Multimodal Data Fusion based on the Global Workspace Theory
This addresses the problem of improving multimodal data fusion for applications like pain assessment in healthcare, though it appears incremental as it builds on existing cognitive theory.
The paper tackled the challenge of dynamic and unspecified uncertainties in multimodal data fusion by proposing the Global Workspace Network (GWN), achieving an average F1 score of 0.92 for discriminating between pain patients and healthy participants and 0.75 for classifying three pain levels on the EmoPain dataset.
We propose a novel neural network architecture, named the Global Workspace Network (GWN), which addresses the challenge of dynamic and unspecified uncertainties in multimodal data fusion. Our GWN is a model of attention across modalities and evolving through time, and is inspired by the well-established Global Workspace Theory from the field of cognitive science. The GWN achieved average F1 score of 0.92 for discrimination between pain patients and healthy participants and average F1 score = 0.75 for further classification of three pain levels for a patient, both based on the multimodal EmoPain dataset captured from people with chronic pain and healthy people performing different types of exercise movements in unconstrained settings. In these tasks, the GWN significantly outperforms the typical fusion approach of merging by concatenation. We further provide extensive analysis of the behaviour of the GWN and its ability to address uncertainties (hidden noise) in multimodal data.