Empatica E4 Wristband Research Articles

Detecting Emotional Arousal and Aggressive Driving Using Neural Networks: A Pilot Study Involving Young Drivers in Duluth.

Driving is integral to many people's daily existence, but aggressive driving behavior increases the risk of road traffic collisions. Young drivers are more prone to aggressive driving and danger perception impairments. A driver's physiological state (e.g., fatigue, anger, or stress) can negatively affect their driving performance. This is especially true for young drivers who have limited driving experience. This research focuses on examining the connection between emotional arousal and aggressive driving behavior in young drivers, using predictive analysis based on electrodermal activity (EDA) data through neural networks. The study involved 20 participants aged 18 to 30, who completed 84 driving sessions. During these sessions, their EDA signals and driving behaviors, including acceleration and braking, were monitored using an Empatica E4 wristband and a telematics device. This study conducted two key analyses using neural networks. The first analysis used a comprehensive set of EDA features to predict emotional arousal, achieving an accuracy of 65%. The second analysis concentrated on predicting aggressive driving behaviors by leveraging the top 10 most significant EDA features identified from the arousal prediction model. Initially, the arousal prediction was performed using the complete set of EDA features, from which feature importance was assessed. The top 10 features with the highest importance were then selected to predict aggressive driving behaviors. Another aggressive driving behavior prediction with a refined set of difference features, representing the changes from baseline EDA values, was also utilized in this analysis to enhance the prediction of aggressive driving events. Despite moderate accuracy, these findings suggest that EDA data, particularly difference features, can be valuable in predicting emotional states and aggressive driving, with future research needed to incorporate additional physiological measures for enhanced predictive performance.

Empatica E4 Assessment of Child Physiological Measures of Listening Effort During Remote and In-Person Communication.

Telepractice is a growing service model that delivers aural rehabilitation to deaf and hard-of hearing children via telecommunications technology. Despite known benefits of telepractice, this delivery approach may increase patients' listening effort (LE) characterized as an allocation of cognitive resources toward an auditory task. The study tested techniques for collecting physiological measures of LE in normal-hearing (NH) children during remote (referred to as tele-) and in-person communication using the wearable Empatica E4 wristband. Participants were 10 children (age range: 9-12 years old) who came to two tele- and two in-person weekly sessions, order counterbalanced. During each session, the children heard a short passage read by the clinical provider, completed an auditory passage comprehension task, and self-rated their effort as a part of the larger study. Measures of electrodermal activity and blood volume pulse amplitude were collected from the child E4 wristband. No differences in child subjective, physiological measures of LE or passage comprehension scores were found between in-person sessions and telesessions. However, an effect of treatment duration on subjective and physiological measures of LE was identified. Children self-reported a significant increase in LE over time. However, their physiological measures demonstrated a trend indicating a decrease in LE. A significant association between subjective measures and the passage comprehension task was found suggesting that those children who reported more effort demonstrated a higher proportion of correct responses. The study demonstrated the feasibility of collection of physiological measures of LE in NH children during remote and in-person communication using the E4 wristband. The results suggest that measures of LE are multidimensional and may reflect different sources of, or cognitive responses to, increased listening demand. https://doi.org/10.23641/asha.27122064.

Comparison of feature learning methods for non-invasive interstitial glucose prediction using wearable sensors in healthy cohorts: a pilot study

BackgroundAlterations in glucose metabolism, especially the postprandial glucose response (PPGR), are crucial contributors to metabolic dysfunction, which underlies the pathogenesis of metabolic syndrome (MetSyn). Personalized low-glycemic diets (PLGD) have shown promise in reducing postprandial glucose spikes. However, current methods such as invasive continuous glucose monitoring (CGM) or multi-omics data integration to assess PPGR come with limitations, including cost and invasiveness, hindering widespread adoption in primary disease prevention. Our aim is to assess machine-learning algorithms for predicting individual PPGR using non-invasive wearable data, thereby circumventing the limitations associated with existing approaches. By identifying the most accurate model, we seek to provide a more accessible and efficient method for managing glucose metabolism. MethodsThis data-driven analysis utilized the experimental dataset from the SENSE (”Systemische Ernährungsmedizin”) study. Healthy participants used an Empatica E4 wristband and Abbott Freestyle Libre 3 CGM for ten days. Blood volume pulse (BVP), electrodermal activity (EDA), heart rate (HR), skin temperature (TEMP), and the corresponding CGM values were measured. Subsequently, four data-driven deep learning (DL) model-convolutional neural network (CNN), lightweight transformer (LTF), long short-term memory with attention (LSTM-A), and Bi-directional LSTM (BiLSTM)-were implemented and compared to determine the potential of DL in predicting interstitial glucose levels without involving food and activity logs. ResultsThe proposed BiLSTM achieved the best interstitial glucose prediction performance, with an average root mean squared error (RMSE) of 13.42 mg/dL, an average mean absolute percentage error (MAPE) of 0.12, and only 3.01% values falling within area D in Clarke error grid analysis (CEGA), incorporating the leave-one-out cross-validation (LOOCV) strategy for a five-minute prediction horizon. ConclusionThe findings of this study may demonstrate the feasibility of transferring knowledge gained from invasive glucose monitoring devices to non-invasive approaches. Furthermore, it emphasizes the promising prospects of combining deep learning with wearable technologies to predict glucose levels in healthy individuals.

The Effects of Virtual Reality-Based Mindfulness Exercises on the Perception of Time, Psychological and Physiological States of Young People: A Randomized Crossover Trial

ObjectivesThe purpose of this study was to assess and compare the efficacy of different electronic devices (VR headsets and tablet devices) supported mindfulness exercises. Contrary to previous studies, we compared the technologies not only regarding psychological but also physiological parameters. Additionally, we assessed time perception as an indicator of flow state, which can increase therapeutic adherence.MethodFifty volunteers (26 females and 24 males) aged 19–28 years (M = 23, SD = 1.93 years) participated in our cross-over trial. A 20-min mindfulness program (Guided Meditation VR™) was shown on both a VR headset and a tablet device, with a 1-week interval in randomized order. Psychological parameters and time perception were assessed through surveys, and an Empatica E4 wristband collected physiological data (heart rate, body temperature, electrodermal activity).ResultsBoth VR- and tablet-based mindfulness programs reduced stress, as reflected by improvements in both anxiety (a 7.06-point reduction in STAI-Y score, p < 0.001) and in-session physiological parameters (a 4.82 bpm reduction in HR, p < 0.001; 1.11 °C increase in body temperature, p < 0.001), without significant differences between the two devices. However, participants perceived the intervention as shorter than its actual time only in the VR condition (VR: 26 shorter, 9 longer out of 47, p = 0.006; tablet: 20 shorter, 14 longer out of 47, p = 0.39).ConclusionsWhile affirming the efficacy of electronic device-supported mindfulness in stress reduction, our study suggests no significant disparity between VR and tablet-supported exercises. Our findings also suggest that participants in the VR session perceived the intervention as shorter than its actual duration.PreregistrationThis study is not preregistered.

An Explainable Deep Learning Approach for Stress Detection in Wearable Sensor Measurements.

Stress has various impacts on the health of human beings. Recent success in wearable sensor development, combined with advancements in deep learning to automatically detect features from raw data, opens several interesting applications related to detecting emotional states. Being able to accurately detect stress-related emotional arousal in an acute setting can positively impact the imminent health status of humans, i.e., through avoiding dangerous locations in an urban traffic setting. This work proposes an explainable deep learning methodology for the automatic detection of stress in physiological sensor data, recorded through a non-invasive wearable sensor device, the Empatica E4 wristband. We propose a Long-Short Term-Memory (LSTM) network, extended through a Deep Generative Ensemble of conditional GANs (LSTM DGE), to deal with the low data regime of sparsely labeled sensor measurements. As explainability is often a main concern of deep learning models, we leverage Integrated Gradients (IG) to highlight the most essential features used by the model for prediction and to compare the results to state-of-the-art expert-based stress-detection methodologies in terms of precision, recall, and interpretability. The results show that our LSTM DGE outperforms the state-of-the-art algorithm by 3 percentage points in terms of recall, and 7.18 percentage points in terms of precision. More importantly, through the use of Integrated Gradients as a layer of explainability, we show that there is a strong overlap between model-derived stress features for electrodermal activity and existing literature, which current state-of-the-art stress detection systems in medical research and psychology are based on.

Using Precision Medicine to Disentangle Genotype-Phenotype Relationships in Twins with Rett Syndrome: A Case Report.

Rett syndrome (RTT) is a paediatric neurodevelopmental disorder spanning four developmental stages. This multi-system disorder offers a unique window to explore genotype-phenotype relationships in a disease model. However, genetic prognosticators of RTT have limited clinical value due to the disorder's heterogeneity on multiple levels. This case report used a precision medicine approach to better understand the clinical phenotype of RTT twins with an identical pathogenic MECP2 mutation and discordant neurodevelopmental profiles. Targeted genotyping, objective physiological monitoring of heart rate variability (HRV) parameters, and clinical severity were assessed in a RTT twin pair (5 years 7 months old) with an identical pathogenic MECP2 mutation. Longitudinal assessment of autonomic HRV parameters was conducted using the Empatica E4 wristband device, and clinical severity was assessed using the RTT-anchored Clinical Global Impression Scale (RTT-CGI) and the Multi-System Profile of Symptoms Scale (MPSS). Genotype data revealed impaired BDNF function for twin A when compared to twin B. Twin A also had poorer autonomic health than twin B, as indicated by lower autonomic metrics (autonomic inflexibility). Hospitalisation, RTT-CGI-S, and MPSS subscale scores were used as measures of clinical severity, and these were worse in twin A. Treatment using buspirone shifted twin A from an inflexible to a flexible autonomic profile. This was mirrored in the MPSS scores, which showed a reduction in autonomic and cardiac symptoms following buspirone treatment. Our findings showed that a combination of a co-occurring rs6265 BDNF polymorphism, and worse autonomic and clinical profiles led to a poorer prognosis for twin A compared to twin B. Buspirone was able to shift a rigid autonomic profile to a more flexible one for twin A and thereby prevent cardiac and autonomic symptoms from worsening. The clinical profile for twin A represents a departure from the disorder trajectory typically observed in RTT and underscores the importance of wider genotype profiling and longitudinal objective physiological monitoring alongside measures of clinical symptoms and severity when assessing genotype-phenotype relationships in RTT patients with identical pathogenic mutations. A precision medicine approach that assesses genetic and physiological risk factors can be extended to other neurodevelopmental disorders to monitor risk when genotype-phenotype relationships are not so obvious.

Wearable Data From Subjects Playing Super Mario, Taking University Exams, or Performing Physical Exercise Help Detect Acute Mood Disorder Episodes via Self-Supervised Learning: Prospective, Exploratory, Observational Study.

Personal sensing, leveraging data passively and near-continuously collected with wearables from patients in their ecological environment, is a promising paradigm to monitor mood disorders (MDs), a major determinant of the worldwide disease burden. However, collecting and annotating wearable data is resource intensive. Studies of this kind can thus typically afford to recruit only a few dozen patients. This constitutes one of the major obstacles to applying modern supervised machine learning techniques to MD detection. In this paper, we overcame this data bottleneck and advanced the detection of acute MD episodes from wearables' data on the back of recent advances in self-supervised learning (SSL). This approach leverages unlabeled data to learn representations during pretraining, subsequently exploited for a supervised task. We collected open access data sets recording with the Empatica E4 wristband spanning different, unrelated to MD monitoring, personal sensing tasks-from emotion recognition in Super Mario players to stress detection in undergraduates-and devised a preprocessing pipeline performing on-/off-body detection, sleep/wake detection, segmentation, and (optionally) feature extraction. With 161 E4-recorded subjects, we introduced E4SelfLearning, the largest-to-date open access collection, and its preprocessing pipeline. We developed a novel E4-tailored transformer (E4mer) architecture, serving as the blueprint for both SSL and fully supervised learning; we assessed whether and under which conditions self-supervised pretraining led to an improvement over fully supervised baselines (ie, the fully supervised E4mer and pre-deep learning algorithms) in detecting acute MD episodes from recording segments taken in 64 (n=32, 50%, acute, n=32, 50%, stable) patients. SSL significantly outperformed fully supervised pipelines using either our novel E4mer or extreme gradient boosting (XGBoost): n=3353 (81.23%) against n=3110 (75.35%; E4mer) and n=2973 (72.02%; XGBoost) correctly classified recording segments from a total of 4128 segments. SSL performance was strongly associated with the specific surrogate task used for pretraining, as well as with unlabeled data availability. We showed that SSL, a paradigm where a model is pretrained on unlabeled data with no need for human annotations before deployment on the supervised target task of interest, helps overcome the annotation bottleneck; the choice of the pretraining surrogate task and the size of unlabeled data for pretraining are key determinants of SSL success. We introduced E4mer, which can be used for SSL, and shared the E4SelfLearning collection, along with its preprocessing pipeline, which can foster and expedite future research into SSL for personal sensing.

Heart rate prediction with contactless active assisted living technology: a smart home approach for older adults.

As global demographics shift toward an aging population, monitoring their heart rate becomes essential, a key physiological metric for cardiovascular health. Traditional methods of heart rate monitoring are often invasive, while recent advancements in Active Assisted Living provide non-invasive alternatives. This study aims to evaluate a novel heart rate prediction method that utilizes contactless smart home technology coupled with machine learning techniques for older adults. The study was conducted in a residential environment equipped with various contactless smart home sensors. We recruited 40 participants, each of whom was instructed to perform 23 types of predefined daily living activities across five phases. Concurrently, heart rate data were collected through Empatica E4 wristband as the benchmark. Analysis of data involved five prominent machine learning models: Support Vector Regression, K-nearest neighbor, Random Forest, Decision Tree, and Multilayer Perceptron. All machine learning models achieved commendable prediction performance, with an average Mean Absolute Error of 7.329. Particularly, Random Forest model outperformed the other models, achieving a Mean Absolute Error of 6.023 and a Scatter Index value of 9.72%. The Random Forest model also showed robust capabilities in capturing the relationship between individuals' daily living activities and their corresponding heart rate responses, with the highest R2 value of 0.782 observed during morning exercise activities. Environmental factors contribute the most to model prediction performance. The utilization of the proposed non-intrusive approach enabled an innovative method to observe heart rate fluctuations during different activities. The findings of this research have significant implications for public health. By predicting heart rate based on contactless smart home technologies for individuals' daily living activities, healthcare providers and public health agencies can gain a comprehensive understanding of an individual's cardiovascular health profile. This valuable information can inform the implementation of personalized interventions, preventive measures, and lifestyle modifications to mitigate the risk of cardiovascular diseases and improve overall health outcomes.

Effects of forest bathing (Shinrin-yoku) in stressed people.

This study aims to explore the physiological effect of forest bathing on stress management. A total of 29 volunteers participated in this pre-post design, which lacked a control group. Several physiological parameters were recorded, including heart rate (HR), heart rate variability (HRV), electrodermal activity (EDA), blood pressure (BP), immunoglobulin A (IGA), and salivary cortisol (sCort). Additionally, the Perceived Stress Scale (PSS-10) was administered before forest exposure. Measurements were taken before and after participants spent 2 days fully immersed in a forest environment. To further assess stress management, participants completed a Mental Arithmetic Task (MAT) before and after forest immersion, during which EDA, HRV, and HR were monitored using an Empatica E4 wristband. Measurements were taken at baseline, during MAT, and afterward (recovery). Participants exhibited moderate perceived stress levels before forest immersion (mean PSS-10 = 21.22, SD = 3.78). Post-forest exposure, there was a significant decrease in sCort (p < 0.05) and EDA (p < 0.001), while HRV increased (p < 0.001), and diastolic blood pressure rose (p < 0.05). ANOVA results from the MAT showed a significant increase in parasympathetic activity across all conditions post-immersion (p < 0.05), except during recovery, while EDA decreased in all conditions post-forest exposure (p < 0.05). Shinrin-yoku significantly improved stress management at a physiological level and could be a valuable intervention for individuals experiencing stress. However, longitudinal studies with a control group are necessary to determine whether these effects are sustained over time. Nonetheless, this study highlights the potential benefits of forest immersion for stress reduction by enhancing sympathovagal balance and the adaptability of the stress response system.

An Automated On-The-Go Unloading System Reduces Harvest Operator Stress Relative to Manual Operation

Highlights Stress was measured in harvest operators who performed on-the-go unloading manually and with an automated system. Automated unloading reduced the average grain cart and combine operator stress rate by 18% and 12%, respectively, compared to manual operation. Harvest operators usually worked more than 9 hours and often worked more than 12 hours per workday during harvest. The use of automated unloading systems could positively affect the health of harvest operators. Abstract. On-the-go unloading improves harvest operational efficiency, but it requires skilled labor because it is challenging and stressful to balance numerous concurrent tasks. Harvest automation reduces workload, stress, and fatigue. The objective of this study was to determine if using a commercially available, automated on-the-go unloading system (Raven Cart AutomationTM, RCA, Raven Industries) would reduce operator stress compared to manual operation. Nine grain cart tractor operators and six combine operators participated in this study. Operators performed their typical harvest operation, except to alternate on-the-go unloading using RCA or operating manually. Skin conductance (electrodermal activity) was measured with an Empatica E4 wristband, and stressful events were quantified. Machine data was collected from the tractor and combine via CAN logs. Over 200 total unload events were analyzed. Grain cart and combine operators using RCA had an 18% (p = 0.022) and 12% (p = 0.18) reduction in stress rate, respectively, compared to operating the grain cart tractor manually. RCA reduced the tractor cross-track error standard deviation by 2.5 cm on straight passes (p &amp;lt; 0.0001). The use of an automated on-the-go unloading system reduces operator stress during harvest and could positively affect the health of operators, especially during the long harvest workdays. Keywords: Agricultural workers, Combine operators, Custom harvesters, Electrodermal activity, Grain cart operators, Guidance systems, Harvest, Skin conductance, Stress, Vehicle automation.

Using Voice and Biofeedback to Predict User Engagement during Product Feedback Interviews

Capturing users’ engagement is crucial for gathering feedback about the features of a software product. In a market-driven context, current approaches to collecting and analyzing users’ feedback are based on techniques leveraging information extracted from product reviews and social media. These approaches are hardly applicable in contexts where online feedback is limited, as for the majority of apps, and software in general. In such cases, companies need to resort to face-to-face interviews to get feedback on their products. In this paper, we propose to utilize biometric data, in terms of physiological and voice features, to complement product feedback interviews with information about the engagement of the user on product-relevant topics. We evaluate our approach by interviewing users while gathering their physiological data (i.e., biofeedback ) using an Empatica E4 wristband, and capturing their voice through the default audio-recorder of a common laptop. Our results show that we can predict users’ engagement by training supervised machine learning algorithms on biofeedback and voice data, and that voice features alone can be sufficiently effective. The best configurations evaluated achieve an average F1 \(\sim 70\% \) in terms of classification performance, and use voice features only. This work is one of the first studies in requirements engineering in which biometrics are used to identify emotions. Furthermore, this is one of the first studies in software engineering that considers voice analysis. The usage of voice features can be particularly helpful for emotion-aware feedback collection in remote communication, either performed by human analysts or voice-based chatbots, and can also be exploited to support the analysis of meetings in software engineering research.

Accessibility first: detecting frustration in web browsing for visually impaired and sighted smartphone users

AbstractSmartphone adoption has become increasingly prevalent in modern society, reflecting the widespread integration of these devices into various aspects of daily life, yet accessibility and usability problems persist. Smartphones pose numerous challenges to individuals with visual impairments (VI). This is due to smaller screen sizes, lack of physical buttons, and prevalent problems. These challenges frustrate users as they are unable to accomplish their goals. In this paper, the physiological response of VI and sighted individuals are compared and examined. The participant's frustration is measured through physiological signals. The GSR is the signal captured to detect the user's frustration caused by the superimposed accessibility and usability web-related issues. GSR, being less obtrusive, is an effective way to measure frustration. There were 13 VI and 16 sighted participants. Using a within-subject and between-subject design, participants completed four tasks, each was completed under frustrating and non-frustrating conditions while wearing an Empatica E4 wristband to collect GSR data. Challenges were both group-specific and mutual. A slowed internet connection and constant page refreshes are frustrating tasks for sighted participants. VI participants faced an unsearchable drop-down list and an inaccessible menu. Pop-up ads and session timeout are common tasks. Among VI participants, there was no significant difference between frustrating and non-frustrating tasks. When VI participants experienced a session timeout, they significantly showed a higher level of arousal. When comparing the physiological responses of sighted and VI participants in the page refresh and session timeout tasks, the results show that the arousal level is significantly higher in VI participants, primarily due to accessibility issues.

Wearable-based human flow experience recognition enhanced by transfer learning methods using emotion data

Background:Flow experience is a specific positive and affective state that occurs when humans are completely absorbed in an activity and forget everything else. This state can lead to high performance, well-being, and productivity at work. Few studies have been conducted to determine the human flow experience using physiological wearable sensor devices. Other studies rely on self-reported data. Methods:In this article, we use physiological data collected from 25 subjects with multimodal sensing devices, in particular the Empatica E4 wristband, the Emotiv Epoc X electroencephalography (EEG) headset, and the Biosignalplux RespiBAN – in arithmetic and reading tasks to automatically discriminate between flow and non-flow states using feature engineering and deep feature learning approaches. The most meaningful wearable device for flow detection is determined by comparing the performances of each device. We also investigate the connection between emotions and flow by testing transfer learning techniques involving an emotion recognition-related task on the source domain. Results:The EEG sensor modalities yielded the best performances with an accuracy of 64.97%, and a macro Averaged F1 (AF1) score of 64.95%. An accuracy of 73.63% and an AF1 score of 72.70% were obtained after fusing all sensor modalities from all devices. Additionally, our proposed transfer learning approach using emotional arousal classification on the DEAP dataset led to an increase in performances with an accuracy of 75.10% and an AF1 score of 74.92%. Conclusion:The results of this study suggest that effective discrimination between flow and non-flow states is possible with multimodal sensor data. The success of transfer learning using the DEAP emotion dataset as a source domain indicates that emotions and flow are connected, and emotion recognition can be used as a latent task to enhance the performance of flow recognition.

Feasibility of wearable sensors in the NICU: Psychophysiological measures of parental stress

BackgroundParents report elevated stress during their infant's NICU hospitalization. Real-time measures may improve our understanding of parental stress in the NICU. AimExamine the feasibility of wearable sensors to describe parental stress in the NICU. Study designIn this prospective feasibility study of 12 parent-infant dyads, parents wore an Empatica E4 wristband to measure psychophysiological stress via electrodermal activity (EDA) during sensory interventions (holding, massage, reading, touch, etc) with their babies. Baseline and intervention periods were delineated during which concurrent monitoring and clinical observations of infant behavior and environmental factors were recorded. Feasibility was assessed by investigating recruitment/enrollment, retention/adherence, acceptability, sensor usability, and changes in EDA waveforms based on potential stressors. For the latter, independent samples t-tests and ANOVA were used to examine differences in EDA from baseline to intervention, and the impact of environmental and infant factors on parent stress were visually analyzed against EDA waveforms. ResultsWearable sensor use in the NICU appeared feasible as assessed by all methods. Preliminary data analysis indicated that overall parent EDA levels during parent-infant interactions were low, and engagement in sensory intervention(s) led to a non-significant increase in parental EDA, measured by both skin conductance levels and non-specific skin conductance responses. Three main patterns of EDA emerged: a temporary increase in EDA at the beginning of the intervention followed by a decrease and plateau, a plateau in EDA from baseline to intervention, and a gradual rise in EDA throughout intervention. Specific environmental and infant factors, such as infant stress and health care providers entering the room, appeared to impact parent stress levels. ConclusionAlthough these preliminary findings provide support for use of EDA in the NICU, future studies are needed.

Wearable Technologies for Electrodermal and Cardiac Activity Measurements: A Comparison between Fitbit Sense, Empatica E4 and Shimmer GSR3.

The capability of measuring specific neurophysiological and autonomic parameters plays a crucial role in the objective evaluation of a human's mental and emotional states. These human aspects are commonly known in the scientific literature to be involved in a wide range of processes, such as stress and arousal. These aspects represent a relevant factor especially in real and operational environments. Neurophysiological autonomic parameters, such as Electrodermal Activity (EDA) and Photoplethysmographic data (PPG), have been usually investigated through research-graded devices, therefore resulting in a high degree of invasiveness, which could negatively interfere with the monitored user's activity. For such a reason, in the last decade, recent consumer-grade wearable devices, usually designed for fitness-tracking purposes, are receiving increasing attention from the scientific community, and are characterized by a higher comfort, ease of use and, therefore, by a higher compatibility with daily-life environments. The present preliminary study was aimed at assessing the reliability of a consumer wearable device, i.e., the Fitbit Sense, with respect to a research-graded wearable, i.e., the Empatica E4 wristband, and a laboratory device, i.e., the Shimmer GSR3+. EDA and PPG data were collected among 12 participants while they performed multiple resting conditions. The results demonstrated that the EDA- and PPG-derived features computed through the wearable and research devices were positively and significantly correlated, while the reliability of the consumer device was significantly lower.

Assessing the association between overcrowding and human physiological stress response in different urban contexts: a case study in Salzburg, Austria

Overcrowding in densely populated urban areas is increasingly becoming an issue for mental health disorders. Yet, only few studies have examined the association between overcrowding in cities and physiological stress responses. Thus, this study employed wearable sensors (a wearable camera, an Empatica E4 wristband and a smartphone-based GPS) to assess the association between overcrowding and human physiological stress response in four types of urban contexts (green space, transit space, commercial space, and blue space). A case study with 26 participants was conducted in Salzburg, Austria. We used Mask R-CNN to detect elements related to overcrowding such as human crowds, sitting facilities, vehicles and bikes from first-person video data collected by wearable cameras, and calculated a change score (CS) to assess human physiological stress response based on galvanic skin response (GSR) and skin temperature from the physiological data collected by the wristband, then this study used statistical and spatial analysis to assess the association between the change score and the above elements. The results demonstrate the feasibility of using sensor-based measurement and quantitative analysis to investigate the relationship between human stress and overcrowding in relation to different urban elements. The findings of this study indicate the importance of considering human crowds, sitting facilities, vehicles and bikes to assess the impact of overcrowding on human stress at street level.

Multi-sensor driver monitoring for drowsiness prediction

Objective Driver monitoring systems are growing in importance as well as capability. This paper reports drowsy driving detection models that use vehicular, behavioral, and physiological data. The objectives were to augment camera-based system with vehicle-based and heart rate variability measures from a wearable device and compare the performance of drowsiness detection models that use these data sources. Timeliness of the models in predicting drowsiness is analyzed. Timeliness refers to how quickly a model can identify drowsiness and, by extension, how far in advance of an adverse event a classification can be given. Methods Behavioral data were provided by a production-type Driver Monitoring System manufactured by Aisin Technical Center of America. Vehicular data were recorded from the National Advanced Driving Simulator’s large-excursion motion-base driving simulator. Physiological data were collected from an Empatica E4 wristband. Forty participants drove the simulator for up to three hours after being awake for at least 16 hours. Periodic measurements of drowsiness were recorded every ten minutes using both observational rating of drowsiness by an external rater and the self-reported Karolinska Sleepiness Scale. Nine binary random forest models were created, using different combinations of data sources and ground truths. Results The classification accuracy of the nine models ranged from 0.77 to 0.92 on a scale from 0 to 1, with 1 indicating a perfect model. The best-performing model included physiological data and used a reduced dataset that eliminated missing data segments after heartrate variability measures were computed. The most timely model was able to detect the presence of drowsiness 6.7 minutes before a drowsy lane departure. Conclusions The addition of physiological measures added a small amount of accuracy to the model performance. Models trained on observational ratings of drowsiness detected drowsiness earlier than those based only on Karolinska Sleepiness Scale, making them more timely in detecting the onset of drowsiness.

A naturalistic study assessing the impact of daytime running lights and vehicle passing events on cyclist’s physiological stress

Bicyclists are vulnerable road users who are at a greater risk for injury and fatality during crashes. Additionally, the “near-miss” incidents they experience during regular trips can increase the perceived risk and deter them from riding again. This paper aims to use naturalistic bicycling data collected in Johnson County, Iowa to: 1) study the effect of factors such as road surface type, parked vehicles, pavement markings and car passing events on cyclists’ physiological stress and 2) understand the effect of daytime running lights (DRL) as an on-bicycle safety system in providing comfort to cyclists and highlight of their presence on the road to other vehicles. A total of 37 participants were recruited to complete trips over two weekends, one weekend with DRL and the other without DRL. Recruitment was specifically targeted toward cyclists who expressed discomfort riding in traffic. Data were collected using a front forward facing camera, GPS, and a vehicle lateral passing distance sensor mounted on the bicycle and a Empatica E4 wrist band (providing physiological data such as electrodermal activity; EDA) worn by the cyclist. Data from those sources were cleaned, processed, merged, and aggregated into time windows depicting car passing and no car passing events. Mixed effects models were used to study the cyclists’ skin conductance response (phasic EDA) and baseline skin conductance level (tonic EDA). Car passing, parked vehicles, and roads with dashed centerline markings were observed to increase the cyclists stress. The use of DRL had negligible impact on cyclist stress on roads.

Validity of the Empatica E4 wristband to estimate resting-state heart rate variability in a lab-based context

Lab research might benefit from the advantages of wearable devices, such as their ease of use, to estimate pulse rate (PR) and pulse rate variability (PRV) as an equivalent for heart rate (HR) and heart rate variability. However, before implementing them in a lab context, the validity of the PR and PRV, also on ultra-short time scales (e.g., 30s), needs to be confirmed. We recorded heart activity simultaneously with an E4 wristband and an ECG device in a seated resting condition for 5 min. Our results showed that HR, RMSSD, SDNN and LF, but not HF, were validly estimated by the E4 wristband. Furthermore, the E4 wristband could validly estimate PR with recording lengths as short as 10s. RMSSD and SDNN were validly estimated using 30s or 120 s or an average of multiple short intervals (10s), while HF likely requires longer recording intervals. Based on this study, we formulated several recommendations for using the E4 wristband in a lab context.

Analyzing the Usability and Acceptability of Wearable Sensors for Health Care Workers

Health care organizations should prevent clinician burnout to improve quality of care, but current methods to detect burnout add work and are retrospective. This study is part of a project developing a system to pre- dict burnout leveraging wearable sensors. It is important to evaluate participants’ reactions and perceptions of the wearable device. Our objective in this study is to evaluate the usability of the Empatica E4 wrist- bands utilized in the larger project, making design recommendations for improvement. Three health care workers from a COVID-19 diagnostic laboratory wore the Empatica E4 wristband during 10-20 shifts, after which they completed a survey that included the System Usability Scale and other questions about their experience and perceptions. The Empatica E4 has marginally acceptable usability; participants identified its size as particularly negative. We recommend keeping the band size inclusive while reducing the bulkiness of the wearable sensor and exploring alternative materials to improve comfort.