000101526 001__ 101526
000101526 005__ 20220817094632.0
000101526 0247_ $$2doi$$a10.1007/s00779-020-01393-4
000101526 0248_ $$2sideral$$a118015
000101526 037__ $$aART-2020-118015
000101526 041__ $$aeng
000101526 100__ $$aMedina, Yesid O.
000101526 245__ $$aEmotional classification of music using neural networks with the MediaEval dataset
000101526 260__ $$c2020
000101526 5060_ $$aAccess copy available to the general public$$fUnrestricted
000101526 5203_ $$aThe proven ability of music to transmit emotions provokes the increasing interest in the development of new algorithms for music emotion recognition (MER). In this work, we present an automatic system of emotional classification of music by implementing a neural network. This work is based on a previous implementation of a dimensional emotional prediction system in which a multilayer perceptron (MLP) was trained with the freely available MediaEval database. Although these previous results are good in terms of the metrics of the prediction values, they are not good enough to obtain a classification by quadrant based on the valence and arousal values predicted by the neural network, mainly due to the imbalance between classes in the dataset. To achieve better classification values, a pre-processing phase was implemented to stratify and balance the dataset. Three different classifiers have been compared: linear support vector machine (SVM), random forest, and MLP. The best results are obtained with the MLP. An averaged F-measure of 50% is obtained in a four-quadrant classification schema. Two binary classification approaches are also presented: one vs. rest (OvR) approach in four-quadrants and binary classifier in valence and arousal. The OvR approach has an average F-measure of 69%, and the second one obtained F-measure of 73% and 69% in valence and arousal respectively. Finally, a dynamic classification analysis with different time windows was performed using the temporal annotation data of the MediaEval database. The results obtained show that the classification F-measures in four quadrants are practically constant, regardless of the duration of the time window. Also, this work reflects some limitations related to the characteristics of the dataset, including size, class balance, quality of the annotations, and the sound features available.
000101526 536__ $$9info:eu-repo/grantAgreement/ES/DGA-FEDER/Construyendo Europa desde Aragón$$9info:eu-repo/grantAgreement/ES/DGA/T25-17D$$9info:eu-repo/grantAgreement/ES/MCIU-AEI-FEDER/RTI2018-096986-B-C31$$9info:eu-repo/grantAgreement/ES/MCIU-AEI-FEDER/TIN2015-72241-EXP
000101526 540__ $$9info:eu-repo/semantics/openAccess$$aAll rights reserved$$uhttp://www.europeana.eu/rights/rr-f/
000101526 590__ $$a3.006$$b2020
000101526 591__ $$aTELECOMMUNICATIONS$$b43 / 91 = 0.473$$c2020$$dQ2$$eT2
000101526 591__ $$aCOMPUTER SCIENCE, INFORMATION SYSTEMS$$b75 / 162 = 0.463$$c2020$$dQ2$$eT2
000101526 592__ $$a0.415$$b2020
000101526 593__ $$aComputer Science Applications$$c2020$$dQ2
000101526 593__ $$aManagement Science and Operations Research$$c2020$$dQ2
000101526 593__ $$aHardware and Architecture$$c2020$$dQ2
000101526 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/acceptedVersion
000101526 700__ $$0(orcid)0000-0002-7500-4650$$aBeltrán, José Ramón$$uUniversidad de Zaragoza
000101526 700__ $$0(orcid)0000-0002-9315-6391$$aBaldassarri, Sandra$$uUniversidad de Zaragoza
000101526 7102_ $$15008$$2785$$aUniversidad de Zaragoza$$bDpto. Ingeniería Electrón.Com.$$cÁrea Tecnología Electrónica
000101526 7102_ $$15007$$2570$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Lenguajes y Sistemas Inf.
000101526 773__ $$g26 (2020), 1237–1249$$pPersonal and Ubiquitous Computing$$tPersonal and Ubiquitous Computing$$x1617-4909
000101526 8564_ $$s782151$$uhttps://zaguan.unizar.es/record/101526/files/texto_completo.pdf$$yPostprint
000101526 8564_ $$s530182$$uhttps://zaguan.unizar.es/record/101526/files/texto_completo.jpg?subformat=icon$$xicon$$yPostprint
000101526 909CO $$ooai:zaguan.unizar.es:101526$$particulos$$pdriver
000101526 951__ $$a2022-08-17-09:34:00
000101526 980__ $$aARTICLE