Authors:
S. Rubin Bose, J. Angelin Jeba, B. Judy Flavia, R. Regin, S. Suman Rajest, Moustafa Adel Darwish

Addresses:
School of Computer Science and Engineering, SRM Institute of Science and Technology, Ramapuram, Chennai, Tamil Nadu, India. Department of Electronics and Communication Engineering, S.A. Engineering College, Chennai, Tamil Nadu, India. Department of Research and Development, Dhaanish Ahmed College of Engineering, Chennai, Tamil Nadu, India. Department of Physics, Faculty of Science, Tanta University, Tanta, Gharbia Governorate, Egypt.

Abstract:

Electroencephalography (EEG) provides a powerful non-invasive modality for capturing millisecond-scale brain dynamics, yet traditional analysis pipelines often rely on hand-crafted features and classical models with limited ability to capture nonlinear dependencies. This study introduces Q-EEG, a novel quantum-enhanced computational framework for brain state classification. The proposed approach integrates classical pre-processing with quantum machine learning to exploit the representational capacity of quantum circuits. Raw EEG signals are first band-pass filtered into canonical rhythms—delta (0.5–4 Hz), theta (4–8 Hz), alpha (8–13 Hz), beta (13–30 Hz), and gamma (30–100 Hz)—and artefact removal is performed using ICA. Average band powers are then computed via the PSD and assembled into feature vectors. These normalized features are embedded in quantum states via rotation gates, forming the initial input to a VQC. The VQC models cross-frequency relationships using parameterised rotating layers and entangling operations, with weights trained using hybrid classical–quantum training with the parameter-shift rule and gradient-based optimisers. The computational basis classifies via measurements and evaluates the framework on seizure-versus-non-seizure detection tasks. Compared to SVM and Random Forest, accuracy, precision, recall, and F1-score are measured. Experimental results show that quantum-enhanced EEG analysis may capture complex brain patterns, enabling scalable, interpretable, and clinically useful diagnostic systems. This study shows that Q-EEG can bridge neuroscience with quantum computing, enabling clinical translation.

Keywords: Quantum Electroencephalography (Q-EEG); Independent Component Analysis (ICA); Variational Quantum Circuit (VQC); Power Spectral Density (PSD); Artefact Removal; Random Forest; Quantum Neural Networks.

Received on: 01/05/2025, Revised on: 04/07/2025, Accepted on: 25/08/2025, Published on: 03/03/2026

DOI: 10.69888/FTSNL.2026.000642

FMDB Transactions on Sustainable Neuroscience Letters, 2026 Vol. 1 No. 1, Pages: 22–31

• Views : 31
• Downloads : 8

Download PDF