Open Access

ARTICLE

Real-Time Mouth State Detection Based on a BiGRU-CLPSO Hybrid Model with Facial Landmark Detection for Healthcare Monitoring Applications

Mong-Fong Horng^1,#, Thanh-Lam Nguyen^1,#, Thanh-Tuan Nguyen^2,*, Chin-Shiuh Shieh^1,*, Lan-Yuen Guo³, Chen-Fu Hung⁴, Chun-Chih Lo¹

1 Department of Electronic Engineering, National Kaohsiung University of Science and Technology, Kaohsiung, 807618, Taiwan
2 Faculty of Electrical and Electronics Engineering, Nha Trang University, Nha Trang, 650000, Vietnam
3 Department of Sports Medicine, College of Medicine, Kaohsiung Medical University, Kaohsiung, 807378, Taiwan
4 Program in Biomedical Engineering, College of Medicine, Kaohsiung Medical University, Kaohsiung, 807378, Taiwan

* Corresponding Authors: Thanh-Tuan Nguyen. Email: ; Chin-Shiuh Shieh. Email:
# These authors contributed equally as co-first authors

(This article belongs to the Special Issue: Artificial Intelligence Models in Healthcare: Challenges, Methods, and Applications)

Computer Modeling in Engineering & Sciences 2026, 146(1), 42 https://doi.org/10.32604/cmes.2025.075064

Received 24 October 2025; Accepted 19 December 2025; Issue published 29 January 2026

Abstract

The global population is rapidly expanding, driving an increasing demand for intelligent healthcare systems. Artificial intelligence (AI) applications in remote patient monitoring and diagnosis have achieved remarkable progress and are emerging as a major development trend. Among these applications, mouth motion tracking and mouth-state detection represent an important direction, providing valuable support for diagnosing neuromuscular disorders such as dysphagia, Bell’s palsy, and Parkinson’s disease. In this study, we focus on developing a real-time system capable of monitoring and detecting mouth state that can be efficiently deployed on edge devices. The proposed system integrates the Facial Landmark Detection technique with an optimized model combining a Bidirectional Gated Recurrent Unit (BiGRU) and Comprehensive Learning Particle Swarm Optimization (CLPSO). We conducted a comprehensive comparison and evaluation of the proposed model against several traditional models using multiple performance metrics, including accuracy, precision, recall, F1-score, cosine similarity, ROC–AUC, and the precision–recall curve. The proposed method achieved an impressive accuracy of 96.57% with an excellent precision of 98.25% on our self-collected dataset, outperforming traditional models and related works in the same field. These findings highlight the potential of the proposed approach for implementation in real-time patient monitoring systems, contributing to improved diagnostic accuracy and supporting healthcare professionals in patient treatment and care.

---

Keywords

---