Feature Extraction for Stress Detection in Electrodermal Activity

Lutin, Erika; Hashimoto, Reiji; Raedt, W. De; Hoof, Chris Van

doi:10.5220/0010244601770185

Cited by 9 publications

(6 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Stress causes an increase in electrical bursts towards the sweat glands that produce changes in skin conductance. In [67] the authors found that the best consistent features from the EDA was the driver function given by Ledalab [68] (a Matlab GUI for EDA analysis), which is obtained by applying a deconvolution process. Other studies have used only HR features, derived from PPG or/and ECG signals [69], or EEG features [70], with an accuracy of 86.9% or 97.95%, respectively.…”

Section: Stress Detectionmentioning

confidence: 99%

Towards Human Stress and Activity Recognition: A Review and a First Approach Based on Low-Cost Wearables

et al. 2022

View full text Add to dashboard Cite

Detecting stress when performing physical activities is an interesting field that has received relatively little research interest to date. In this paper, we took a first step towards redressing this, through a comprehensive review and the design of a low-cost body area network (BAN) made of a set of wearables that allow physiological signals and human movements to be captured simultaneously. We used four different wearables: OpenBCI and three other open-hardware custom-made designs that communicate via bluetooth low energy (BLE) to an external computer—following the edge-computingconcept—hosting applications for data synchronization and storage. We obtained a large number of physiological signals (electroencephalography (EEG), electrocardiography (ECG), breathing rate (BR), electrodermal activity (EDA), and skin temperature (ST)) with which we analyzed internal states in general, but with a focus on stress. The findings show the reliability and feasibility of the proposed body area network (BAN) according to battery lifetime (greater than 15 h), packet loss rate (0% for our custom-made designs), and signal quality (signal-noise ratio (SNR) of 9.8 dB for the ECG circuit, and 61.6 dB for the EDA). Moreover, we conducted a preliminary experiment to gauge the main ECG features for stress detection during rest.

show abstract

Section: Stress Detectionmentioning

confidence: 99%

Towards Human Stress and Activity Recognition: A Review and a First Approach Based on Low-Cost Wearables

et al. 2022

View full text Add to dashboard Cite

show abstract

“…There are two methods to quantify each component: Continuous Deconvolution Analysis (CDA) and Discrete deconvolution Analysis (DDA). Although DDA employs a strict nonnegative deconvolution, CDA merely tries to minimize negativity so that the analysis is more robust (Lutin et al, 2021). Therefore, in this study, CDA was adopted.…”

Section: Skin Conductancementioning

confidence: 99%

Assessing Workers’ Mental Stress in Hand-over Activities during Human-robot Collaboration

Xie

Wang

et al. 2022

Proceedings of the Human Factors and Ergonomics Society Annual

View full text Add to dashboard Cite

Human-robot collaboration (HRC) is an emerging research area that has gained tremendous attention from both academia and industry. Since some robot-related factors can elicit mental stress or have negative psychological effects on human workers, it is essential to understand these factors and maintain workers’ mental stress at a low level. Galvanic Skin Response (GSR) measures skin conductance and is known to be a physiological measurement that reflects short-term mental stress. Typically, skin conductance increases in response to greater mental stress. In this study, the mental stress caused by the hand-over activities of a collaborative robot was investigated using both GSR as an objective measurement and NASA-Task Load Index (TLX) as a subjective assessment. Several robot-related factors that may lead to mental stress were experimentally examined. GSR outcomes indicated that end effector approaching within workers’ view, low end effector speed, and constrained end effector trajectory led to a significantly lower skin conductance. Some aspects of the NASA-TLX also indicated that speed and trajectory significantly affected the scores. Yet, no significant differences were found between approaching directions regarding NASA-TLX scores.

show abstract

“…These factors resulted in an accuracy of 78.94%. An accuracy of approximately 89% was achieved [40] using support vector machine approach to detect the stress state of participants in three types of tasks: Stroop color-word test, arithmetic test of counting numbers, and talking about stressful experience or events. During the comparison of previous and present methods, it was proposed that EDA signal shows potential to recognize human emotions and stress levels.…”

Section: A Performance Of Modelsmentioning

confidence: 99%

User Stress in Artificial Intelligence: Modeling in Case of System Failure

et al. 2021

View full text Add to dashboard Cite

The uninterrupted operation of systems with artificial intelligence (AI) ensures high productivity and accuracy of the tasks performed. The physiological state of AI operators indicates a relation with an AI system failure event and can be measured through electrodermal activity. This study aims to model the stress levels of system operators based on system trustworthiness and physiological responses during a correct AI operation and its failure. Two groups of 18 and 19 participants took part in the experiments using two different types of software with elements of AI. The first group of participants used English proofreading software and the second group used drawing software as the AI tools. During the tasks, the electrodermal activities of the participants as a stress level indicator were measured. Based on the results obtained, the users' stress was determined and classified using logistic regression models with an accuracy of approximately 70%. The insights obtained can serve AI product developers in increasing the level of user trust and managing the anxiety and stress levels of AI operators.

show abstract

Feature Extraction for Stress Detection in Electrodermal Activity

Cited by 9 publications

References 0 publications

Towards Human Stress and Activity Recognition: A Review and a First Approach Based on Low-Cost Wearables

Towards Human Stress and Activity Recognition: A Review and a First Approach Based on Low-Cost Wearables

Assessing Workers’ Mental Stress in Hand-over Activities during Human-robot Collaboration

User Stress in Artificial Intelligence: Modeling in Case of System Failure

Contact Info

Product

Resources

About