000285257 001__ 285257
000285257 005__ 20260217100411.0
000285257 0247_ $$2doi$$a10.3390/s26031060
000285257 0247_ $$2pmid$$apmid:41682575
000285257 0247_ $$2pmc$$apmc:PMC12899966
000285257 037__ $$aDZNE-2026-00199
000285257 041__ $$aEnglish
000285257 082__ $$a620
000285257 1001_ $$00009-0005-8655-493X$$aAldenhoven, Céline Madeleine$$b0
000285257 245__ $$aReal-Time Emotion Recognition Performance of Mobile Devices: A Detailed Analysis of Camera and TrueDepth Sensors Using Apple's ARKit.
000285257 260__ $$aBasel$$bMDPI$$c2026
000285257 3367_ $$2DRIVER$$aarticle
000285257 3367_ $$2DataCite$$aOutput Types/Journal article
000285257 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1771318847_24677
000285257 3367_ $$2BibTeX$$aARTICLE
000285257 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000285257 3367_ $$00$$2EndNote$$aJournal Article
000285257 520__ $$aFacial features hold information about a person's emotions, motor function, or genetic defects. Since most current mobile devices are capable of real-time face detection using cameras and depth sensors, real-time facial analysis can be utilized in several mobile use cases. Understanding the real-time emotion recognition capabilities of device sensors and frameworks is vital for developing new, valid applications. Therefore, we evaluated on-device emotion recognition using Apple's ARKit on an iPhone 14 Pro. A native app elicited 36 blend shape-specific movements and 7 discrete emotions from N=31 healthy adults. Per frame, standardized ARKit blend shapes were classified using a prototype-based cosine similarity metric; performance was summarized as accuracy and area under the receiver operating characteristic curves. Cosine similarity achieved an overall accuracy of 68.3%, exceeding the mean of three human raters (58.9%; +9.4 percentage points, ≈16% relative). Per-emotion accuracy was highest for joy, fear, sadness, and surprise, and competitive for anger, disgust, and contempt. AUCs were ≥0.84 for all classes. The method runs in real time on-device using only vector operations, preserving privacy and minimizing compute. These results indicate that a simple, interpretable cosine-similarity classifier over ARKit blend shapes delivers human-comparable, real-time facial emotion recognition on commodity hardware, supporting privacy-preserving mobile applications.
000285257 536__ $$0G:(DE-HGF)POF4-353$$a353 - Clinical and Health Care Research (POF4-353)$$cPOF4-353$$fPOF IV$$x0
000285257 588__ $$aDataset connected to CrossRef, PubMed, , Journals: pub.dzne.de
000285257 650_7 $$2Other$$aARKit
000285257 650_7 $$2Other$$aemotion recognition
000285257 650_7 $$2Other$$aface tracking
000285257 650_7 $$2Other$$areal-time
000285257 650_7 $$2Other$$asensors
000285257 650_2 $$2MeSH$$aHumans
000285257 650_2 $$2MeSH$$aEmotions: physiology
000285257 650_2 $$2MeSH$$aAdult
000285257 650_2 $$2MeSH$$aMale
000285257 650_2 $$2MeSH$$aFemale
000285257 650_2 $$2MeSH$$aMobile Applications
000285257 650_2 $$2MeSH$$aSmartphone
000285257 650_2 $$2MeSH$$aYoung Adult
000285257 650_2 $$2MeSH$$aFacial Expression
000285257 7001_ $$00009-0009-3884-0850$$aNissen, Leon$$b1
000285257 7001_ $$00009-0001-1402-0876$$aHeinemann, Marie$$b2
000285257 7001_ $$0P:(DE-2719)9002372$$aDogdu, Cem$$b3$$udzne
000285257 7001_ $$aHanke, Alexander$$b4
000285257 7001_ $$00000-0002-3687-6165$$aJonas, Stephan$$b5
000285257 7001_ $$0P:(DE-2719)9002403$$aReimer, Lara Marie$$b6$$udzne
000285257 773__ $$0PERI:(DE-600)2052857-7$$a10.3390/s26031060$$gVol. 26, no. 3, p. 1060 -$$n3$$p1060$$tSensors$$v26$$x1424-8220$$y2026
000285257 8564_ $$uhttps://pub.dzne.de/record/285257/files/DZNE-2026-00199.pdf$$yRestricted
000285257 8564_ $$uhttps://pub.dzne.de/record/285257/files/DZNE-2026-00199.pdf?subformat=pdfa$$xpdfa$$yRestricted
000285257 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)9002372$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b3$$kDZNE
000285257 9101_ $$0I:(DE-HGF)0$$6P:(DE-2719)9002403$$aExternal Institute$$b6$$kExtern
000285257 9131_ $$0G:(DE-HGF)POF4-353$$1G:(DE-HGF)POF4-350$$2G:(DE-HGF)POF4-300$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bGesundheit$$lNeurodegenerative Diseases$$vClinical and Health Care Research$$x0
000285257 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bSENSORS-BASEL : 2022$$d2025-11-11
000285257 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2025-11-11
000285257 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2025-11-11
000285257 915__ $$0StatID:(DE-HGF)0320$$2StatID$$aDBCoverage$$bPubMed Central$$d2025-11-11
000285257 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2024-04-10T15:28:10Z
000285257 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2024-04-10T15:28:10Z
000285257 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Anonymous peer review$$d2024-04-10T15:28:10Z
000285257 915__ $$0LIC:(DE-HGF)CCBYNV$$2V:(DE-HGF)$$aCreative Commons Attribution CC BY (No Version)$$bDOAJ$$d2024-04-10T15:28:10Z
000285257 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search$$d2025-11-11
000285257 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC$$d2025-11-11
000285257 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2025-11-11
000285257 915__ $$0StatID:(DE-HGF)1150$$2StatID$$aDBCoverage$$bCurrent Contents - Physical, Chemical and Earth Sciences$$d2025-11-11
000285257 915__ $$0StatID:(DE-HGF)1160$$2StatID$$aDBCoverage$$bCurrent Contents - Engineering, Computing and Technology$$d2025-11-11
000285257 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2025-11-11
000285257 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2025-11-11
000285257 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2025-11-11
000285257 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5$$d2025-11-11
000285257 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2025-11-11
000285257 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2025-11-11
000285257 9201_ $$0I:(DE-2719)1011305$$kAG Schneider$$lTranslational Dementia Research (Bonn)$$x0
000285257 980__ $$ajournal
000285257 980__ $$aEDITORS
000285257 980__ $$aVDBINPRINT
000285257 980__ $$aI:(DE-2719)1011305
000285257 980__ $$aUNRESTRICTED