Joan Gregorio Pérez - Publicación Científica
Título: Dynamic Cognitive Load Estimation via Multi-Modal Eye Tracking and Electroencephalography Transformers
Año: 2026
Venue: IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
DOI: 10.1109/TNNLS.2026.3418902

Abstract:
Understanding real-time cognitive workload is critical for designing adaptive educational interfaces and high-stakes decision-support systems. We propose CogFormer, a novel multimodal cross-attention transformer architecture that synchronizes non-invasive 64-channel EEG streams with high-frequency eye gaze fixations and pupillometry. Across a cohort of 140 participants performing complex algorithmic tasks, CogFormer achieved a 94.2% F1-score in detecting cognitive overload states with a sub-18ms inference latency on consumer-grade hardware.

BibTeX:
@article{pérez2026dynamic,
  author = Pérez, Joan Gregorio and Rostova, Dr. Elena and Ph.D., Sarah Lin,,
  title = {Dynamic Cognitive Load Estimation via Multi-Modal Eye Tracking and Electroencephalography Transformers},
  journal = {IEEE Transactions on Neural Networks and Learning Systems (TNNLS)},
  year = 2026,
  doi = {10.1109/TNNLS.2026.3418902},
  eprint = {2603.04891},
  archiveprefix = {arXiv},
  primaryclass = {cs.AI},
  url = {https://joangregorioperez.com/papers/dynamic-cognitive-load-estimation-multimodal-eeg-transformers},
  abstract = {Understanding real-time cognitive workload is critical for designing adaptive educational interfaces and high-stakes decision-support systems. We propose CogFormer, a novel multimodal cross-attention transformer architecture that synchronizes non-invasive 64-channel EEG streams with high-frequency e...},
  volume = {37},
  number = {4},
  pages = {1120--1135},
  publisher = {IEEE},
}