Automated Affective Computing Based on Bio-Signals Analysis and Deep Learning Approach

Age-related differences on temporal source memory by using dynamic stimuli: the effects of POV and emotional valence

Previous studies have highlighted that temporal source memory can be influenced by factors such as the individual's age and the emotional valence of the event to be remembered. In this study, we investigated how the different points of view (POVs) from which an event is presented could interact with the relationship between age-related differences and emotional valence on temporal source memory. One hundred and forty-one younger adults (aged 18-30) and 90 older adults (aged 65-74) were presented with a series of emotional videos shot from different POVs (first vs. third-person) in three sessions. In the fourth session, participants were asked to indicate in which session (1, 2, or 3) they viewed each video. The results indicated that the first-person POV amplified the effects of the emotional valence on temporal source memory. Only in this experimental condition, older adults "pushed away" negative stimuli by perceiving them as more distant in time, and "kept closer" positive stimuli by perceiving them as more recent. In comparison, younger adults "kept closer" positive stimuli. These findings add to the existing literature on the positivity effect on temporal source memory and highlighted the importance of considering the POV in relation to the emotional valence.

Detecting Prolonged Stress in Real Life Using Wearable Biosensors and Ecological Momentary Assessments: Naturalistic Experimental Study

BACKGROUND

Increasing efforts toward the prevention of stress-related mental disorders have created a need for unobtrusive real-life monitoring of stress-related symptoms. Wearable devices have emerged as a possible solution to aid in this process, but their use in real-life stress detection has not been systematically investigated.

OBJECTIVE

We aimed to determine the utility of ecological momentary assessments (EMA) and physiological arousal measured through wearable devices in detecting ecologically relevant stress states.

METHODS

Using EMA combined with wearable biosensors for ecological physiological assessments (EPA), we investigated the impact of an ecological stressor (ie, a high-stakes examination week) on physiological arousal and affect compared to a control week without examinations in first-year medical and biomedical science students (51/83, 61.4% female). We first used generalized linear mixed-effects models with maximal fitting approaches to investigate the impact of examination periods on subjective stress exposure, mood, and physiological arousal. We then used machine learning models to investigate whether we could use EMA, wearable biosensors, or the combination of both to classify momentary data (ie, beeps) as belonging to examination or control weeks. We tested both individualized models using a leave-one-beep-out approach and group-based models using a leave-one-subject-out approach.

RESULTS

During stressful high-stakes examination (versus control) weeks, participants reported increased negative affect and decreased positive affect. Intriguingly, physiological arousal decreased on average during the examination week. Time-resolved analyses revealed peaks in physiological arousal associated with both momentary self-reported stress exposure and self-reported positive affect. Mediation models revealed that the decreased physiological arousal in the examination week was mediated by lower positive affect during the same period. We then used machine learning to show that while individualized EMA outperformed EPA in its ability to classify beeps as originating from examinations or from control weeks (1603/4793, 33.45% and 1648/4565, 36.11% error rates, respectively), a combination of EMA and EPA yields optimal classification (1363/4565, 29.87% error rate). Finally, when comparing individualized models to group-based models, we found that the individualized models significantly outperformed the group-based models across all 3 inputs (EMA, EPA, and the combination).

CONCLUSIONS

This study underscores the potential of wearable biosensors for stress-related mental health monitoring. However, it emphasizes the necessity of psychological context in interpreting physiological arousal captured by these devices, as arousal can be related to both positive and negative contexts. Moreover, our findings support a personalized approach in which momentary stress is optimally detected when referenced against an individual's own data.

Assessing Feasibility of Cognitive Impairment Testing Using Social Robotic Technology Augmented with Affective Computing and Emotional State Detection Systems

Social robots represent a valid opportunity to manage the diagnosis, treatment, care, and support of older people with dementia. The aim of this study is to validate the Mini-Mental State Examination (MMSE) test administered by the Pepper robot equipped with systems to detect psychophysical and emotional states in older patients. Our main result is that the Pepper robot is capable of administering the MMSE and that cognitive status is not a determinant in the effective use of a social robot. People with mild cognitive impairment appreciate the robot, as it interacts with them. Acceptability does not relate strictly to the user experience, but the willingness to interact with the robot is an important variable for engagement. We demonstrate the feasibility of a novel approach that, in the future, could lead to more natural human-machine interaction when delivering cognitive tests with the aid of a social robot and a Computational Psychophysiology Module (CPM).

Special Issue "Feature Papers in Biosensors Section 2022"

Biosensors are devices composed of a biorecognition part and of a transduction part [...].

Enabling Remote Responder Bio-Signal Monitoring in a Cooperative Human-Robot Architecture for Search and Rescue

The roles of emergency responders are challenging and often physically demanding, so it is essential that their duties are performed safely and effectively. In this article, we address real-time bio-signal sensor monitoring for responders in disaster scenarios. In particular, we propose the integration of a set of health monitoring sensors suitable for detecting stress, anxiety and physical fatigue in an Internet of Cooperative Agents architecture for search and rescue (SAR) missions (SAR-IoCA), which allows remote control and communication between human and robotic agents and the mission control center. With this purpose, we performed proof-of-concept experiments with a bio-signal sensor suite worn by firefighters in two high-fidelity SAR exercises. Moreover, we conducted a survey, distributed to end-users through the Fire Brigade consortium of the Provincial Council of Málaga, in order to analyze the firefighters' opinion about biological signals monitoring while on duty. As a result of this methodology, we propose a wearable sensor suite design with the aim of providing some easy-to-wear integrated-sensor garments, which are suitable for emergency worker activity. The article offers discussion of user acceptance, performance results and learned lessons.

Psychophysiological Assessment of Children with Cerebral Palsy during Robotic-Assisted Gait Training through Infrared Imaging

Cerebral palsy (CP) is a non-progressive neurologic pathology representing a leading cause of spasticity and concerning gait impairments in children. Robotic-assisted gait training (RAGT) is widely employed to treat this pathology to improve children's gait pattern. Importantly, the effectiveness of the therapy is strictly related to the engagement of the patient in the rehabilitation process, which depends on his/her psychophysiological state. The aim of the study is to evaluate the psychophysiological condition of children with CP during RAGT through infrared thermography (IRT), which was acquired during three sessions in one month. A repeated measure ANOVA was performed (i.e., mean value, standard deviation, and sample entropy) extracted from the temperature time course collected over the nose and corrugator, which are known to be indicative of the psychophysiological state of the individual. Concerning the corrugator, significant differences were found for the sample entropy (F (1.477, 5.907) = 6.888; p = 0.033) and for the mean value (F (1.425, 5.7) = 5.88; p = 0.047). Regarding the nose tip, the sample entropy showed significant differences (F (1.134, 4.536) = 11.5; p = 0.041). The findings from this study suggests that this approach can be used to evaluate in a contactless manner the psychophysiological condition of the children with CP during RAGT, allowing to monitor their engagement to the therapy, increasing the benefits of the treatment.

Automated Emotion Identification Using Fourier-Bessel Domain-Based Entropies

Human dependence on computers is increasing day by day; thus, human interaction with computers must be more dynamic and contextual rather than static or generalized. The development of such devices requires knowledge of the emotional state of the user interacting with it; for this purpose, an emotion recognition system is required. Physiological signals, specifically, electrocardiogram (ECG) and electroencephalogram (EEG), were studied here for the purpose of emotion recognition. This paper proposes novel entropy-based features in the Fourier-Bessel domain instead of the Fourier domain, where frequency resolution is twice that of the latter. Further, to represent such non-stationary signals, the Fourier-Bessel series expansion (FBSE) is used, which has non-stationary basis functions, making it more suitable than the Fourier representation. EEG and ECG signals are decomposed into narrow-band modes using FBSE-based empirical wavelet transform (FBSE-EWT). The proposed entropies of each mode are computed to form the feature vector, which are further used to develop machine learning models. The proposed emotion detection algorithm is evaluated using publicly available DREAMER dataset. K-nearest neighbors (KNN) classifier provides accuracies of 97.84%, 97.91%, and 97.86% for arousal, valence, and dominance classes, respectively. Finally, this paper concludes that the obtained entropy features are suitable for emotion recognition from given physiological signals.