Mostrar el registro sencillo del ítem

Toward User-Independent Emotion Recognition Using Physiological Signals

dc.creatorAlbraikan A.
dc.creatorTobon D.P.
dc.creatorEl Saddik A.
dc.date2019
dc.date.accessioned2020-04-29T14:53:44Z
dc.date.available2020-04-29T14:53:44Z
dc.identifier.issn1530437X
dc.identifier.urihttp://hdl.handle.net/11407/5711
dc.descriptionMany techniques have been developed to improve the flexibility and the fit of detection models beyond user-dependent models, yet detection tasks continue to be complex and challenging. For emotion, which is known to be highly user-dependent, improvements to the emotion learning algorithm can greatly boost predictive power. Our aim is to improve the accuracy rate of the classifier using peripheral physiological signals. Here, we present a hybrid sensor fusion approach based on a stacking model that allows for data from multiple sensors and emotion models to be jointly embedded within a user-independent model. WMD-DTW, which is a weighted multi-dimensional DTW, and the k-nearest neighbor's algorithm k-NN are used to classify the emotions as a base model. The ensemble methods were used to learn a high-level classifier on top of the two base models. We applied a meta-learning approach to the data set and showed that the ensemble approach outperforms any individual method. We also compared the results using two data sets. Our proposed system achieved an overall accuracies of 65.6% for all users for the E4-data set and 94.0% and 93.6% for recognizing valence and arousal emotions, respectively, using the MAHNOB data set. © 2001-2012 IEEE.
dc.language.isoeng
dc.publisherInstitute of Electrical and Electronics Engineers Inc.
dc.relation.isversionofhttps://www2.scopus.com/inward/record.uri?eid=2-s2.0-85052687193&doi=10.1109%2fJSEN.2018.2867221&partnerID=40&md5=d1d77f582f295d557a4b39e856ab7495
dc.sourceIEEE Sensors Journal
dc.subjectEmotion recognition
dc.subjectensemble learning
dc.subjectmulti-dimensional dynamic time warping (MD-DTW)
dc.subjectoptimization
dc.subjectphysiological signals
dc.subjectBiological systems
dc.subjectElectrocardiography
dc.subjectElectromyography
dc.subjectLearning algorithms
dc.subjectNearest neighbor search
dc.subjectOptimization
dc.subjectPhysiology
dc.subjectPsychology computing
dc.subjectSensor data fusion
dc.subjectSensors
dc.subjectSpeech recognition
dc.subjectSupport vector machines
dc.subjectBiological system modeling
dc.subjectEmotion recognition
dc.subjectEnsemble learning
dc.subjectMulti-dimensional dynamics
dc.subjectPhysiological signals
dc.subjectBiomedical signal processing
dc.titleToward User-Independent Emotion Recognition Using Physiological Signals
dc.typeArticleeng
dc.rights.accessrightsinfo:eu-repo/semantics/restrictedAccess
dc.publisher.programIngeniería de Telecomunicaciones
dc.identifier.doi10.1109/JSEN.2018.2867221
dc.relation.citationvolume19
dc.relation.citationissue19
dc.relation.citationstartpage8402
dc.relation.citationendpage8412
dc.publisher.facultyFacultad de Ingenierías
dc.affiliationAlbraikan, A., Multimedia Computing Research Laboratory, University of Ottawa, Ottawa, ON, Canada, Department of Computer Science, Princess Nourah Bint Abdulrahman University, Riyadh, Saudi Arabia; Tobon, D.P., Telecommunications Engineering Department, Universidad de Medellín, Medellín, Colombia; El Saddik, A., Multimedia Computing Research Laboratory, University of Ottawa, Ottawa, ON, Canada
dc.type.versioninfo:eu-repo/semantics/publishedVersion
dc.type.driverinfo:eu-repo/semantics/article


Ficheros en el ítem

FicherosTamañoFormatoVer

No hay ficheros asociados a este ítem.

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem