This study introduces EEG-QtransNet, a quantum classical hybrid neural network designed to address the challenge of excessive parameters in EEG signal classification. By replacing the attention layer in a Transformer with a Variational Quantum Circuit (VQC), the model leverages quantum superposition and entanglement to efficiently model long-range dependencies in EEG data. This substitution reduces the total parameter count by approximately 17% while maintaining classification performance. EEG-QtransNet achieves average classification accuracies of 81.52% and 84.68% on BCI Competition IV-2a and IV-2b datasets, respectively, showing significant improvements over classical architectures. The study validates the method's effectiveness in processing time-series EEG data and analyzes the impact of quantum layers on performance. The results demonstrate the robustness and high precision of the quantum Transformer, offering valuable insights for designing hybrid architectures under limited qubit conditions and guiding future algorithm evaluation and system design.
This study introduces EEG-QtransNet, a quantum classical hybrid neural network designed to address the challenge of excessive parameters in EEG signal classification. By replacing the attention layer in a Transformer with a Variational Quantum Circuit (VQC), the model leverages quantum superposition and entanglement to efficiently model long-range dependencies in EEG data. This substitution reduces the total parameter count by approximately 17% while maintaining classification performance. EEG-QtransNet achieves average classification accuracies of 81.52% and 84.68% on BCI Competition IV-2a and IV-2b datasets, respectively, showing significant improvements over classical architectures. The study validates the method's effectiveness in processing time-series EEG data and analyzes the impact of quantum layers on performance. The results demonstrate the robustness and high precision of the quantum Transformer, offering valuable insights for designing hybrid architectures under limited qubit conditions and guiding future algorithm evaluation and system design.
Medical image classification is a critical component of modern healthcare; however, accurate diagnosis remains challenging due to limited annotated datasets, class imbalance, and the high dimensionality of medical imaging data. To address these challenges, a hybrid quantum-classical neural network (HQCNN) is proposed, integrating classical deep learning with variational quantum learning for medical image classification. The proposed architecture combines a five-layer convolutional neural network (CNN) for hierarchical feature extraction with a lightweight 4-qubit variational quantum circuit (VQC) incorporating quantum state encoding, superposition and entanglement mechanisms, and a quantum attention-Fourier (QAF) module. This hybrid design aims to improve nonlinear feature representation and quantum parameter efficiency while maintaining a shallow quantum circuit suitable for noisy intermediate-scale quantum (NISQ)-era constraints. Experimental evaluation on six MedMNIST benchmark datasets demonstrated competitive performance across both binary and multi-class classification tasks. HQCNN achieved 98.88% accuracy on the binary subset of PathMNIST (classes 0 vs. 1), 97.61% accuracy on the multi-class OrganAMNIST dataset, and 86.29% accuracy on BreastMNIST. Comparative experiments and statistical analyses demonstrated consistent improvements over the controlled BHQNN baseline, while component-wise ablation studies showed that the QAF module, superposition and entanglement mechanisms, and expressive parameterized rotations contributed to classification performance in a complementary and dataset-dependent manner. Moreover, HQCNN reduced the number of trainable quantum parameters by approximately 55.6% compared with the baseline hybrid quantum neural network (BHQNN). Noise-aware simulations further showed that the model retained relatively stable predictive performance under moderate depolarizing noise, supporting further evaluation under near-term quantum computing conditions. Overall, the results demonstrate that HQCNN provides a parameter-efficient hybrid quantum-classical framework for medical image classification and offers a promising foundation for further investigation of quantum-enhanced medical image analysis.
Automated epileptic seizure detection from electroencephalogram (EEG) recordings remains a challenging biomedical signal analysis task because of the nonlinear, non-stationary, and high-dimensional characteristics of neural activity. Although deep learning has substantially improved automated seizure classification, conventional architectures may exhibit limited capability in modeling complex latent feature interactions while maintaining computational efficiency in biomedical applications. This study presents an entanglement-driven hybrid quantum–classical representation learning framework that integrates Continuous Wavelet Transform (CWT)-based time–frequency analysis, EfficientNet-B0 feature extraction, quantum-compatible latent feature compression, angle-based quantum state encoding, and a customized four-qubit Variational Quantum Convolutional Neural Network (QCNN) for EEG seizure classification. The proposed shallow variational quantum architecture is designed to facilitate expressive quantum feature learning while remaining compatible with the computational constraints of near-term noisy intermediate-scale quantum (NISQ) systems. An experimental evaluation was conducted on a balanced subset of 4,000 EEG segments from the UCI Epileptic Seizure Recognition Dataset. Stratified five-fold cross-validation achieved a mean classification accuracy of 97.80% ± 1.50%, demonstrating consistent predictive performance and generalization across several data partitions. Furthermore, evaluation on an independent held-out test set yielded 99.50% accuracy, 99.03% precision, 100.00% recall, 99.51% F1-score, and an area under the ROC curve (AUC) of 1.000. To comprehensively assess the proposed framework, additional investigations, including quantum circuit expressibility, barren plateau analysis, optimization trainability, latent feature-space separability, robustness evaluation, computational scalability, and patch-level quantum attention visualization, were performed, offering complementary evidence regarding representation quality, optimization stability, and model interpretability. Although the proposed framework is currently validated using classical quantum simulation, the results demonstrate the feasibility of hybrid quantum–classical representation learning for intelligent EEG seizure analysis and establish a foundation for future deployment on emerging quantum-computing platforms.
A brain-computer interface (BCI) system enables direct communication between the brain and external devices, offering significant potential for assistive technologies and advanced human-computer interaction. Despite progress, BCI systems face persistent challenges, including signal variability, classification inefficiency, and difficulty adapting to individual users in real time. In this study, we propose a novel hybrid quantum learning model, termed QSVM-QNN, which integrates a Quantum Support Vector Machine (QSVM) with a Quantum Neural Network (QNN), to improve classification accuracy and robustness in EEG-based BCI tasks. Unlike existing models, QSVM-QNN combines the decision boundary capabilities of QSVM with the expressive learning power of QNN, leading to superior generalization performance. The proposed model is evaluated on two benchmark EEG datasets, achieving high accuracies of 0.990 and 0.950, outperforming both classical and standalone quantum models. To demonstrate real-world viability, we further validated the robustness of QNN, QSVM, and QSVM-QNN against six realistic quantum noise models, including bit flip and phase damping. These experiments reveal that QSVM-QNN maintains stable performance under noisy conditions, establishing its applicability for deployment in practical, noisy quantum environments. Beyond BCI, the proposed hybrid quantum architecture is generalizable to other biomedical and time-series classification tasks, offering a scalable and noise-resilient solution for next-generation neurotechnological systems.
Electroencephalography (EEG) is widely used in neuroscience and clinical research for analyzing brain activity. While deep learning models such as EEGNet have shown success in decoding EEG signals, they often struggle with data complexity, inter-subject variability, and noise robustness. Recent advancements in quantum machine learning (QML) offer new opportunities to enhance EEG analysis by leveraging quantum computing’s unique properties. In this study, we extend the previously proposed Quantum-EEGNet (QEEGNet), a hybrid neural network incorporating quantum layers into EEGNet, to investigate its generalization ability across multiple EEG datasets. Our evaluation spans a diverse set of cognitive and motor task datasets, assessing QEEGNet’s performance in different learning scenarios. Experimental results reveal that while QEEGNet demonstrates competitive performance and maintains robustness in certain datasets, its improvements over traditional deep learning methods remain inconsistent. These findings suggest that hybrid quantum-classical architectures require further optimization to fully leverage quantum advantages in EEG processing. Despite these limitations, our study provides new insights into the applicability of QML in EEG research and highlights challenges that must be addressed for future advancements.
Combining variational quantum circuits with classical neural network models is a potential direction for quantum natural language processing (QNLP) in the NISQ (Noisy Intermediate-Scale Quantum) era. We propose a hybrid classical-quantum neural network that enhances a transformer architecture in two key ways: first, by incorporating optimized variational quantum circuits into the self-attention and multilayer perceptron components, and second, by integrating a hybrid convolutional module for effective dimensionality reduction which can reduce the quantum resources required for subsequent layers and enhances the model’s trainability by mitigating issues like the barren plateau phenomenon, thus making it feasible to construct a deeper and more powerful network architecture. Our experiments on three widely-used sentiment analysis datasets demonstrate that the proposed model achieves comparable or even superior performance in terms of accuracy and F1 score compared to classical transformer-based sentiment classification models with similar structures, while reducing the number of parameters through the utilization of quantum advantages.
In neuroscience and therapeutic practice, electroencephalography (EEG) is a vital instrument for tracking and analysing brain activity. While traditional neural network models, like EEG-Net, have made significant progress in interpreting EEG signals, they frequently encounter difficulties due to the great dimensionality and complexity of the data. Quantum machine learning (QML) techniques offer new ways to improve machine learning models, thanks to recent developments in quantum computing. As a forward-looking approach, we present Quantum-EEG Net (QEEG Net), a novel hybrid neural network that combines quantum computing with the classical EEG Net architecture to improve EEG encoding and analysis. While the results may not always outperform conventional methods, it demonstrates its potential. In order to capture more complex patterns in EEG data and maybe provide computational benefits, QEEG Net integrates quantum layers into the neural network. Using the benchmark EEG dataset, BCI Competition IV 2a, we test QEEG Net and show that it consistently performs better than standard EEG-Net on the majority of participants and has other robustness to noise.