A Network-based Multimodal Data Fusion Approach for Characterizing Dynamic Multimodal Physiological Patterns
This work addresses the problem of understanding emotional states through physiological responses for researchers in affective computing or biomedical engineering, but it appears incremental as it builds on existing network and fusion methods.
The study tackled the problem of characterizing dynamic multimodal physiological patterns by presenting a novel multimodal data fusion approach to construct a complex network modeling interactions of biological subsystems under emotional states, using joint recurrence plot and temporal network metrics, and evaluated it on a benchmark public dataset.
Characterizing the dynamic interactive patterns of complex systems helps gain in-depth understanding of how components interrelate with each other while performing certain functions as a whole. In this study, we present a novel multimodal data fusion approach to construct a complex network, which models the interactions of biological subsystems in the human body under emotional states through physiological responses. Joint recurrence plot and temporal network metrics are employed to integrate the multimodal information at the signal level. A benchmark public dataset of is used for evaluating our model.