019
• Subjects: alpha integration; classification; EEG; Electroencephalography; Estimation; Feature extraction; Independent component analysis; late fusion; Mixture models; neuropsychological tests; Probability density function; Resource description framework
• DOI: 10.1109/CSCI49370.2019.00116

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.