EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Recurrent Neural Networks for Mexican Sign Language Interpretation in Healthcare Services

Armando de Jesús Becerril-Carrillo iD, Héctor Julián Selley-Rojas iD, Elizabeth Guevara-Martínez iD

Sensors · 19.12.2025 · 26 (1) · 27

DOI: 10.3390/s26010027 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 19.12.2025. Verfasst von Armando de Jesús Becerril-Carrillo und 2 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Engineering, Universidad Anáhuac México, Avenida Universidad Anáhuac 46, Col. Lomas Anáhuac, Huixquilucan 52786, Estado de Mexico, Mexico. Hauptthemen laut MEDLINE: Sign Language, Delivery of Health Care, Neural Networks, Computer. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In Mexico, the Deaf community faces persistent communication barriers that restrict their integration and access to essential services, particularly in healthcare. Even though approximately two million individuals use Mexican Sign Language (MSL) as their primary form of communication, technological tools for supporting effective interaction remain limited. While recent research in sign-language recognition has led to important advances for several languages, work focused on MSL, particularly for healthcare scenarios, remains scarce. To address this gap, this study introduces a health-oriented dataset of 150 signs, with 800 synthetic video sequences per word, totaling more than 35 GB of data. This dataset was used to train recurrent neural networks with regularization and data augmentation. The best configuration achieved a maximum precision of 98.36% in isolated sign classification, minimizing false positives, which is an essential requirement in clinical applications. Beyond isolated recognition, the main contribution of this study is its exploratory evaluation of sequential narrative inference in MSL. Using short scripted narratives, the system achieved a global sequential recall of 45.45% under a realistic evaluation protocol that enforces temporal alignment. These results highlight both the potential of recurrent architectures in generalizing from isolated gestures to structured sequences and the substantial challenges posed by continuous signing, co-articulation, and signer-specific variation. While not intended for clinical deployment, the methodology, dataset, and open-source implementation presented here establish a reproducible baseline for future research. This work provides initial evidence, tools, and insights to support the long-term development of accessible technologies for the Deaf community in Mexico.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Sign LanguageDelivery of Health CareNeural Networks, ComputerHumansMexicoRecurrent Neural NetworksDeafness

Stichwörter der Autor:innen

GRULSTMMexican Sign Languageartificial intelligencecomputer visiondata augmentationprecisionrecall

Autor:innen und Institutionen

  • Faculty of Engineering, Universidad Anáhuac México, Avenida Universidad Anáhuac 46, Col. Lomas Anáhuac, Huixquilucan 52786, Estado de Mexico, Mexico.

ORCID-Profile: Armando de Jesús Becerril-Carrillo, Héctor Julián Selley-Rojas, Elizabeth Guevara-Martínez

Zitieren

APA

Becerril-Carrillo, A. J., Selley-Rojas, H. J., & Guevara-Martínez, E. (2025). Recurrent Neural Networks for Mexican Sign Language Interpretation in Healthcare Services. Sensors, 26(1), 27. https://doi.org/10.3390/s26010027

Vancouver

Becerril-Carrillo AJ, Selley-Rojas HJ, Guevara-Martínez E. Recurrent Neural Networks for Mexican Sign Language Interpretation in Healthcare Services. Sensors. 2025;26(1):27. doi:10.3390/s26010027

BibTeX
@article{BecerrilCarrillo2025,
  author = {Becerril-Carrillo, Armando de Jesús and Selley-Rojas, Héctor Julián and Guevara-Martínez, Elizabeth},
  title = {Recurrent Neural Networks for Mexican Sign Language Interpretation in Healthcare Services},
  journal = {Sensors},
  year = {2025},
  volume = {26},
  number = {1},
  pages = {27},
  doi = {10.3390/s26010027}
}
Kostenlos starten →