Please use this identifier to cite or link to this item:
Title: Emotional AI in Healthcare: a pilot architecture proposal to merge emotion recognition tools
Authors: Marcos-Pablos, S.
García-Peñalvo, F. J.
Vázquez-Ingelmo, A.
Keywords: Emotional AI
Digital Ecosystems
Software Architecture
Issue Date: 27-Oct-2021
Publisher: ACM
Citation: Marcos-Pablos, S., García-Peñalvo, F. J., & Vázquez-Ingelmo, A. (2021). Emotional AI in Healthcare: A Pilot Architecture Proposal to Merge Emotion Recognition Tools. In M. Alier & D. Fonseca (Eds.), Proceedings TEEM’21. Ninth International Conference on Technological Ecosystems for Enhancing Multiculturality (Barcelona, Spain, October 27th – 29th, 2021) (pp. 342-349). ACM.
Abstract: The use of emotional artificial intelligence (EAI) looks promising and is continuing to improve during the last years. However, in order to effectively use EAI to help in the diagnose and treat health conditions there are still significant challenges to be tackled. Be-cause EAI is still under development, one of the most important challenges is to integrate the technology into the health provision process. In this sense, it is important to complement EAI technolo-gies with expert supervision, and to provide health professionals with the necessary tools to make the best of EAI without a deep knowledge of the technology. The present work aims to provide an initial architecture proposal for making use of different available technologies for emotion recognition, where their combination could enhance emotion detection. The proposed architecture is based on an evolutionary approach so to be integrated in digital health ecosystems, so new modules can be easily integrated. In addition, internal data exchange utilizes Robot Operating System (ROS) syntax, so it can also be suitable for physical agents.
ISBN: 978-1-4503-9066-8
Appears in Collections:Publications

Files in This Item:
File Description SizeFormat 
Samuel.pdfArticle1,64 MBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.