DS-CNN: Deep Convolutional Neural Networks for Facial Emotion Detection in Children with Down Syndrome during Dolphin-Assisted Therapy
-
Published:2023-08-14
Issue:16
Volume:11
Page:2295
-
ISSN:2227-9032
-
Container-title:Healthcare
-
language:en
-
Short-container-title:Healthcare
Author:
Moreno Escobar Jesús Jaime1ORCID, Morales Matamoros Oswaldo1ORCID, Aguilar del Villar Erika Yolanda1ORCID, Quintana Espinosa Hugo1ORCID, Chanona Hernández Liliana1
Affiliation:
1. Escuela Superior de Ingeniería Mecánica y Eléctrica, Unidad Zacatenco, Instituto Politécnico Nacional, Ciudad de México 07340, Mexico
Abstract
In Mexico, according to data from the General Directorate of Health Information (2018), there is an annual incidence of 689 newborns with Trisomy 21, well-known as Down Syndrome. Worldwide, this incidence is estimated between 1 in every 1000 newborns, approximately. That is why this work focuses on the detection and analysis of facial emotions in children with Down Syndrome in order to predict their emotions throughout a dolphin-assisted therapy. In this work, two databases are used: Exploratory Data Analysis, with a total of 20,214 images, and the Down’s Syndrome Dataset database, with 1445 images for training, validation, and testing of the neural network models. The construction of two architectures based on a Deep Convolutional Neural Network manages an efficiency of 79%, when these architectures are tested with a large reference image database. Then, the architecture that achieves better results is trained, validated, and tested in a small-image database with the facial emotions of children with Down Syndrome, obtaining an efficiency of 72%. However, this increases by 9% when the brain activity of the child is included in the training, resulting in an average precision of 81%. Using electroencephalogram (EEG) signals in a Convolutional Neural Network (CNN) along with the Down’s Syndrome Dataset (DSDS) has promising advantages in the field of brain–computer interfaces. EEG provides direct access to the electrical activity of the brain, allowing for real-time monitoring and analysis of cognitive states. Integrating EEG signals into a CNN architecture can enhance learning and decision-making capabilities. It is important to note that this work has the primary objective of addressing a doubly vulnerable population, as these children also have a disability.
Funder
National Polytechnic Institute (Instituto Poliécnico Nacional) of Mexico Secretariat of Research and Postgraduate (Secretería de Investigación y Posgrado), National Council of Science and Technology of Mexico
Subject
Health Information Management,Health Informatics,Health Policy,Leadership and Management
Reference25 articles.
1. (2023, April 09). Día Mundial del Síndrome de Down. Available online: https://www.un.org/es/observances/down-syndrome-day. 2. Zhao, Q., Rosenbaum, K., Okada, K., Zand, D.J., Sze, R., Summar, M., and Linguraru, M.G. (2013, January 3–7). Automated Down Syndrome detection using facial photographs. Proceedings of the 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Osaka, Japan. 3. Escobar, J.J.M., Matamoros, O.M., del Villar, E.Y.A., Padilla, R.T., Reyes, I.L., Zambrano, B.E., Gómez, B.D.L., and Morfín, V.H.C. (2021). Non-Parametric Evaluation Methods of the Brain Activity of a Bottlenose Dolphin during an Assisted Therapy. Animals, 11. 4. (2023, April 09). SÍNDROME DE DOWN: HABLA, LENGUAJE Y COMUNICACIÓN. Available online: https://psikids.es/2021/09/27/sindrome-de-down-habla-lenguaje-y-comunicacion-2/. 5. Video-based Facial Micro-Expression Analysis: A Survey of Datasets, Features and Algorithms;Ben;IEEE Trans. Pattern Anal. Mach. Intell.,2021
|
|