Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Expert Systems with Applications

EEG-based motor imagery classification with quantum algorithms

Cynthia Olvera, Oscar Montiel, Yoshio Rubio

Published Jan 30, 2024• 28 citations
Publisher
DOI
10.1016/j.eswa.2024.123354

Related papers

Exploring Quantum Machine Learning-Enhanced Models for EEG Data Classification

Stephanie Anne Murray

•Jan 1, 2025•0 citations

Exploring the Usability of Quantum Machine Learning for EEG Signal Classification

Devansh Singh, Yashasvi Kanathey, Yoginii Waykole +4 more

Communications in computer and information science•Jan 1, 2024•4 citations

Motor imagery classification for EEG using quantum approach

Krishna Kant Dixit, Kirti Singh, Chandradeep Bhatt +1 more

This is giving rise to the blended quantum-soft computing methods mimicking algorithms that take benefit of existing capabilities in present-day q-pu development. Here we presented two quantum-classifier methods to classify motor imagery in EEG datasets. The second approach is based on a hybrid classical/quantum network that consists of a fixed feature extraction network and the classifier itself, being parameterized by variational quantum circuit. Whereas, wrapper feature selection with quantum genetic algorithm is employed by the former one. Results: In the task of lowering user-overlap (ii-a) our approach showed a higher performance, and even if not reaching perfect success in classification on target subjects as defined by that metric it achieved at least competitive accuracies compared to other similar method. From our statistical study, we ascertained that the hybrid models outperformed most modern architectures, showing a clear indication of how quantum-hybrid can be quite effective in solving real-world problems.

AIP conference proceedings•Jan 1, 2025•0 citations

Variational Phasor Circuits for Phase-Native Brain-Computer Interface Classification

Dibakar Sigdel

We present the Variational Phasor Circuit (VPC), a deterministic classical learning architecture on the continuous $S^1$ unit-circle manifold. Inspired by variational quantum circuits, VPC replaces dense weight matrices with trainable phase shifts, local unitary mixing, and structured interference in the ambient complex space, giving a unified method for binary and multi-class classification of spatially distributed signals. We evaluate VPC on real motor-imagery electroencephalography (EEG) from the PhysioNet Motor Movement/Imagery database (10 subjects, Common Spatial Pattern features, subject-wise cross-validation), where it attains a mean decoding accuracy of $0.60$ -- the highest among standard brain--computer-interface baselines (linear discriminant analysis, logistic regression, RBF-SVM, and a multilayer perceptron) -- using an order of magnitude fewer parameters and the lowest cross-subject variance. We also characterize capacity honestly: with phase-only shifts and unitary mixing, VPC realizes a linear decision function in a fixed cosine/sine feature lifting, well matched to the largely separable band-power structure of EEG but unable to represent parity-type functions, a ceiling that depth does not raise. These results position unit-circle phase interference as a parameter-efficient alternative to dense neural computation for signal classification, and motivate VPC both as a standalone classifier and a front-end for hybrid phasor-quantum systems.

arXiv:2603.18078•Mar 18, 2026•0 citations

Q-DIVER: Integrated Quantum Transfer Learning and Differentiable Quantum Architecture Search with EEG Data

Junghoon Justin Park, Yeonghyeon Park, Jiook Cha

Integrating quantum circuits into deep learning pipelines remains challenging due to heuristic design limitations. We propose Q-DIVER, a hybrid framework combining a large-scale pretrained EEG encoder (DIVER-1) with a differentiable quantum classifier. Unlike fixed-ansatz approaches, we employ Differentiable Quantum Architecture Search to autonomously discover task-optimal circuit topologies during end-to-end fine-tuning. On the PhysioNet Motor Imagery dataset, our quantum classifier achieves predictive performance comparable to classical multi-layer perceptrons (Test F1: 63.49\%) while using approximately \textbf{50$\times$ fewer task-specific head parameters} (2.10M vs. 105.02M). These results validate quantum transfer learning as a parameter-efficient strategy for high-dimensional biological signal processing.

quant-pharXiv:2603.28122•International Conference on Quantum Communications, Networking, and Computing (QCNC)•Mar 31, 2026•0 citations

EEG-Based Emotion Recognition Using Quantum Machine Learning

Divya Garg, Gyanendra K. Verma, Awadhesh Kumar Singh

SN Computer Science•Jun 24, 2023•16 citations
This is giving rise to the blended quantum-soft computing methods mimicking algorithms that take benefit of existing capabilities in present-day q-pu development. Here we presented two quantum-classifier methods to classify motor imagery in EEG datasets. The second approach is based on a hybrid classical/quantum network that consists of a fixed feature extraction network and the classifier itself, being parameterized by variational quantum circuit. Whereas, wrapper feature selection with quantum genetic algorithm is employed by the former one. Results: In the task of lowering user-overlap (ii-a) our approach showed a higher performance, and even if not reaching perfect success in classification on target subjects as defined by that metric it achieved at least competitive accuracies compared to other similar method. From our statistical study, we ascertained that the hybrid models outperformed most modern architectures, showing a clear indication of how quantum-hybrid can be quite effective in solving real-world problems.
We present the Variational Phasor Circuit (VPC), a deterministic classical learning architecture on the continuous S1S^1S1 unit-circle manifold. Inspired by variational quantum circuits, VPC replaces dense weight matrices with trainable phase shifts, local unitary mixing, and structured interference in the ambient complex space, giving a unified method for binary and multi-class classification of spatially distributed signals. We evaluate VPC on real motor-imagery electroencephalography (EEG) from the PhysioNet Motor Movement/Imagery database (10 subjects, Common Spatial Pattern features, subject-wise cross-validation), where it attains a mean decoding accuracy of 0.600.600.60 -- the highest among standard brain--computer-interface baselines (linear discriminant analysis, logistic regression, RBF-SVM, and a multilayer perceptron) -- using an order of magnitude fewer parameters and the lowest cross-subject variance. We also characterize capacity honestly: with phase-only shifts and unitary mixing, VPC realizes a linear decision function in a fixed cosine/sine feature lifting, well matched to the largely separable band-power structure of EEG but unable to represent parity-type functions, a ceiling that depth does not raise. These results position unit-circle phase interference as a parameter-efficient alternative to dense neural computation for signal classification, and motivate VPC both as a standalone classifier and a front-end for hybrid phasor-quantum systems.
Integrating quantum circuits into deep learning pipelines remains challenging due to heuristic design limitations. We propose Q-DIVER, a hybrid framework combining a large-scale pretrained EEG encoder (DIVER-1) with a differentiable quantum classifier. Unlike fixed-ansatz approaches, we employ Differentiable Quantum Architecture Search to autonomously discover task-optimal circuit topologies during end-to-end fine-tuning. On the PhysioNet Motor Imagery dataset, our quantum classifier achieves predictive performance comparable to classical multi-layer perceptrons (Test F1: 63.49\%) while using approximately \textbf{50×\times× fewer task-specific head parameters} (2.10M vs. 105.02M). These results validate quantum transfer learning as a parameter-efficient strategy for high-dimensional biological signal processing.