Goal: This paper reports on a novel algorithm for the analysis of electrodermal activity (EDA) using methods of convex optimization. EDA can be considered as one of the most common observation channels of sympathetic nervous system activity, and manifests itself as a change in electrical properties of the skin, such as skin conductance (SC). Methods: The proposed model describes SC as the sum of three terms: the phasic component, the tonic component, and an additive white Gaussian noise term incorporating model prediction errors as well as measurement errors and artifacts. This model is physiologically inspired and fully explains EDA through a rigorous methodology based on Bayesian statistics, mathematical convex optimization, and sparsity. Results: The algorithm was evaluated in three different experimental sessions to test its robustness to noise, its ability to separate and identify stimulus inputs, and its capability of properly describing the activity of the autonomic nervous system in response to strong affective stimulation. Significance: Results are very encouraging, showing good performance of the proposed method and suggesting promising future applicability, e.g., in the field of affective computing.

Affective Computing has emerged as an important field of study that aims to develop systems that can automatically recognize emotions. Up to the present, elicitation has been carried out with non-immersive stimuli. This study, on the other hand, aims to develop an emotion recognition system for affective states evoked through Immersive Virtual Environments. Four alternative virtual rooms were designed to elicit four possible arousal-valence combinations, as described in each quadrant of the Circumplex Model of Affects. An experiment involving the recording of the electroencephalography (EEG) and electrocardiography (ECG) of sixty participants was carried out. A set of features was extracted from these signals using various state-of-the-art metrics that quantify brain and cardiovascular linear and nonlinear dynamics, which were input into a Support Vector Machine classifier to predict the subject’s arousal and valence perception. The model’s accuracy was 75.00% along the arousal dimension and 71.21% along the valence dimension. Our findings validate the use of Immersive Virtual Environments to elicit and automatically recognize different emotional states from neural and cardiac dynamics; this development could have novel applications in fields as diverse as Architecture, Health, Education and Videogames.

This paper reports on how emotional states elicited by affective sounds can be effectively recognized by means of estimates of Autonomic Nervous System (ANS) dynamics. Specifically, emotional states are modeled as a combination of arousal and valence dimensions according to the well-known circumplex model of affect, whereas the ANS dynamics is estimated through standard and nonlinear analysis of Heart rate variability (HRV) exclusively, which is derived from the electrocardiogram (ECG). In addition, Lagged Poincaré Plots of the HRV series were also taken into account. The affective sounds were gathered from the International Affective Digitized Sound System and grouped into four different levels of arousal (intensity) and two levels of valence (unpleasant and pleasant). A group of 27 healthy volunteers were administered with these standardized stimuli while ECG signals were continuously recorded. Then, those HRV features showing significant changes (p $<;$ 0.05 from statistical tests) between the arousal and valence dimensions were used as input of an automatic classification system for the recognition of the four classes of arousal and two classes of valence. Experimental results demonstrated that a quadratic discriminant classifier, tested through Leave-One-Subject-Out procedure, was able to achieve a recognition accuracy of 84.72 percent on the valence dimension, and 84.26 percent on the arousal dimension.

Standard functional assessment of autonomic nervous system (ANS) activity on cardiovascular control relies on spectral analysis of heart rate variability (HRV) series. However, difficulties in obtaining a reliable measure of sympathetic activity from HRV spectra limits the exploitation of sympatho-vagal metrics. On the other hand, measures of electrodermal activity (EDA) have been demonstrated to provide a reliable quantifier of sympathetic dynamics. In this study we propose novel indices of phasic autonomic regulation mechanisms by combining HRV and EDA correlates and thoroughly investigating their time-varying dynamics. HRV and EDA series were gathered from 26 healthy subjects during a cold-pressor test and emotional stimuli. Instantaneous linear and nonlinear (bispectral) estimates of vagal dynamics were obtained from HRV through inhomogeneous point-process models, and combined with a sensitive maker of sympathetic tone from EDA spectral power. A wavelet decomposition analysis was applied to estimate phasic components of the proposed sympatho-vagal indices. Results show significant statistical differences for the proposed indices between the cold-pressor elicitation and previous resting state. Furthermore, an accuracy of 73.08% was achieved for the automatic emotional valence recognition. The proposed nonlinear processing of phasic ANS markers brings novel insights on autonomic functioning that can be exploited in the field of affective computing and psychophysiology.

This paper reports on the autonomic nervous system (ANS) changes and driving style modifications as a response to incremental stressing level stimulation during simulated driving. Fifteen subjects performed a driving simulation experiment consisting of three driving sessions. Starting from a first session where participants performed a steady motorway driving, the experimental protocol includes two additional driving sessions with incremental stress load. More specifically, the first stressing load consists of randomly administering mechanical stimuli to the vehicle during a steady motorway driving by means of a series of sudden and unexpected skids, such as those produced by a strong wind gust. These skids were supposed to produce in the driver a given level of stress. In order to assess this mental workload, dedicated psychological tests were performed. The second stressing load implied an incremental psychological load, consisting of a battery of time pressing arithmetical questions, added to the mechanical stimuli. For the whole experimental session, the driver's physiological signals and the vehicle's mechanical parameters were recorded and analyzed. In this paper, the ANS changes were investigated in terms of heart rate variability, respiration activity, and electrodermal response along with mechanical information such as that coming from steering wheel angle corrections, velocity changes, and time responses. Results are satisfactory and promising. In particular, significant statistical differences were found among the three driving sessions with an increasing stress level both in ANS responses and mechanical parameter changes. In addition, a good recognition of these sessions was carried out by pattern classification algorithms achieving an accuracy greater than 90%.

Virtual reality is a powerful tool in human behaviour research. However, few studies compare its capacity to evoke the same emotional responses as in real scenarios. This study investigates psycho-physiological patterns evoked during the free exploration of an art museum and the museum virtualized through a 3D immersive virtual environment (IVE). An exploratory study involving 60 participants was performed, recording electroencephalographic and electrocardiographic signals using wearable devices. The real vs. virtual psychological comparison was performed using self-assessment emotional response tests, whereas the physiological comparison was performed through Support Vector Machine algorithms, endowed with an effective feature selection procedure for a set of state-of-the-art metrics quantifying cardiovascular and brain linear and nonlinear dynamics. We included an initial calibration phase, using standardized 2D and 360° emotional stimuli, to increase the accuracy of the model. The self-assessments of the physical and virtual museum support the use of IVEs in emotion research. The 2-class (high/low) system accuracy was 71.52% and 77.08% along the arousal and valence dimension, respectively, in the physical museum, and 75.00% and 71.08% in the virtual museum. The previously presented 360° stimuli contributed to increasing the accuracy in the virtual museum. Also, the real vs. virtual classifier accuracy was 95.27%, using only EEG mean phase coherency features, which demonstrates the high involvement of brain synchronization in emotional virtual reality processes. These findings provide an important contribution at a methodological level and to scientific knowledge, which will effectively guide future emotion elicitation and recognition systems using virtual reality.