This work reports an innovative framework toward the practical implementation of tactile sensors based on electrical impedance tomography. Particularly, we tested our framework on the development of a piezoresistive insole-shaped sensor prototype. Our approach couples the implementation of the forward model through a physics-based general purpose FEM software and an ANN model for the inverse problem solution. First, we developed a FEM forward model in COMSOL Multyphysics, and we optimized the parameters of the model to better resemble the prototype characteristics. Then, we trained an ANN model with an “artificial” dataset generated by feeding the forward model with a large set of different conductivity distribution samples and measuring the voltage at the boundary electrodes. For comparison, we employed the forward model also to compute the sensitivity matrix, which is required to apply standard linear reconstruction methods. We statistically compared the performance of the proposed machine learning approach with those of standard linear reconstruction methods. The results on simulated data highlight the higher accuracy of the ANN with respect to the other methods. In particular, the mean conductivity RMSE is 0.8 S/m. Finally, we tested our approach with the physical prototype to evaluate the performance in touch position detection. Again, the ANN achieves the minimum mean position error (5.74 mm), demonstrating the feasibility of using machine learning trained with artificial datasets for solving the inverse problem in EIT-based tactile sensors.

Physiological phenomena exhibit complex behaviours arising at multiple time scales. To investigate them, techniques derived from chaos theory were applied to physiological signals, providing promising results in distinguishing between healthy and pathological states. Fractal-like properties of electrodermal activity (EDA), a well-validated tool for monitoring the autonomic nervous system state, have been reported in previous literature. This study proposes the multiscale complexity index of electrodermal activity ($MComEDA$) to discern different autonomic responses based on EDA signals. This method builds upon our previously proposed algorithm, $ComEDA$, and it is empowered with a coarse-graining procedure to provide a view at multiple time scales of the EDA response. We tested $MComEDA$’s performance on the EDA signals of two publicly available datasets, i.e., the Continuously Annotated Signals of Emotion (CASE) dataset and the Affect, Personality and Mood Research on Individuals and Groups (AMIGOS) dataset, both containing physiological data recorded from healthy participants during the view of ultra-short emotional video clips. Our results highlighted that the values of $MComEDA$ were significantly different (p-value < 0.05 after Wilcoxon signed rank test with Bonferroni’s correction) when comparing high- and low-arousal stimuli. Furthermore, $MComEDA$ outperformed the single-scale approach in discriminating among different valence levels of high-arousal stimuli, e.g., showing significantly different values for scary and amusing stimuli (p-value = 0.024). These findings suggest that a multiscale approach to the nonlinear analysis of EDA signals can improve the information gathered on task-specific autonomic response, even when ultra-short time series are considered.

Human emotions are characterized by a complex interaction between conscious experience, physiological arousal, and social dimension. Although the importance of considering emotion response as a nonlinear dynamical system is widely recognized, mathematical models able to describe the time-varying conscious emotional states are still lacking. In recent literature on Affective Computing, novel annotating tools have been introduced to record continuous self-assessed emotion ratings. These data represent a valuable source to describe the dynamics arising during the conscious experience of emotions. Therefore, in this study, we investigate the trajectories traced in the reconstructed phase space of continuously annotated arousal signals acquired during an experimental protocol of emotion elicitation. We use a subset of the Continuously Anno-tated Signals of Emotions (CASE) dataset, including self-assessed ratings from thirty healthy subjects while watching two video clips: one fear-inducing and one relaxing. We analyse intrinsic irregularity and complexity of arousal time-series, performing Sample Entropy and Distribution Entropy algorithms. Results show a significantly higher complexity of time-varying emotion perception during the scary video compared to the relaxing video. Our findings, although preliminary, highlight a promising field of application of chaos theory methodologies to continuous emotion ratings, which can be exploited for the prediction of pathological moods in ecological settings.

Emotions arise from a complex interplay of various factors, including conscious experience, physiological processes, and contextual elements. Although emotions are inherently dynamic processes, this aspect is oftentimes neglected in experimental protocols. In this study, we employed dynamical systems theory to investigate the time-varying self-assessed emotion ratings. We used the continuous ratings of the publicly available CASE dataset, in which thirty individuals rated their level of arousal and valence while watching videos designed to evoke four different emotions. Firstly, we analyzed the univariate dynamics by reconstructing the phase space from the arousal and valence series separately, and quantified their regularity and spatial complexity by using three metrics: Fuzzy, Sample, and Distribution Entropy. Then, we combined the arousal and valence series and proposed a novel index, the Multichannel Distribution Entropy (MDistEn), to estimate the complexity of the bivariate phase space. By coupling the two dimensions, we found that MDistEn resulted as an effective marker of fear, showing patterns statistically different from all of the other stimuli (p-value $\leq$ 0.001). These findings support the investigation of the time-varying dynamics of annotated emotion ratings as a promising pathway to discriminate the onset of fear-related pathological states.

Emotions arise from a complex interplay of various factors, including conscious experience, physiological processes, and contextual elements. Although emotions are inherently dynamic processes, this aspect is oftentimes neglected in experimental protocols. In this study, we employed dynamical systems theory to investigate the time-varying self-assessed emotion ratings. We used the continuous ratings of the publicly available CASE dataset, in which thirty individuals rated their level of arousal and valence while watching videos designed to evoke four different emotions. Firstly, we analyzed the univariate dynamics by reconstructing the phase space from the arousal and valence series separately and quantified their regularity and spatial complexity by using three metrics: Fuzzy, Sample, and Distribution Entropy. Then, we combined the arousal and valence series by proposing a novel index, the Multichannel Distribution Entropy (MDistEn), to estimate the complexity of the bivariate phase space. By coupling the two dimensions, we found that MDistEn resulted as an effective marker of fear, showing patterns statistically different from all of the other stimuli (p-value≤0.001). These findings support the investigation of the time-varying dynamics of annotated emotion ratings, as a promising pathway to discriminate the onset of fear-related pathological states.