Optimal processing of surface facial EMG to identify emotional expressions: A data-driven approach.

Surface facial electromyography (EMG) is commonly used to detect emotions from subtle facial expressions. Although there are established procedures for collecting EMG data and some aspects of their processing, there is little agreement among researchers about the optimal way to process the EMG signal, so that the study-unrelated variability (noise) is removed, and the emotion-related variability is best detected. The aim of the current paper was to establish an optimal processing pipeline for EMG data for identifying emotional expressions in facial muscles. We identified the most common processing steps from existing literature and created 72 processing pipelines that represented all the different processing choices. We applied these pipelines to a previously published dataset from a facial mimicry experiment, where 100 adult participants observed happy and sad facial expressions, whilst the activity of their facial muscles, zygomaticus major and corrugator supercilii, was recorded with EMG. We used a resampling approach and subsets of the original data to investigate the effect and robustness of different processing choices on the performance of a logistic regression model that predicted the mimicked emotion (happy/sad) from the EMG signal. In addition, we used a random forest model to identify the most important processing steps for the sensitivity of the logistic regression model. Three processing steps were found to be most impactful: baseline correction, standardisation within muscles, and standardisation within subjects. The chosen feature of interest and the signal averaging had little influence on the sensitivity to the effect. We recommend an optimal processing pipeline, share our code and data, and provide a step-by-step walkthrough for researchers.

Hey Google! Intelligent personal assistants and well-being in the context of disability during COVID-19.

BACKGROUND: Amidst the greatest technological advancement that societies have seen, the (health)care and quality of life of all, and especially of vulnerable individuals, see unprecedented improvements. Intelligent personal assistants (IPAs), such as Google Home (GH), can easily be implemented in their daily lives to facilitate routines. Technology can offer significant benefits for individuals with impairments and/or limitations in achieving greater autonomy and well-being. However, this opportunity still needs to be fully exploited, especially in long-term care facilities. Furthermore, such potential may be particularly needed during social isolation due to health concerns, such as the COVID-19 lockdowns and restrictions. We investigated the validity of implementing GH in residential care for individuals with visual impairments (VIs) and intellectual disabilities (IDs) and assessed the effects of a 10-week intervention on self-reported well-being. METHODS: We used a mixed-methods multiple case studies approach (N = 7) and performed intensive assessments (20 weeks), including self-report well-being questionnaires and observations focusing on well-being, autonomy, social participation and GH experiences. Nonoverlap of all pairs analyses were performed for quantitative data indexing performance differences between intervention phases. Thematic analysis was performed for the qualitative data. RESULTS: We found meaningful improvements in well-being in five clients, while all rated the experience of using GH positively. CONCLUSIONS: Our findings from the quantitative and qualitative analyses document that individuals with VI and/or ID benefit from IPAs in fostering better autonomy by facilitating access to information and entertainment. Further implications and possible barriers to large-scale implementation of IPAs in residential care are discussed.

Eating in Synch: An investigation of parent-infant behaviour coordination during feeding interactions.

During feeding, parents have been described to move their mouth as if they were eating themselves. Such matching of behaviours between parents and their infants during face-to-face interactions represents an example of behavioural synchrony. To date, however, the function of these synchronous eating-like mouth movements by the caregiver remains unexplored. To address this question, two competing hypotheses were tested: 1) the instructional hypothesis proposing that parents make eating-like mouth movements, such as opening and closing their mouth, to demonstrate to their infants what they need to do; 2) the mimicry hypothesis suggesting that parents imitate their infant's mouth actions to enhance affiliation. To test these hypotheses, we examined the temporal dependencies between parents' and infants' mouth movements. We reasoned that parents' mouth movements would occur before their infants' if they serve an instructional purpose, but that they would happen after, if parents mimic their infants. Additionally, we expected that parents' matching mouth movements would be more likely when their infants looked at them in both cases. To examine these hypotheses, fifteen caregivers were observed as they were feeding their six-month-old infants. Time-window sequential analysis was conducted to quantify how likely parents were to display mouth opening and closing before or after their infants did. The results revealed that parents' mouth movements were more likely to follow infants' movements and are thus in line with the mimicry hypothesis. Interestingly, these mouth movements of parents were independent of infant's gaze.