An Evaluation of Physiological Public Datasets for Emotion Recognition Systems

No hay miniatura disponible
Mendoza A.
Cuno A.
Condori-Fernandez N.
Lovón W.R.
Título de la revista
Revista ISSN
Título del volumen
Springer Science and Business Media Deutschland GmbH
Proyectos de investigación
Unidades organizativas
Número de la revista
[Background] The performance of emotion recognition systems depends heavily on datasets used in their training, validation, or testing stages. [Aims] This research aims to evaluate the extent to which public available physiological datasets created for emotion recognition systems meet a set of reference requirements. [Method] Firstly, we analyze the applicability of some reference requirements proposed for stress datasets and adjust the corresponding evaluation criteria. Secondly, nine public physiological datasets were identified from a previous survey. [Results] None of the evaluated datasets satisfy all the reference requirements in order to be considered as a reference dataset for being used in the construction of reliable emotion recognition systems. [Conclusion] Although the evaluated datasets do not support the whole reference requirements, they provide a baseline for further development. Also, a greater effort is needed to establish specific reference requirements that can appropriately guide the creation of physiological datasets for emotion recognition systems. © 2021, Springer Nature Switzerland AG.
Acknowledgment. A. Mendoza, A. Cuno, N. Condori-Fernandez and W. Ramos acknowledge financial support from the “Proyecto Concytec - Banco Mundial, Mejo-ramiento y Ampliación de los Servicios del Sistema Nacional de Ciencia Tecnología e Innovación Tecnológica” 8682-PE, through its executing unit FONDECYT [Contract N? 014-2019-FONDECYT-BM-INC.INV]. Also, this work has been partially supported by Datos 4.0 (TIN2016-78011-C4-1-R) funded by MINECO-AEI/FEDER-UE.
Palabras clave
Reference requirements, Assessment, Physiological datasets