Live intelligence

Latest AI updates

1 updates
Research

InertiaMPDD: Multimodal Personalized Depression Detection via Emotional Inertia-Inspired Dynamics Modeling

The paper introduces InertiaMPDD, a multimodal depression screening method that models emotional inertia by learning healthy next-state patterns with a world-model-inspired latent predictor. It derives reference-derived emotional dynamics descriptors from deviations, residual decay rates, and Jacobian spectral properties, and evaluates them as candidate proxy biomarkers for standalone screening and personalized decision correction. Across five cohorts from four datasets, fusion reaches 98.41% F1 on D-Vlog and 84.98% on LMVD, while standalone descriptors outperform fixed additive fusion on MPDD but discriminate weakly on AVEC2014. The findings highlight that reference informativeness and fusion benefit are distinct and context-dependent.

depression screeningmultimodal machine learningaffective computing