Design of a Vision Transformer-Based Architecture for Automatic Facial Emotion Monitoring in Workplace Environments

Facial emotion recognition is increasingly considered in affective computing as a mechanism for unobtrusive emotional awareness in organizational environments. This study proposes the design of a Vision Transformer (ViT)-based system architecture for automatic facial emotion monitoring, focusing on deployability, modular integration, and data-governance considerations rather than model benchmarking. The architecture defines a complete pipeline comprising a visual data acquisition layer, a processing backend for transformer-based inference, and a web-based visualization interface intended for aggregated emotional analytics. Publicly available datasets such as FER2013 and AffectNet are identified as reference sources for model adaptation within the proposed framework. The work details system components, data flow, scalability strategies, and privacy-by-design mechanisms, including transient image handling and non-persistent processing. Rather than presenting experimental performance, this study provides a technical blueprint and feasibility analysis intended to guide future implementation and validation of transformer-driven emotion monitoring systems in workplace contexts. The proposed framework aims to bridge the gap between advances in deep learning models and their practical integration into real-world organizational infrastructures.

@article{Caceres2026,
  title     = {Design of a Vision Transformer-Based Architecture for Automatic Facial Emotion Monitoring in Workplace Environments},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {17},
  number    = {2},
  year      = {2026},
  publisher = {The Science and Information Organization},
  author    = {Renzo Sebastian Gonzalez Caceres and Jeramel Melissa Avila Saldaña and Patricia Gissela Pereyra Salvador},
  doi       = {10.14569/IJACSA.2026.0170251},
  url       = {https://doi.org/10.14569/IJACSA.2026.0170251}
}