Academic Journal
Detection of arousal and valence from facial expressions and physiological responses evoked by different types of stressors
| العنوان: | Detection of arousal and valence from facial expressions and physiological responses evoked by different types of stressors |
|---|---|
| المؤلفون: | Bruin, J., Stuldreher, I.V., Perone, P., Hogenelst, K., Naber, M., Brouwer, A.M. |
| المصدر: | Frontiers in Neuroergonomics, 5 |
| سنة النشر: | 2024 |
| المجموعة: | Radboud University: DSpace |
| مصطلحات موضوعية: | Cognitive artificial intelligence |
| الوصف: | Contains fulltext : 304521.pdf (Publisher’s version ) (Open Access) ; Automatically detecting mental state such as stress from video images of the face could support evaluating stress responses in applicants for high risk jobs or contribute to timely stress detection in challenging operational settings (e.g., aircrew, command center operators). Challenges in automatically estimating mental state include the generalization of models across contexts and across participants. We here aim to create robust models by training them using data from different contexts and including physiological features. Fifty-one participants were exposed to different types of stressors (cognitive, social evaluative and startle) and baseline variants of the stressors. Video, electrocardiogram (ECG), electrodermal activity (EDA) and self-reports (arousal and valence) were recorded. Logistic regression models aimed to classify between high and low arousal and valence across participants, where "high" and "low" were defined relative to the center of the rating scale. Accuracy scores of different models were evaluated: models trained and tested within a specific context (either a baseline or stressor variant of a task), intermediate context (baseline and stressor variant of a task), or general context (all conditions together). Furthermore, for these different model variants, only the video data was included, only the physiological data, or both video and physiological data. We found that all (video, physiological and video-physio) models could successfully distinguish between high- and low-rated arousal and valence, though performance tended to be better for (1) arousal than valence, (2) specific context than intermediate and general contexts, (3) video-physio data than video or physiological data alone. Automatic feature selection resulted in inclusion of 3–20 features, where the models based on video-physio data usually included features from video, ECG and EDA. Still, performance of video-only models approached the performance of ... |
| نوع الوثيقة: | article in journal/newspaper |
| اللغة: | unknown |
| Relation: | https://repository.ubn.ru.nl//bitstream/handle/2066/304521/304521.pdf; https://repository.ubn.ru.nl/handle/2066/304521 |
| DOI: | 10.3389/fnrgo.2024.1338243 |
| الاتاحة: | https://repository.ubn.ru.nl//bitstream/handle/2066/304521/304521.pdf https://repository.ubn.ru.nl/handle/2066/304521 https://doi.org/10.3389/fnrgo.2024.1338243 |
| رقم الانضمام: | edsbas.AF07D7CF |
| قاعدة البيانات: | BASE |
| DOI: | 10.3389/fnrgo.2024.1338243 |
|---|