Electrodermal Activity Signals Research Articles

Machine Learning-Based Anxiety Detection in Older Adults Using Wristband Sensors and Context Feature

This paper explores a novel method for anxiety detection in older adults using simple wristband sensors such as electrodermal activity (EDA) and photoplethysmogram (PPG) and a context-based feature. The proposed method for anxiety detection combines features from a single physiological signal with an experimental context-based feature to improve the performance of the anxiety detection model. The experimental data for this work are obtained from a year-long experiment on 41 healthy older adults (26 females and 15 males) in the age range 60–80 with mean age \(73.36 \pm 5.25\) during a Trier Social Stress Test (TSST) protocol. The anxiety level ground truth was obtained from State–Trait Anxiety Inventory (STAI), which is regarded as the gold standard to measure perceived anxiety. EDA and blood volume pulse (BVP) signals were recorded using a wrist-worn EDA and PPG sensor, respectively. 47 features were computed from EDA and BVP signal, out of which a final set of 24 significantly correlated features were selected for analysis. The phases of the experimental study are encoded as unique integers to generate the context feature vector. A combination of features from a single sensor with the context feature vector is used for training a machine learning model to distinguish between anxious and not-anxious states. Results and analysis showed that the EDA and BVP machine learning models that combined the context feature along with the physiological features achieved 3.37% and 6.41% higher accuracy, respectively, than the models that used only physiological features. Further, end-to-end processing of EDA and BVP signals was simulated for real-time anxiety level detection. This work demonstrates the practicality of the proposed anxiety detection method in facilitating long-term monitoring of anxiety in older adults using low-cost consumer devices.

Real-Time High-Level Acute Pain Detection Using a Smartphone and a Wrist-Worn Electrodermal Activity Sensor.

The subjectiveness of pain can lead to inaccurate prescribing of pain medication, which can exacerbate drug addiction and overdose. Given that pain is often experienced in patients’ homes, there is an urgent need for ambulatory devices that can quantify pain in real-time. We implemented three time- and frequency-domain electrodermal activity (EDA) indices in our smartphone application that collects EDA signals using a wrist-worn device. We then evaluated our computational algorithms using thermal grill data from ten subjects. The thermal grill delivered a level of pain that was calibrated for each subject to be 8 out of 10 on a visual analog scale (VAS). Furthermore, we simulated the real-time processing of the smartphone application using a dataset pre-collected from another group of fifteen subjects who underwent pain stimulation using electrical pulses, which elicited a VAS pain score level 7 out of 10. All EDA features showed significant difference between painless and pain segments, termed for the 5-s segments before and after each pain stimulus. Random forest showed the highest accuracy in detecting pain, 81.5%, with 78.9% sensitivity and 84.2% specificity with leave-one-subject-out cross-validation approach. Our results show the potential of a smartphone application to provide near real-time objective pain detection.

Simultaneous Monitoring of ECG and EDA Using a Wearable Armband for Analyzing Sympathetic Nerve Activity

Simultaneous Monitoring of ECG and EDA Using a Wearable Armband for Analyzing Sympathetic Nerve Activity

Non-Parametric Classifiers Based Emotion Classification Using Electrodermal Activity and Modified Hjorth Features.

In this work, an attempt has been made to classify various emotional states in Electrodermal Activity (EDA) signals using modified Hjorth features and non-parametric classifiers. For this, the EDA signals are collected from a publicly available online database. The EDA is decomposed into SCL (Skin Conductance Level) and SCR (Skin Conductance Response). Five features, namely activity, mobility, complexity, chaos, and hazard, collectively known as modified Hjorth features, are extracted from SCR and SCL. Four non-parametric classifiers, namely, random forest, k-nearest neighbor, support vector machine, and rotation forest, are used for the classification. The results demonstrate that the proposed approach can classify the emotional states in EDA. Most of the features exhibit statistical significance in discriminating emotional states. It is found that the combination of modified Hjorth features and rotation forest is most accurate in classifying the emotional states. Thus, the result demonstrates that this method can recognize valence and arousal dimensions under various clinical conditions.

Psychophysiological Modeling of Trust In Technology

Trust as a precursor for users' acceptance of artificial intelligence (AI) technologies that operate as a conceptual extension of humans (e.g., autonomous vehicles (AVs)) is highly influenced by users' risk perception amongst other factors. Prior studies that investigated the interplay between risk and trust perception recommended the development of real-time tools for monitoring cognitive states (e.g., trust). The primary objective of this study was to investigate a feature selection method that yields feature sets that can help develop a highly optimized and stable ensemble trust classifier model. The secondary objective of this study was to investigate how varying levels of risk perception influence users' trust and overall reliance on technology. A within-subject four-condition experiment was implemented with an AV driving game. This experiment involved 25 participants, and their electroencephalogram, electrodermal activity, and facial electromyogram psychophysiological signals were acquired. We applied wrapper, filter, and hybrid feature selection methods on the 82 features extracted from the psychophysiological signals. We trained and tested five voting-based ensemble trust classifier models using training and testing datasets containing only the features identified by the feature selection methods. The results indicate the superiority of the hybrid feature selection method over other methods in terms of model performance. In addition, the self-reported trust measurement and overall reliance of participants on the technology (AV) measured with joystick movements throughout the game reveals that a reduction in risk results in an increase in trust and overall reliance on technology.

Validation of Affect-tag Affective and Cognitive Indicators.

The Affect-tag solution measures physiological signals to deliver indicators derived from cognitive science. To provide the most accurate and effective results, a database of electrodermal activity (EDA) signals acquired using the Affect-tag A1 band was created. An experimental paradigm was designed to measure action-taking, autonomic regulation, cognitive load (CL), emotions, and stress, affects, and social stress. The Affect-tag emotional power (EP), emotional density (ED), and CL affective and cognitive indicators were refined based on the physiological responses of 48 participants during these tasks. Statistical significance was obtained for all indicators in tasks they were designed to measure, resulting in a total accuracy score of 89% for the combined indicators. Data obtained during this study will be further analyzed to define emotional and affective states.

Non-invasive wearable seizure detection using long–short-term memory networks with transfer learning

Objective. The detection of seizures using wearable devices would improve epilepsy management, but reliable detection of seizures in an ambulatory environment remains challenging, and current studies lack concurrent validation of seizures using electroencephalography (EEG) data. Approach. An adaptively trained long–short-term memory deep neural network was developed and trained using a modest number of seizure data sets from wrist-worn devices. Transfer learning was used to adapt a classifier that was initially trained on intracranial electroencephalography (iEEG) signals to facilitate classification of non-EEG physiological datasets comprising accelerometry, blood volume pulse, skin electrodermal activity, heart rate, and temperature signals. The algorithm’s performance was assessed with and without pre-training on iEEG signals and transfer learning. To assess the performance of the seizure detection classifier using long-term ambulatory data, wearable devices were used for multiple months with an implanted neurostimulator capable of recording iEEG signals, which provided independent electrographic seizure detections that were reviewed by a board-certified epileptologist. Main results. For 19 motor seizures from 10 in-hospital patients, the algorithm yielded a mean area under curve (AUC), a sensitivity, and an false alarm rate per day (FAR/day) of 0.98, 0.93, and 2.3, respectively. Additionally, for eight seizures with probable motor semiology from two ambulatory patients, the classifier achieved a mean AUC of 0.97 and an FAR of 2.45 events/day at a sensitivity of 0.9. For all seizure types in the ambulatory setting, the classifier had a mean AUC of 0.82 with a sensitivity of 0.47 and an FAR of 7.2 events/day. Significance. The performance of the algorithm was evaluated using motor and non-motor seizures during in-hospital and ambulatory use. The classifier was able to detect multiple types of motor and non-motor seizures, but performed significantly better on motor seizures.

DIFFERENTIATION OF DICHOTOMOUS EMOTIONAL STATES IN ELECTRODERMAL ACTIVITY SIGNALS USING HIGHER-ORDER CROSSING FEATURES AND PARAMETRIC CLASSIFIERS

Prediction and recognition of happy and sad emotional states play important roles in many aspects of human life. In this work, an attempt has been made to classify them using Electrodermal Activity (EDA). For this, EDA signals are obtained from a public database and decomposed into tonic and phasic components. Features, namely Hjorth and higher-order crossing, are extracted from the phasic component of the signal. Further, these extracted features are fed to four parametric classifiers, namely, linear discriminant analysis, logistic regression, multilayer perceptron, and naive bayes for the classification. The results show that the proposed approach can classify the dichotomous happy and sad emotional states. The multilayer perceptron classifier is accurate (85.7%) in classifying happy and sad emotional states. The proposed method is robust in handling the dynamic variation of EDA signals for happy and sad emotional states. Thus, it appears that the proposed method could be able to understand the neurological, psychiatrical, and biobehavioural mechanisms of happy and sad emotional states.

Wearable Technologies for Mental Workload, Stress, and Emotional State Assessment during Working-Like Tasks: A Comparison with Laboratory Technologies.

The capability of monitoring user’s performance represents a crucial aspect to improve safety and efficiency of several human-related activities. Human errors are indeed among the major causes of work-related accidents. Assessing human factors (HFs) could prevent these accidents through specific neurophysiological signals’ evaluation but laboratory sensors require highly-specialized operators and imply a certain grade of invasiveness which could negatively interfere with the worker’s activity. On the contrary, consumer wearables are characterized by their ease of use and their comfortability, other than being cheaper compared to laboratory technologies. Therefore, wearable sensors could represent an ideal substitute for laboratory technologies for a real-time assessment of human performances in ecological settings. The present study aimed at assessing the reliability and capability of consumer wearable devices (i.e., Empatica E4 and Muse 2) in discriminating specific mental states compared to laboratory equipment. The electrooculographic (EOG), electrodermal activity (EDA) and photoplethysmographic (PPG) signals were acquired from a group of 17 volunteers who took part to the experimental protocol in which different working scenarios were simulated to induce different levels of mental workload, stress, and emotional state. The results demonstrated that the parameters computed by the consumer wearable and laboratory sensors were positively and significantly correlated and exhibited the same evidences in terms of mental states discrimination.

Biometric recognition using wearable devices in real-life settings

The popularity of wearable devices, such as smart glasses, chestbands, and wristbands, is nowadays rapidly growing, thanks to the fact that they can be used to track physical activity and monitor users’ health. Recently, researchers have proposed to exploit their capability to collect physiological signals for enabling automatic user recognition. Wearable devices inherently provide the means for detecting their unauthorized usage, or for being used as front-end in biometric recognition systems controlling the access to either physical or virtual locations and services. The present work evaluates the feasibility of performing biometric recognition using signals captured by wearable devices, considering data collected through off-the-shelf commercial wristbands, and comparing recordings taken during two distinct sessions separated by an average time of 7 days. In more detail, recognition is performed leveraging on electrodermal activity (EDA) and blood volume pulse (BVP), considering measurements taken from 17 subjects performing natural activities such as attending or teaching lectures. Several tests have been carried out to determine the most effective representation of the considered EDA and BVP signals, as well as the most suitable classifier. The best recognition performance has been achieved exploiting convolutional neural networks to extract discriminative characteristics from the combined spectrograms of the employed EDA and BVP data, guaranteeing average correct identification rate of 98.58% for test samples lasting 30 seconds.

Electrophysiological effects of mindfulness meditation in a concentration test

In this paper, we evaluate the effects of mindfulness meditation training in electrophysiological signals, recorded during a concentration task. Longitudinal experiments have been limited to the analysis of psychological scores through depression, anxiety, and stress state (DASS) surveys. Here, we present a longitudinal study, confronting DASS survey data with electrocardiography (ECG), electroencephalography (EEG), and electrodermal activity (EDA) signals. Twenty-five university student volunteers (mean age = 26, SD = 7, 9 male) attended a 25-h mindfulness-based stress reduction (MBSR) course, over a period of 8 weeks. There were four evaluation periods: pre/peri/post-course and a fourth follow-up, after 2 months. All three recorded biosignals presented congruent results, in line with the expected benefits of regular meditation practice. In average, EDA activity decreased throughout the course, -64.5%, whereas the mean heart rate displayed a small reduction, -5.8%, possibly as a result of an increase in parasympathetic nervous system activity. Prefrontal (AF3) cortical alpha activity, often associated with calm conditions, saw a very significant increase, 148.1%. Also, the number of stressed and anxious subjects showed a significant decrease, -92.9% and -85.7%, respectively. Easy to practice and within everyone's reach, this mindfulness meditation can be used proactively to prevent or enhance better quality of life. 25 volunteers attended a Mindfulness-Based Stress Reduction (MBSR) course in 4 evaluation periods: Pre/Peri/Post-course and a fourth follow-up after two months. A Depression, Anxiety and Stress State (DASS) survey is completed in each period. Electrodermal Activity (EDA), Electrocardiography (ECG) and Electroencephalography (EEG) are also recorded and processed. By integrating self-reported surveys and electrophysiological recordings there is strong evidence of evolution in wellbeing. Mindfulness meditation can be used proactively to prevent or enhance better quality of life.

Towards a model of arousal change after affective word pronunciation based on electrodermal activity and speech analysis

In this paper, we explore the possibility of building a model of subject arousal by exploiting the acquisition and the analysis of speech and electrodermal activity (EDA). Several issues have to be addressed to reach this goal as the estimation of the relationship between arousal and behavioral measures and the reliability of EDA signal during speech production. To accomplish this task, we will investigate the relation among EDA, speech activity and subject arousal, during isolated affective word pronunciation. Our results show that significant information on subject arousal can be obtained by analyzing EDA during the processing of out-of-context words with an emotional content in a reading aloud task. Based on a sample of eighteen Italian participants, we observed a significant relation between EDA features and self-reported arousal scores. Quantitative models relating EDA- and speech-derived features are proposed and discussed. We found that increasing values of tonic and phasic components of EDA signals correspond to increasing self-assessed arousal scores; Mel-frequency cepstral analysis of speech was also shown to carry relevant information about subject arousal, with a significant inverse relation to self-assessed scores. Our results suggest how the analysis of concurrent acquisition of EDA and speech features may offer a valid approach for the prediction of subject arousal during speech production, as well as a method for validating self-assessment ratings themselves.

Emotion Recognition Using Electrodermal Activity Signals and Multiscale Deep Convolutional Neural Network.

In this work, an attempt has been made to classify emotional states using electrodermal activity(EDA) signals and multiscale convolutional neural networks. For this, EDA signals are considered from a publicly available "A Dataset for Emotion Analysis using Physiological Signals" (DEAP) database. These signals are decomposed into multiple-scales using the coarse-grained method. The multiscale signals are applied to the Multiscale Convolutional Neural Network (MSCNN) to automatically learn robust features directly from the raw signals. Experiments are performed with the MSCNN approach to evaluate the hypothesis (i) improved classification with electrodermal activity signals, and (ii) multiscale learning captures robust complementary features at a different scale. Results show that the proposed approach is able to differentiate various emotional states. The proposed approach yields a classification accuracy of 69.33% and 71.43% for valence and arousal states, respectively. It is observed that the number of layers and the signal length are the determinants for the classifier performance. The performance of the proposed approach outperforms the single-layer convolutional neural network. The MSCNN approach provides end-to-end learning and classification of emotional states without additional signal processing. Thus, it appears that the proposed method could be a useful tool to assess the difference in emotional states for automated decision making.

UBFC-Phys: A Multimodal Database For Psychophysiological Studies of Social Stress

As humans, we experience social stress in countless everyday-life situations. Giving a speech in front of an audience, passing a job interview, and similar experiences all lead us to go through stress states that impact both our psychological and physiological states. Therefore, studying the link between stress and physiological responses had become a critical societal issue, and recently, research in this field has grown in popularity. However, publicly available datasets have limitations. In this article, we propose a new dataset, UBFC-Phys, collected with and without contact from participants living social stress situations. A wristband was used to measure contact blood volume pulse (BVP) and electrodermal activity (EDA) signals. Video recordings allowed to compute remote pulse signals, using remote photoplethysmography (RPPG), and facial expression features. Pulse rate variability (PRV) was extracted from BVP and RPPG signals. Our dataset permits to evaluate the possibility of using video-based physiological measures compared to more conventional contact-based modalities. The goal of this article is to present both the dataset, which we make publicly available, and experimental results of contact and non-contact data comparison, as well as stress recognition. We obtained a stress state recognition accuracy of 85.48 percent, achieved by remote PRV features.

Assessing the feasibility of detecting epileptic seizures using non-cerebral sensor data

This paper investigates the feasibility of using non-cerebral, time-series data to detect epileptic seizures. Data were recorded from fifteen patients (7 male, 5 female, 3 not noted, mean age 36.17 yrs), five of whom had a total of seven seizures. Patients were monitored in an inpatient setting using standard video-electroencephalography (vEEG), while also wearing sensors monitoring electrocardiography, electrodermal activity, electromyography, accelerometry, and audio signals (vocalizations). A systematic and detailed study was conducted to identify the sensors and the features derived from the non-cerebral sensors that contribute most significantly to separability of data acquired during seizures from non-seizure data. Post-processing of the data using linear discriminant analysis (LDA) shows that seizure data are strongly separable from non-seizure data based on features derived from the signals recorded. The mean area under the receiver operator characteristic (ROC) curve for each individual patient that experienced a seizure during data collection, calculated using LDA, was 0.9682. The features that contribute most significantly to seizure detection differ for each patient. The results show that a multimodal approach to seizure detection using the specified sensor suite is promising in detecting seizures with both sensitivity and specificity. Moreover, the study provides a means to quantify the contribution of each sensor and feature to separability. Development of a non-electroencephalography (EEG) based seizure detection device would give doctors a more accurate seizure count outside of the clinical setting, improving treatment and the quality of life of epilepsy patients.

PyEDA: An Open-Source Python Toolkit for Pre-processing and Feature Extraction of Electrodermal Activity

Abstract Physiological response is an automatic reaction that triggers a physical response to a stimulus such as stress, emotion, pain, etc. Examples include changes in heart rate, respiration, perspiration, and eye pupil dilation. Electrodermal Activity (EDA), also known as Galvanic Skin Response (GSR), measures changes in perspiration by detecting the changes in electrical conductivity of skin. Previous studies have already shown that EDA is one of the leading indicators for a stimulus. However, the EDA signal itself is not trivial to analyze. To detect different stimuli in human subjects, variety of features are extracted from EDA signals such as the number of peaks, max peak amplitude, to name a few, showing the prevalence of this signal in bio-medical as well as ubiquitous and wearable computing research. In this paper, we present an open-source Python toolkit for EDA signal preprocessing and statistical and automatic feature extraction. To the best of our knowledge, this is the first effort for developing a versatile and generic tool to extract any number of automatic features from EDA signals. We evaluate our toolkit using different machine learning algorithms applied to the Wearable Stress and Affect Detection (WESAD) dataset. Our results show higher validation accuracy for a stress detection task using the the features automatically extracted by pyEDA.

Physiological State Can Help Predict the Perceived Emotion of Music: Evidence from ECG and EDA Signals

As the soul of music, emotion information is widely used in music retrieval and recommendation systems because the pursuit of emotional experience is the main motivation for music listening. In the field of music emotion recognition, computer scientists investigated computation models to automatically detect the perceived emotion of music, but this method ignores the differences between listeners. To provide users with the most accurate music emotion information, this study investigated the effects of physiological features on personalized music emotion recognition (PMER) models, which can automatically identify an individual’s perceived emotion of music. Applying machine learning methods, we formed relations among audio features, physiological features, and music emotions. First, computational modeling analysis shows that physiological features extracted from electrocardiogram and electro-dermal activity signals can predict the perception of music emotion for some individuals. Second, we compared the performance of physiological feature-based perception and feeling models and observed substantial individual differences. In addition, we found that the performance of the perception model and the feeling model is related in predicting happy, relaxed, and sad emotions. Finally, by adding physiological features to the audio-based PMER model, the prediction effect of some individuals was improved. Our work investigated the relationship between physiological state and perceived emotion of music, constructed models with practical value, and provided a reference for the optimization of PMER systems.

Emotion Recognition Using a Glasses-Type Wearable Device via Multi-Channel Facial Responses

We present a glasses type wearable device to detect emotions from a human face in an unobtrusive manner. The device is designed to gather multi channel responses from the user face naturally and continuously while the user is wearing it. The multi channel responses include physiological responses of the facial muscles and organs based on electrodermal activity (EDA) and photoplethysmogram. We conducted experiments to determine the optimal positions of EDA sensors on the wearable device because EDA signal quality is very sensitive to the sensing position. In addition to the physiological data, the device can capture the image region representing local facial expressions around the left eye via a built in camera. In this study, we developed and validated an algorithm to recognize emotions using multi channel responses obtained from the device. The results show that the emotion recognition algorithm using only local facial expressions has an accuracy of 78 percent at classifying emotions. Using multi channel data, this accuracy was increased by 10.1 percent. This unobtrusive wearable system with facial multi channel responses is very useful for monitoring a user emotions in daily life, which has a huge potential for use in the healthcare industry.

Mapping of electrodermal activity (EDA) during outdoor community-level mobility tasks in individuals with lower-limb amputation.

IntroductionBalance confidence and perception of task challenge is an important construct to measure in rehabilitation of people with lower-limb amputation (LLA). Measurement of electrodermal activity (EDA) captures physiological arousal responses reflecting an individual’s perceived challenge in a task. This study explores the feasibility of the use of EDA during outdoor walking tasks to capture task-specific physiological arousal changes associated with perception of challenge in people with amputation.ObjectiveTo develop and demonstrate feasibility of a portable EDA/GPS system mapping physiological arousal while challenging walking balance outdoors in individuals with LLA and controls.MethodsSixteen people (eight with LLA and eight age-/sex-matched controls) completed an outdoor walking course in the community (3 laps). A battery-powered portable device was developed containing EDA/GPS sensors with data logged on a microcontroller. Phasic EDA response was extracted from EDA signal to explore the physiological arousal response to walking tasks.ResultsPhysiological arousal demonstrated task-specific modulation with ascending stairs without a handrail showing higher levels of phasic EDA than walking on a paved incline (p = 0.01) or a gravel decline (p = 0.01) in people with LLA. While evidence of habituation over repeated trials was shown in controls with lap 1 of walking down a gravel decline showing higher levels of phasic EDA than lap 3 (p = 0.01). Phasic EDA maps, representative of arousal levels throughout the walking course, showed individual-specific response.ConclusionMapping of EDA during outdoor walking is feasible. Modulation of physiological arousal between outdoor walking tasks and over repeated trials is suggestive of clinical utility. Further research is warranted to explore how EDA may be incorporated into assessment of response to outdoor walking amongst individuals following LLA.

Comparison of Wearable and Clinical Devices for Acquisition of Peripheral Nervous System Signals.

A key access point to the functioning of the autonomic nervous system is the investigation of peripheral signals. Wearable devices (WDs) enable the acquisition and quantification of peripheral signals in a wide range of contexts, from personal uses to scientific research. WDs have lower costs and higher portability than medical-grade devices. However, the achievable data quality can be lower, and data are subject to artifacts due to body movements and data losses. It is therefore crucial to evaluate the reliability and validity of WDs before their use in research. In this study, we introduce a data analysis procedure for the assessment of WDs for multivariate physiological signals. The quality of cardiac and electrodermal activity signals is validated with a standard set of signal quality indicators. The pipeline is available as a collection of open source Python scripts based on the pyphysio package. We apply the indicators for the analysis of signal quality on data simultaneously recorded from a clinical-grade device and two WDs. The dataset provides signals of six different physiological measures collected from 18 subjects with WDs. This study indicates the need to validate the use of WDs in experimental settings for research and the importance of both technological and signal processing aspects to obtain reliable signals and reproducible results.