Physiological characterization of electrodermal activity enables scalable near real-time autonomic nervous system activation inference

Abstract

Electrodermal activities (EDA) are any electrical phxenomena observed on the skin. Skin conductance (SC), a measure of EDA, shows fluctuations due to autonomic nervous system (ANS) activation induced sweat secretion. Since it can capture psychophysiological information, there is a significant rise in the research work for tracking mental and physiological health with EDA. However, the current state-of-the-art lacks a physiologically motivated approach for real-time inference of ANS activation from EDA. Therefore, firstly, we propose a comprehensive model for the SC dynamics. The proposed model is a 3D state-space representation of the direct secretion of sweat via pore opening and diffusion followed by corresponding evaporation and reabsorption. As the input to the model, we consider a sparse signal representing the ANS activation that causes the sweat glands to produce sweat. Secondly, we derive a scalable fixed-interval smoother-based sparse recovery approach utilizing the proposed comprehensive model to infer the ANS activation enabling edge computation. We incorporate a generalized-cross-validation to tune the sparsity level. Finally, we propose an Expectation-Maximization based deconvolution approach for learning the model parameters during the ANS activation inference. For evaluation, we utilize a dataset with 26 participants, and the results show that our comprehensive state-space model can successfully describe the SC variations with high scalability, showing the feasibility of real-time applications. Results validate that our physiology-motivated state-space model can comprehensively explain the EDA and outperforms all previous approaches. Our findings introduce a whole new perspective and have a broader impact on the standard practices of EDA analysis.

Sparse Multichannel Decomposition of Electrodermal Activity With Physiological Priors

“…Combining these processes, we get a second-order differential equation given by \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} \begin{equation*} \tau _{d} \tau _{r} \frac{d^{2} y_{p} (t)}{dt^{2}}+(\tau _{d}+\tau _{r}) \frac{dy_{p} (t)}{dt} +y_{p} (t)=u(t). \tag{2} \end{equation*}\end{document} where \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} $\tau _{r}$\end{document} and \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} $\tau _{d}$\end{document} are the rise and fall times, respectively, of the SC response assumed to be constant for the entire duration of the experiment following the assumption made in previous studies [9] , [10] , [11] , [24] , [27] . \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} $u(t)$\end{document} is defined as a summation of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} $N$\end{document} weighted and shifted impulse functions.…”

“…The extraction of reliable arousal state information from Skin Conductance (SC) signals calls for the effective separation of tonic and phasic components, a process crucial to understanding distinct physiological stimuli [8] . Previous studies [10] , [11] , [24] , [25] , [26] , [27] , [28] , [29] , [30] , [31] , [32] , [33] , [34] , [35] , [36] , [37] , [38] have made strides towards this goal, predominantly employing single-channel data. This study innovates by applying a multi-channel approach, concurrently separating tonic and phasic components from SC data, using physiological priors as an inherent part of the optimization problem.…”

Biomarkers of Anxiety and Depression – A Novel Method of Tracking the Autonomic Nervous System with Machine Learning

“…A commonly used measure of EDA is the continuous exosomatic recording of skin conductance (SC). 70 The SC level or the tonic component of EDA is the slow-moving, spontaneous electrical fluctuations of the sweat gland activity that results from an interaction between tonic discharges of sympathetic innervation and local factors like skin temperature and hydration. 71 The fast-changing element of the EDA signal is referred to as the Skin Conductance Response (SCR) and SCR is correlated with phasic sympathetic nervous discharges.…”

Comparative Analysis of Electrodermal Activity Decomposition Methods in Emotion Detection Using Machine Learning

“…The performance of emotion detection highly relies on decomposition methods, so it's essential to find a reliable decomposition technique that will improve the human emotion monitoring system. Researchers have proposed a variety of EDA decomposition methods such as non-negative deconvolution, dynamic causal modelling, cubic-spline-based nonnegative sparse deconvolution (cvxEDA), compressed sensing, non-negative sparse deconvolution (SparsEDA) [3] and BayesianEDA [4]. The performance of the decomposition methods can be evaluated using feature extraction methods and machine learning algorithms.…”