Key result
A personalized probabilistic point-process nonlinear model using heartbeat dynamics achieved an overall accuracy of 79.29% in recognizing four emotional states during short-time visual stimuli.
Population
30 healthy subjects, not suffering from cardiovascular and evident mental pathologies, with Patient Health…
Comparison
Personalized probabilistic point-process… vs Basic linear point-process model.
Authors
Loading...
May enable real-time affective monitoring in research settings; leaves open validation before clinical adoption.
Observational (n=30)
No
A personalized probabilistic point-process nonlinear model can accurately characterize emotional states in real-time using only short-term heartbeat dynamics.
Valenza et al. (2014) conducted an observational in Healthy subjects (emotion recognition) (n=30). Personalized probabilistic point-process nonlinear model (NARI) vs. Linear point-process model was evaluated on Overall accuracy in recognizing four emotional states (sadness, anger, happiness, relaxation). A personalized probabilistic point-process nonlinear model using heartbeat dynamics achieved an overall accuracy of 79.29% in recognizing four emotional states during short-time visual stimuli.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: