AI-Driven Analysis of Electrodermal and Multimodal Biosignals for Autonomic and Neurocognitive State Monitoring

The autonomic nervous system and the brain interact continuously to shape emotional, cognitive, and physiological states. Electrodermal activity (EDA), long recognized as a sensitive marker of sympathetic arousal, is now increasingly paired with EEG, fNIRS, and other neural signals to build richer, AI-driven models of autonomic-neural function. Advances in machine learning, deep learning, and nonlinear signal processing have made it possible to extract subtle, previously inaccessible patterns from these biosignals — enabling new tools for stress detection, pain assessment, cognitive workload estimation, sleep and arousal monitoring, and early detection of autonomic or neurocognitive dysfunction.This Research Topic focuses on computational and AI methods for processing and interpreting electrodermal activity alongside neural and other physiological signals to characterize autonomic-neural interactions. We invite original research articles, reviews, and methodological papers that advance robust, interpretable, and clinically translatable AI approaches to biosignal analysis, with an emphasis on studies that combine electrodermal activity with neural or other physiological modalities.We welcome contributions on:- Novel signal processing algorithms (time-frequency, nonlinear dynamics, fractal analysis)- Machine learning and deep learning models for biosignal classification and prediction- Wearable and mobile sensing platforms- Multimodal fusion of EDA with EEG/fNIRS- Explainable AI applied to autonomic-neural biomarkers- Validated applications in stress and emotion recognition, pain assessment, driver and operator state monitoring, and neurocognitive health tracking Topic editors: Yedukondala Rao Veeranki, Hugo F. Posada-Quintero Source: https://www.frontiersin.org/research-topics/84726/ai-driven-analysis-of-electrodermal-and-multimodal-biosignals-for-autonomic-and-neurocognitive-state-monitoring