Detection of maternal and fetal stress from the electrocardiogram with self-supervised representation learning

In the pregnant mother and her fetus, chronic prenatal stress results in entrainment of the fetal heartbeat by the maternal heartbeat, quantified by the fetal stress index (FSI). Deep learning (DL) is capable of pattern detection in complex medical data with high accuracy in noisy real-life environments, but little is known about DL’s utility in non-invasive biometric monitoring during pregnancy. A recently established self-supervised learning (SSL) approach to DL provides emotional recognition from electrocardiogram (ECG). We hypothesized that SSL will identify chronically stressed mother-fetus dyads from the raw maternal abdominal electrocardiograms (aECG), containing fetal and maternal ECG. Chronically stressed mothers and controls matched at enrolment at 32 weeks of gestation were studied. We validated the chronic stress exposure by psychological inventory, maternal hair cortisol and FSI. We tested two variants of SSL architecture, one trained on the generic ECG features for emotional recognition obtained from public datasets and another transfer-learned on a subset of our data. Our DL models accurately detect the chronic stress exposure group (AUROC = 0.982 ± 0.002), the individual psychological stress score (R2 = 0.943 ± 0.009) and FSI at 34 weeks of gestation (R2 = 0.946 ± 0.013), as well as the maternal hair cortisol at birth reflecting chronic stress exposure (0.931 ± 0.006). The best performance was achieved with the DL model trained on the public dataset and using maternal ECG alone. The present DL approach provides a novel source of physiological insights into complex multi-modal relationships between different regulatory systems exposed to chronic stress. The final DL model can be deployed in low-cost regular ECG biosensors as a simple, ubiquitous early stress detection and monitoring tool during pregnancy. This discovery should enable early behavioral interventions.

Masked Emotions: Do Face Mask Patterns and Colors Affect the Recognition of Emotions?

Previous research has shown that face masks restrain the ability to perceive social information and readability of emotions. These studies mostly explored the effect of standard medical, often white masks on emotion recognition. However, in reality, many individuals prefer masks with different styles. We investigated whether the appearance of the mask (pattern-angular vs. curvy and color-black vs. white) affected the recognition of emotional states. Participants were asked to identify the emotions on faces covered by masks with different designs. The presence of masks impeded emotional recognition, dropping the accuracy and confidence and increasing reaction times. There were no main effects of angularity vs. curvature or color on emotion recognition, which suggests that mask design may not impair the recognition beyond the effect of mere mask wearing. Besides, we found relationships between individual difference variables such as mask wearing attitudes, mask design preferences, individual traits and emotional recognition. The majority of participants demonstrated positive attitudes towards mask wearing and preferred non-patterned black and white masks. Preferences for white masks were associated with better emotional recognition of masked faces. In contrast, those with negative attitudes towards masks showed lower performance in emotional recognition for masked faces, preferring patterned more than plain masks, perhaps viewing masks as a fashion item rather than a necessity. Moreover, preferences to wear patterned masks were negatively related to actual wearing masks indoors and perceived risks of COVID.

Emotions and the Systematization of Connective Labor

A profusion of jobs has arisen in contemporary capitalism involving ‘connective labor’, or the work of emotional recognition. Yet the expansion of this interpersonal work occurs at the same time as its systematization, as pressures of efficiency, measurement and automation reshape the work, generating a ‘colliding intensification’. Existing scholarship offers three different ways of understanding the role of emotions in connective labor – as tool, commodity or vulnerability – depending on their view of systematization as useful, inseparable or dehumanizing. Based on 106 in-depth interviews and 300+ hours of observations, I found that vestiges of all three models lurked in the experience of providing connective labor, yet none fully captured the profound meaning practitioners reported finding in their work. Systems varied on three dimensions, reflecting the relative worth of worker, recipient or the work, extracting value from the forged connections, while the meanings workers derived shaped their perspective on its systematization.

Separable convolutional neural networks for facial expressions recognition

Social interactions are important for us, humans, as social creatures. Emotions play an important part in social interactions. They usually express meanings along with the spoken utterances to the interlocutors. Automatic facial expressions recognition is one technique to automatically capture, recognise, and understand emotions from the interlocutor. Many techniques proposed to increase the accuracy of emotions recognition from facial cues. Architecture such as convolutional neural networks demonstrates promising results for emotions recognition. However, most of the current models of convolutional neural networks require an enormous computational power to train and process emotional recognition. This research aims to build compact networks with depthwise separable layers while also maintaining performance. Three datasets and three other similar architectures were used to be compared with the proposed architecture. The results show that the proposed architecture performed the best among the other architectures. It achieved up to 13% better accuracy and 6–71% smaller and more compact than the other architectures. The best testing accuracy achieved by the architecture was 99.4%.

Empathic gaze: a study of human resource professionals

PurposeThe purpose of this viewpoint paper is to explore the fixation of the eyes of human resource (HR) professionals' when identifying emotions in the context of workplace research and to propose measures that might support them in their role.Design/methodology/approachThis paper combines a contemporary literature review with reflections from practice to develop more nuanced understandings of 39 HR professionals' ability to recognise emotions. This paper used eye-tracking technology more commonly used in laboratory-based students to explore the fixation of the eye when identifying emotions.FindingsThe preliminary findings suggest that HR professionals with higher levels of emotional recognition principally focus on the eyes of the recipient, whereas those with lower levels or emotional recognition focus more so the nose or the randomly across the face, depending on the level of emotional recognition. The data suggest that women are better than men, in the sample group at recognising emotions, with some variations in recognising specific emotions such as disgust.Research limitations/implicationsThe viewpoint paper proposes a number of implications for middle leaders and suggests that middle leaders should proactively seek out opportunities to be engaged in activities that support the Default Mode Network (DMN) function of the brain and subsequently the relationship-orientated aspects of leadership, for example, coaching other staff members. However, it has to be recognised that the sample size is small and further work is needed before any generalisations can be made.Originality/valueThis paper offers a contemporary review underpinned by a preliminary study into HR professionals' ability to recognise emotions.