Matches in SemOpenAlex for { <https://semopenalex.org/work/W4309969794> ?p ?o ?g. }
- W4309969794 abstract "Machine-learning-based stress detection systems differ with respect to the ground truth used for training the algorithms. It is unclear how models trained on different facets of the stress reaction (e.g., biological, psychological, social) can be compared, interpreted and applied. In this study, we investigate the influence of the stress label on the performance of machine learning models trained on either vocal characteristics or facial expressions extracted from videos. We collected videos from 40 male participants while being exposed to the Trier Social Stress Test (TSST) and assessed self-reported, live observed, video-annotated and neuro-endocrinological stress levels. We train three standard machine learning models to separately predict different stress labels using either voice or facial cues. Analyzing the relationships of different stress facets we found that observers' annotations were significantly positively associated (live vs. video annotated, <tex xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>$boldsymbol{rho}_{mathbf{s}} = . 53$</tex> ). Similarly, the neuro-endocrinological stress indices correlated with each other (cortisol vs. sAA, <tex xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>$boldsymbol{rho}_{mathbf{s}}$</tex> =.39). Machine learning experiments resulted in predictions that were positively associated with panel-annotated stress levels showing significantly stronger correlations in voice-based models <tex xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>$(boldsymbol{rho}_{mathbf{s}=}.54 mathbf{v}mathbf{s}. boldsymbol{rho}_{mathbf{S}}=.30)$</tex> . Predictions of self-reported stress were positively related to ground truth values for face-based <tex xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>$(boldsymbol{rho}_{mathbf{s}}$</tex> =.24) but not for voice-based models. There was no evidence for successful predictions of video-annotations or endocrinological stress levels in both settings. We provide evidence that machine learning models trained on different stress assessments perform differently and should be interpreted and applied accordingly. Implications and recommendations for future work on video-based stress detection are discussed." @default.
- W4309969794 created "2022-11-30" @default.
- W4309969794 creator A5013666461 @default.
- W4309969794 creator A5040474066 @default.
- W4309969794 creator A5043057031 @default.
- W4309969794 creator A5052236115 @default.
- W4309969794 creator A5058949112 @default.
- W4309969794 creator A5074204533 @default.
- W4309969794 date "2022-10-18" @default.
- W4309969794 modified "2023-10-14" @default.
- W4309969794 title "Automatic Detection of Subjective, Annotated and Physiological Stress Responses from Video Data" @default.
- W4309969794 cites W1664244372 @default.
- W4309969794 cites W1783340786 @default.
- W4309969794 cites W1989439371 @default.
- W4309969794 cites W2009200163 @default.
- W4309969794 cites W2016737068 @default.
- W4309969794 cites W2056403322 @default.
- W4309969794 cites W2059005389 @default.
- W4309969794 cites W2064910482 @default.
- W4309969794 cites W2075194189 @default.
- W4309969794 cites W2092880670 @default.
- W4309969794 cites W2099442165 @default.
- W4309969794 cites W2103153725 @default.
- W4309969794 cites W2117866167 @default.
- W4309969794 cites W2120951423 @default.
- W4309969794 cites W2122219818 @default.
- W4309969794 cites W2143662509 @default.
- W4309969794 cites W2144846685 @default.
- W4309969794 cites W2144961120 @default.
- W4309969794 cites W2169622879 @default.
- W4309969794 cites W2171801645 @default.
- W4309969794 cites W2180164314 @default.
- W4309969794 cites W2239141610 @default.
- W4309969794 cites W2353776729 @default.
- W4309969794 cites W2399131206 @default.
- W4309969794 cites W2486806851 @default.
- W4309969794 cites W2553272317 @default.
- W4309969794 cites W2557159259 @default.
- W4309969794 cites W2609584573 @default.
- W4309969794 cites W2768719377 @default.
- W4309969794 cites W2791322619 @default.
- W4309969794 cites W2800448574 @default.
- W4309969794 cites W2894637834 @default.
- W4309969794 cites W2898901496 @default.
- W4309969794 cites W2912483755 @default.
- W4309969794 cites W2969522137 @default.
- W4309969794 cites W2972961215 @default.
- W4309969794 cites W2976017816 @default.
- W4309969794 cites W2981679558 @default.
- W4309969794 cites W2990091959 @default.
- W4309969794 cites W2998342169 @default.
- W4309969794 cites W3087924339 @default.
- W4309969794 cites W3091878148 @default.
- W4309969794 cites W3122547946 @default.
- W4309969794 cites W3126505626 @default.
- W4309969794 cites W3147645188 @default.
- W4309969794 cites W3205733239 @default.
- W4309969794 cites W3213655796 @default.
- W4309969794 cites W3213726020 @default.
- W4309969794 cites W4200162263 @default.
- W4309969794 cites W4206001786 @default.
- W4309969794 cites W4362204963 @default.
- W4309969794 cites W898822149 @default.
- W4309969794 doi "https://doi.org/10.1109/acii55700.2022.9953894" @default.
- W4309969794 hasPublicationYear "2022" @default.
- W4309969794 type Work @default.
- W4309969794 citedByCount "0" @default.
- W4309969794 crossrefType "proceedings-article" @default.
- W4309969794 hasAuthorship W4309969794A5013666461 @default.
- W4309969794 hasAuthorship W4309969794A5040474066 @default.
- W4309969794 hasAuthorship W4309969794A5043057031 @default.
- W4309969794 hasAuthorship W4309969794A5052236115 @default.
- W4309969794 hasAuthorship W4309969794A5058949112 @default.
- W4309969794 hasAuthorship W4309969794A5074204533 @default.
- W4309969794 hasConcept C104317684 @default.
- W4309969794 hasConcept C119857082 @default.
- W4309969794 hasConcept C138885662 @default.
- W4309969794 hasConcept C146849305 @default.
- W4309969794 hasConcept C154945302 @default.
- W4309969794 hasConcept C21036866 @default.
- W4309969794 hasConcept C2778597338 @default.
- W4309969794 hasConcept C28490314 @default.
- W4309969794 hasConcept C41008148 @default.
- W4309969794 hasConcept C41895202 @default.
- W4309969794 hasConcept C54355233 @default.
- W4309969794 hasConcept C78604142 @default.
- W4309969794 hasConcept C86803240 @default.
- W4309969794 hasConceptScore W4309969794C104317684 @default.
- W4309969794 hasConceptScore W4309969794C119857082 @default.
- W4309969794 hasConceptScore W4309969794C138885662 @default.
- W4309969794 hasConceptScore W4309969794C146849305 @default.
- W4309969794 hasConceptScore W4309969794C154945302 @default.
- W4309969794 hasConceptScore W4309969794C21036866 @default.
- W4309969794 hasConceptScore W4309969794C2778597338 @default.
- W4309969794 hasConceptScore W4309969794C28490314 @default.
- W4309969794 hasConceptScore W4309969794C41008148 @default.
- W4309969794 hasConceptScore W4309969794C41895202 @default.
- W4309969794 hasConceptScore W4309969794C54355233 @default.
- W4309969794 hasConceptScore W4309969794C78604142 @default.
- W4309969794 hasConceptScore W4309969794C86803240 @default.