Machine Learning Techniques for Arousal Classification from Electrodermal Activity: A Systematic Review

Sánchez-Reolid, Roberto; Rosa, Francisco López de la; Sánchez-Reolid, Daniel; López, María Teresa; Fernández-Caballero, Antonio

doi:10.3390/s22228886

Cited by 13 publications

(6 citation statements)

References 130 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This type of kernel is likely more suitable for these signals, given the presence of non-linear relationships among the utilized features that can be effectively captured by this type of kernel function [29]. In the literature, this function is among the most commonly employed when working with SVM methods for arousal classification [30]. Consequently, our study demonstrates that SVM methods can effectively identify autonomic changes in response to levodopa intake in PD patients, producing promising results.…”

Section: Discussionmentioning

confidence: 76%

Advanced Analysis of Electrodermal Activity Measures to Detect the Onset of ON State in Parkinson’s Disease

Barrachina-Fernández,

Valenzuela-López,

Moreno-Verdú

et al. 2023

Mathematics

View full text Add to dashboard Cite

Background: Electrodermal activity (EDA) serves as a prominent biosignal for assessing sympathetic activation across various scenarios. Prior research has suggested a connection between EDA and fluctuations in Parkinson’s disease (PD), but its precise utility in reliably detecting these fluctuations has remained unexplored. This study aims to evaluate the efficacy of both basic and advanced analyses of EDA changes in identifying the transition to the ON state following dopaminergic medication administration in individuals with PD. Methods: In this observational study, 19 individuals with PD were enrolled. EDA was continuously recorded using the Empatica E4 device, worn on the wrist, during the transition from the OFF state to the ON state following levodopa intake. The raw EDA signal underwent preprocessing and evaluation through three distinct approaches. A logistic regression model was constructed to assess the significance of variables predicting the ON/OFF state, and support vector machine (SVM) models along with various Neural Network (NN) configurations were developed for accurate state prediction. Results: Differences were identified between the ON and OFF states in both the time and frequency domains, as well as through the utilization of convex optimization techniques. SVM and NN models demonstrated highly promising results in effectively distinguishing between the OFF and ON states. Conclusions: Evaluating sympathetic activation changes via EDA measures holds substantial promise for detecting non-motor fluctuations in PD. The SVM algorithm, in particular, yields precise outcomes for predicting these non-motor fluctuation states.

show abstract

Section: Discussionmentioning

confidence: 76%

Advanced Analysis of Electrodermal Activity Measures to Detect the Onset of ON State in Parkinson’s Disease

Barrachina-Fernández,

Valenzuela-López,

Moreno-Verdú

et al. 2023

Mathematics

View full text Add to dashboard Cite

show abstract

“…Future research may therefore consider exploring the potential utility of using these devices on people post-admission where the incidence of relapse is substantially higher. Additionally, given the amount of data involved, machine learning may offer a novel solution in being able to assist in identifying the personalized relapse signatures of individuals (Sánchez-Reolid et al, 2022). Ultimately, future research should explore the utility of such technology to assist in improving the care that individuals receive in community health services.…”

Section: Case Study 4: Krystalmentioning

confidence: 99%

Integrating smartwatches in community mental health services for severe mental illness for detecting relapse and informing future intervention: A case series

Johnston,

Foord,

Casties

et al. 2024

Early Intervention Psych

View full text Add to dashboard Cite

ObjectiveThis case series explored the integration of smartwatches in a community mental health service to support severe mental illness (SMI) management and intervention. We examined whether biometric data provided by smartwatches could help to predict relapse and inform treatment decisions.MethodFour Australian SMI outpatients of mixed diagnoses (age range = 19–24) were selected from a prior study. Clinicians accessed patients' biometric data (activity, sleep, heart rate, and electrodermal activity) through smartwatches.ResultsChanges in circadian rhythm and electrodermal activity preceded hospitalization in two cases. Additionally, smartwatch data was effectively used to guide targeted interventions, improving patient treatment outcomes.ConclusionIntegrating smartwatches in community mental health services offers promise as adjunct tools for SMI management. However, ethical considerations on data privacy and technology reliance require further evaluation. Additionally, as this is a small case series, randomized controlled trials with larger sample sizes are required to provide evidence for generalisability of results.

show abstract

“…However, the relationship between EDA and valence-whether the emotional experience is positive or negative-is more complex and requires further exploration. Therefore, EDA serves as a reliable indicator primarily of arousal in affective science (Boucsein, 2012) and for detecting affective dimensions in affective computing (Sánchez-Reolid et al, 2022).…”

Section: Physiological Signals Can Be Broadly Divided Into Central An...mentioning

confidence: 99%

Exploring the Underlying Emotional Models in Emotion Recognition Systems with Electrodermal Activity

D'Amelio,

Galán,

Maldonado

et al. 2023

Preprint

View full text Add to dashboard Cite

Affective computing is an interdisciplinary field that aims to automatically recognize and interpret emotions. Recent research has focused on using physiological signals (e.g., electrodermal activity) to improve emotion recognition. However, little attention has been paid to the theoretical emotion models underlying these systems. Here, we conducted a systematic review and meta-analysis of the literature on automatic emotion recognition systems using electrodermal activity. We found that models predicting arousal generally outperformed those predicting valence, which is consistent with our pre-registered hypothesis. This finding aligns well with the conceptual framework that views arousal as a psychological and physiological state linked to autonomic nervous system activity, making it more directly related to electrodermal activity. Furthermore, we observed a discrepancy between the types of machine learning models used, mainly classification models, and the emotional models adopted, often of a dimensional nature. Specifically, despite the increased use of dimensional affective models, there has been no corresponding increase in the use of regression models, which would be consistent with the continuous nature of these data. We conclude that a comprehensive understanding of affective states requires consideration of both psychological and computational perspectives in affective computing research.

show abstract

Machine Learning Techniques for Arousal Classification from Electrodermal Activity: A Systematic Review

Cited by 13 publications

References 130 publications

Advanced Analysis of Electrodermal Activity Measures to Detect the Onset of ON State in Parkinson’s Disease

Advanced Analysis of Electrodermal Activity Measures to Detect the Onset of ON State in Parkinson’s Disease

Integrating smartwatches in community mental health services for severe mental illness for detecting relapse and informing future intervention: A case series

Exploring the Underlying Emotional Models in Emotion Recognition Systems with Electrodermal Activity

Contact Info

Product

Resources

About