This project develops an objective approach to pain assessment in clinical settings by harnessing brain–computer interface (BCI) technology and electroencephalography (EEG). Our team developed a deep learning-powered pain detection system capable of not only distinguishing between pain and no-pain states, but also classifying pain severity into low, moderate, and high levels. By analyzing EEG signals with state-of-the-art models, this system significantly outperforms traditional subjective assessments, achieving over 91% accuracy for pain detection and 88% for pain severity classification. This research brings us closer to reliable, data-driven pain measurement—offering new possibilities for patient care, clinical research, and technology-driven health solutions.

Researchers: Hadeel Alshehri, Abeer Al-Nafjan, Mashael Aldayel

Publication:

• Al-Nafjan, A., Alshehri, H., & Aldayel, M. (2025). Objective Pain Assessment Using Deep Learning Through EEG-Based Brain–Computer Interfaces. Biology, 14(2), 210. [View Paper]

• Alshehri, H., Al-Nafjan, A., & Aldayel, M. (2025). Decoding Pain: A Comprehensive Review of Computational Intelligence Methods in Electroencephalography-Based Brain–Computer Interfaces. Diagnostics, 15(3), 300. [View Paper]

This project advances intelligent anxiety detection by leveraging both physiological signals and brain-computer interface (BCI) technology. Using galvanic skin response (GSR) data, our team applied machine learning algorithms—including KNN, SVM, and Random Forest—combined with traditional and autoencoder-based feature extraction methods, achieving anxiety classification accuracies above 98%. In parallel, we deployed EEG-driven BCI systems powered by deep learning, most notably convolutional neural networks, to identify anxiety levels with high reliability using the GAMEEMO dataset and adaptive neurofeedback interventions. These approaches offer promising tools for accurate, accessible mental health monitoring and stress management, especially in resource-limited settings.

Researchers: Abeer Alnafjan , Mashael Aldayel, Ruof AlSuliman, Raghad Alhelal, Danah AlHejji

Publication:

• Al-Nafjan, A., & Aldayel, M. (2024). Anxiety Detection System Based on Galvanic Skin Response Signals. Applied Sciences, 14(23), 10788. [View Paper]

• Aldayel, M., Al-Nafjan, A. (2024). A comprehensive exploration of machine learning techniques for EEG-based anxiety detection. PeerJ Computer Science, 10, e1829 [View Paper]

This project explores how brain–computer interfaces (BCIs) and artificial intelligence can support personal wellness and positive user experiences in digital environments. By leveraging EEG brainwave activity as a unique, noninvasive marker of individual identity, the project addresses the growing need for more natural, secure, and seamless interactions between people and technology. The use of BCIs opens new opportunities for intuitive access, self-awareness, and wellness monitoring, as brain signals offer an objective window into mental and emotional states. Ultimately, this project envisions AI-driven BCI solutions that empower users to engage more confidently and comfortably with technology, advancing digital well-being while maintaining privacy and personalization.

Researchers: Abeer Al-Nafjan ,Lamia Alahaideb ,Mashael Aldayel and Hessah Aljumah

Publication:

• Al-Nafjan, A., Alahaideb, L., Aldayel, M., & Aljumah, H. (2025). EEG-Based Authentication Across Various Event-Related Potentials (ERPs). Sensors, 25(16), 4962. [View Paper]

• Alahaideb, L., Al-Nafjan, A., Aljumah, H., & Aldayel, M. (2025). Brain–Computer Interface for EEG-Based Authentication: Advancements and Practical Implications. Sensors, 25(16), 4946. [View Paper]