AffectiveTDA Using Topological Data Analysis to Improve Analysis and Explainability in Affective Computing

AffectiveTDA : Using Topological Data Analysis to Improve Analysis and Explainability in Affective Computing

We present an approach utilizing Topological Data Analysis to study the structure of face poses used in affective computing, i.e., the process of recognizing human emotion. The approach uses a conditional comparison of different emotions, both respective and irrespective of time, with multiple topol...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on visualization and computer graphics. - 1996. - 28(2022), 1 vom: 29. Jan., Seite 769-779
1. Verfasser: Elhamdadi, Hamza (VerfasserIn)
Weitere Verfasser: Canavan, Shaun, Rosen, Paul
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2022
Zugriff auf das übergeordnete Werk:IEEE transactions on visualization and computer graphics
Schlagworte:Journal Article Research Support, U.S. Gov't, Non-P.H.S.
LEADER 01000naa a22002652 4500
001 NLM33128538X
003 DE-627
005 20231225213128.0
007 cr uuu---uuuuu
008 231225s2022 xx |||||o 00| ||eng c
024 7 |a 10.1109/TVCG.2021.3114784  |2 doi 
028 5 2 |a pubmed24n1104.xml 
035 |a (DE-627)NLM33128538X 
035 |a (NLM)34587031 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Elhamdadi, Hamza  |e verfasserin  |4 aut 
245 1 0 |a AffectiveTDA  |b Using Topological Data Analysis to Improve Analysis and Explainability in Affective Computing 
264 1 |c 2022 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Completed 04.01.2022 
500 |a Date Revised 04.01.2022 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a We present an approach utilizing Topological Data Analysis to study the structure of face poses used in affective computing, i.e., the process of recognizing human emotion. The approach uses a conditional comparison of different emotions, both respective and irrespective of time, with multiple topological distance metrics, dimension reduction techniques, and face subsections (e.g., eyes, nose, mouth, etc.). The results confirm that our topology-based approach captures known patterns, distinctions between emotions, and distinctions between individuals, which is an important step towards more robust and explainable emotion recognition by machines 
650 4 |a Journal Article 
650 4 |a Research Support, U.S. Gov't, Non-P.H.S. 
700 1 |a Canavan, Shaun  |e verfasserin  |4 aut 
700 1 |a Rosen, Paul  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on visualization and computer graphics  |d 1996  |g 28(2022), 1 vom: 29. Jan., Seite 769-779  |w (DE-627)NLM098269445  |x 1941-0506  |7 nnns 
773 1 8 |g volume:28  |g year:2022  |g number:1  |g day:29  |g month:01  |g pages:769-779 
856 4 0 |u http://dx.doi.org/10.1109/TVCG.2021.3114784  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 28  |j 2022  |e 1  |b 29  |c 01  |h 769-779