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

IEEE International Conference on Smart Information Systems and Technologies (SIST)

Hybrid Quantum-Classical Neural Network Framework for Sleep Efficiency Classification

Mirwais Mohebi, Aiman Bekturganova, Sarsenbek Zhussupbekov, Jandos Amankulov, Assiya Boltaboyeva, Nurdaulet Tasmurzayev

Published May 13, 2026• 0 citations
Publisher

Abstract

Sleep insufficiency now ranks among the leading modifiable risk factors for cardiovascular disease, metabolic disorders, and cognitive decline, affecting hundreds of millions of people worldwide. Yet assessing sleep quality objectively and at scale remains a significant challenge. This paper presents a hybrid quantum-classical neural network that classifies sleep efficiency into good or poor categories using demographic, physiological, and behavioral data from 452 adult participants. The proposed model integrates classical fully connected layers with a six-qubit variational quantum circuit, trained end-to-end via the PennyLane and PyTorch interface. Its performance is evaluated against six established classifiers, namely SVM, Random Forest, XGBoost, MLP, CNN, and LSTM, under a unified stratified five-fold cross-validation protocol. Among all models tested, the proposed network achieves the highest accuracy (0.923) and ROC-AUC (0.962), while using approximately six times fewer trainable parameters than the MLP. A post-hoc SHAP analysis reveals that the model's predictions are driven by physiologically meaningful features, most notably light sleep percentage, deep sleep percentage, and REM sleep percentage. These results suggest that hybrid quantum-classical architectures offer a promising and practical direction for automated sleep health screening.

DOI
10.1109/sist61674.2026.11596027

Related papers

Quantum machine learning for sleep staging of EEG signals

Ye Tian, Jie Ouyang

Sleep staging is an important task in the field of medicine and is significant for diagnosing sleep disorders and assessing overall health. Classical machine learning has made significant progress in this field, and with the development of quantum computing, quantum machine learning (QML) provides a new model for solving complex data classification tasks. In this paper, we propose a hybrid quantum-classical neural network (HQCNN) architecture based on electroencephalogram (EEG) single-channel signals for automating the sleep staging task. The classical part uses a convolutional neural network (CNN) and a long short-term memory network (LSTM) to extract features of the EEG signal, while the quantum part utilizes variational quantum circuit (VQC) for feature mapping and classification. We evaluated the model on different datasets. The results show that the model is satisfactory for classification. This indicates that the combination of quantum computing and machine learning has great potential and provides new research directions and technical approaches for developing more efficient computational models and dealing with complex data problems.

International Conference on Physics and Quantum Computing (ICPQC)•Aug 5, 2025•1 citation

Hybrid Quantum-Classical Neural Networks for Healthcare Prediction Powered by Automated Scientific Discovery

Karthik Meduri, Ruthvik Yedla, Santosh Reddy Addula +5 more

This study presents a reproducible evaluation framework for hybrid quantum-classical neural networks (HQCNNs) in healthcare classification, rather than a new architecture. We assess a four-qubit HQCNN combining a compact classical encoder, a two-layer parameterized quantum circuit (PQC), and a classical readout (441 trainable parameters) against carefully tuned classical baselines on the Wisconsin Diagnostic Breast Cancer (WDBC) dataset under identical five-fold cross-validation. The work is framed as a single-dataset proof-of-concept: the contribution is a documented, shared-fold evaluation protocol with a parameter-matched classical control and a quantified epistemic-informativeness analysis, not a demonstration of general quantum advantage. The HQCNN reached 96.49±1.96% accuracy and 99.44±0.60% ROC-AUC. A parameter-matched classical multilayer perceptron (441 parameters) reached 95.08±1.81% accuracy; the HQCNN’s +1.41 percentage-point edge at equal capacity was not statistically significant (paired t, p=0.056). Across five shared folds, no HQCNN-versus-classical accuracy difference survived Holm–Bonferroni correction (all adjusted p≥0.625), so we report the HQCNN as competitive with, not superior to, strong tuned classical baselines. A multi-split depth ablation showed that circuit depth L∈{1,2,3} had no statistically detectable effect on accuracy (L=2 vs. L=3: Wilcoxon p=1.00); we therefore adopt two variational layers as a practical default rather than an optimum. Under a low-noise simulator (depolarising and amplitude-damping channels, p=0.01), accuracy was 96.49%, indicating robustness only at modest uniform error rates; realistic hardware noise is higher. We additionally apply Bayesian surprise as an epistemic-informativeness heuristic—not a formal generative model—to rank which findings are most worth building on. The framework offers a reproducible, documented evaluation procedure that can support cumulative comparison of hybrid quantum-classical models in healthcare.

Informatics•Jun 22, 2026•0 citations

A Variational Quantum Classifier Approach to Multi-Age Autism Spectrum Disorder Detection

Dave Machnaim, D. Narmadha Naveen, Naveen Sundar G

Early and accurate identification of autism spectrum disorder (ASD) remains a central challenge in clinical neuroscience due to the subjective nature and high resource demands of traditional diagnostic methods. This paper presents a hybrid classical–quantum learning framework for ASD detection, combining the representational power of quantum circuits with the reliability of classical machine learning. The proposed model, a Variational Quantum Classifier (VQC) implemented using PennyLane and PyTorch, processes structured behavioural and demographic screening data from child, adolescent, and adult cohorts. Features are classically preprocessed, encoded into quantum states through angle embedding, and refined using strongly entangling layers, before being post-processed through a classical dense network. Experimental results show perfect classification performance with 100% accuracy, precision, recall, and F1-score, outperforming comparable classical approaches. The training phase exhibited smooth convergence across 70 epochs, confirming model stability and learning efficiency. Although evaluated in simulation, this study establishes a proof-of-concept for leveraging quantum machine learning in medical diagnostics, laying groundwork for future integration with real quantum hardware in clinical screening applications.

International Conference on Electronics, Communication and Aerospace Technology (ICECA)•Nov 5, 2025•0 citations

HQCNN: A Hybrid Quantum-Classical Neural Network for Medical Image Classification

Shahjalal, Jahid Karim Fahim, Pintu Chandra Paul +3 more

Classification of medical images plays a vital role in medical image analysis; however, it remains challenging due to the limited availability of labeled data, class imbalances, and the complexity of medical patterns. To overcome these challenges, we propose a novel Hybrid Quantum-Classical Neural Network (HQCNN) for both binary and multi-class classification. The architecture of HQCNN integrates a five-layer classical convolutional backbone with a 4-qubit variational quantum circuit that incorporates quantum state encoding, superpositional entanglement, and a Fourier-inspired quantum attention mechanism. We evaluate the model on six MedMNIST v2 benchmark datasets. The HQCNN consistently outperforms classical and quantum baselines, achieving up to 99.91% accuracy and 100.00% AUC on PathMNIST (binary) and 99.95% accuracy on OrganAMNIST (multi-class) with strong robustness on noisy datasets like BreastMNIST (87.18% accuracy). The model demonstrates superior generalization capability and computational efficiency, accomplished with significantly fewer trainable parameters, making it suitable for data-scarce scenarios. Our findings provide strong empirical evidence that hybrid quantum-classical models can advance medical imaging tasks.

arXiv:2509.14277•Sep 16, 2025•5 citations

A Hybrid Deep-Quantum Framework for Robust Stress Classification from EEG Signals

Krishan Sharma, Jayesh V. Hire, Kartike Pushkarna +2 more

Abstract Mental stress detection through electroencephalography (EEG) signals faces difficulties because EEG signals display non-stationary behavior and are vulnerable to artifact interference. The research introduces a hybrid deep-quantum learning framework which combines a one-dimensional convolutional neural network (1D-CNN) with a quantum support vector classifier (QSVC) to differentiate between stress and calm states. The CNN functions as a trainable feature extractor which converts raw EEG time-series data into compressed latent representations that undergo mapping to a quantum Hilbert space through ZZFeatureMap before being classified by a quantum kernel. The research demonstrates through experiments on a multi-subject EEG dataset that the hybrid model reaches its highest accuracy of (81.00%) (F1: 0.81) under optimal configuration using 8-dimensional features with MinMax scaling to [0,1] and 1000 training samples because it surpasses both the classical SVM (76.80%) and end-to-end CNN (78.85%) baselines. The analysis demonstrates that quantum kernel performance depends on feature dimensionality and scaling because lower dimensions (F-4) lack expressivity while higher dimensions (F-12) reach a performance limit and scaling to [-1,1] causes accuracy loss of 16 percentage points when compared to [0,1] scaling. The quantum classifier shows good sample efficiency because it gains more from additional training data compared to the traditional model. The research demonstrates that hybrid deep-quantum architectures function in the NISQ era while creating a performance standard for quantum-based physiological signal processing.

•Aug 19, 2026•0 citations

Hybrid quantum-classical classification of waste using the TrashNet dataset

MOHAMMAD SALAH UDDIN

This study presents a hybrid quantum-classical model for classifying waste images from the TrashNet dataset. TrashNet is a publicly accessible dataset of waste classifications. A classical convolutional neural network is used to extract and reduce image features. These features are then passed into a variational quantum circuit with 4 qubits and a circuit depth of 3. The quantum layer performs the final classification. The system is implemented using PyTorch and PennyLane and trained on a simulated quantum backend. The hybrid model achieves 87.4% test accuracy using fewer than 300 trainable parameters. In comparison, a baseline classical Convolutional Neural Network (CNN) with similar accuracy required more than 11,260 parameters. Furthermore, the quantum model provides 1.6 times faster estimation and converges more faster during training. These results indicate that quantum models can reduce parameter calculations and improve computational efficiency. This work highlights the potential of quantum machine learning for low-resource, sustainable AI applications.

Machine Learning Engineering•May 27, 2026•0 citations
Sleep insufficiency now ranks among the leading modifiable risk factors for cardiovascular disease, metabolic disorders, and cognitive decline, affecting hundreds of millions of people worldwide. Yet assessing sleep quality objectively and at scale remains a significant challenge. This paper presents a hybrid quantum-classical neural network that classifies sleep efficiency into good or poor categories using demographic, physiological, and behavioral data from 452 adult participants. The proposed model integrates classical fully connected layers with a six-qubit variational quantum circuit, trained end-to-end via the PennyLane and PyTorch interface. Its performance is evaluated against six established classifiers, namely SVM, Random Forest, XGBoost, MLP, CNN, and LSTM, under a unified stratified five-fold cross-validation protocol. Among all models tested, the proposed network achieves the highest accuracy (0.923) and ROC-AUC (0.962), while using approximately six times fewer trainable parameters than the MLP. A post-hoc SHAP analysis reveals that the model's predictions are driven by physiologically meaningful features, most notably light sleep percentage, deep sleep percentage, and REM sleep percentage. These results suggest that hybrid quantum-classical architectures offer a promising and practical direction for automated sleep health screening.
Sleep staging is an important task in the field of medicine and is significant for diagnosing sleep disorders and assessing overall health. Classical machine learning has made significant progress in this field, and with the development of quantum computing, quantum machine learning (QML) provides a new model for solving complex data classification tasks. In this paper, we propose a hybrid quantum-classical neural network (HQCNN) architecture based on electroencephalogram (EEG) single-channel signals for automating the sleep staging task. The classical part uses a convolutional neural network (CNN) and a long short-term memory network (LSTM) to extract features of the EEG signal, while the quantum part utilizes variational quantum circuit (VQC) for feature mapping and classification. We evaluated the model on different datasets. The results show that the model is satisfactory for classification. This indicates that the combination of quantum computing and machine learning has great potential and provides new research directions and technical approaches for developing more efficient computational models and dealing with complex data problems.
This study presents a reproducible evaluation framework for hybrid quantum-classical neural networks (HQCNNs) in healthcare classification, rather than a new architecture. We assess a four-qubit HQCNN combining a compact classical encoder, a two-layer parameterized quantum circuit (PQC), and a classical readout (441 trainable parameters) against carefully tuned classical baselines on the Wisconsin Diagnostic Breast Cancer (WDBC) dataset under identical five-fold cross-validation. The work is framed as a single-dataset proof-of-concept: the contribution is a documented, shared-fold evaluation protocol with a parameter-matched classical control and a quantified epistemic-informativeness analysis, not a demonstration of general quantum advantage. The HQCNN reached 96.49±1.96% accuracy and 99.44±0.60% ROC-AUC. A parameter-matched classical multilayer perceptron (441 parameters) reached 95.08±1.81% accuracy; the HQCNN’s +1.41 percentage-point edge at equal capacity was not statistically significant (paired t, p=0.056). Across five shared folds, no HQCNN-versus-classical accuracy difference survived Holm–Bonferroni correction (all adjusted p≥0.625), so we report the HQCNN as competitive with, not superior to, strong tuned classical baselines. A multi-split depth ablation showed that circuit depth L∈{1,2,3} had no statistically detectable effect on accuracy (L=2 vs. L=3: Wilcoxon p=1.00); we therefore adopt two variational layers as a practical default rather than an optimum. Under a low-noise simulator (depolarising and amplitude-damping channels, p=0.01), accuracy was 96.49%, indicating robustness only at modest uniform error rates; realistic hardware noise is higher. We additionally apply Bayesian surprise as an epistemic-informativeness heuristic—not a formal generative model—to rank which findings are most worth building on. The framework offers a reproducible, documented evaluation procedure that can support cumulative comparison of hybrid quantum-classical models in healthcare.
Early and accurate identification of autism spectrum disorder (ASD) remains a central challenge in clinical neuroscience due to the subjective nature and high resource demands of traditional diagnostic methods. This paper presents a hybrid classical–quantum learning framework for ASD detection, combining the representational power of quantum circuits with the reliability of classical machine learning. The proposed model, a Variational Quantum Classifier (VQC) implemented using PennyLane and PyTorch, processes structured behavioural and demographic screening data from child, adolescent, and adult cohorts. Features are classically preprocessed, encoded into quantum states through angle embedding, and refined using strongly entangling layers, before being post-processed through a classical dense network. Experimental results show perfect classification performance with 100% accuracy, precision, recall, and F1-score, outperforming comparable classical approaches. The training phase exhibited smooth convergence across 70 epochs, confirming model stability and learning efficiency. Although evaluated in simulation, this study establishes a proof-of-concept for leveraging quantum machine learning in medical diagnostics, laying groundwork for future integration with real quantum hardware in clinical screening applications.
Classification of medical images plays a vital role in medical image analysis; however, it remains challenging due to the limited availability of labeled data, class imbalances, and the complexity of medical patterns. To overcome these challenges, we propose a novel Hybrid Quantum-Classical Neural Network (HQCNN) for both binary and multi-class classification. The architecture of HQCNN integrates a five-layer classical convolutional backbone with a 4-qubit variational quantum circuit that incorporates quantum state encoding, superpositional entanglement, and a Fourier-inspired quantum attention mechanism. We evaluate the model on six MedMNIST v2 benchmark datasets. The HQCNN consistently outperforms classical and quantum baselines, achieving up to 99.91% accuracy and 100.00% AUC on PathMNIST (binary) and 99.95% accuracy on OrganAMNIST (multi-class) with strong robustness on noisy datasets like BreastMNIST (87.18% accuracy). The model demonstrates superior generalization capability and computational efficiency, accomplished with significantly fewer trainable parameters, making it suitable for data-scarce scenarios. Our findings provide strong empirical evidence that hybrid quantum-classical models can advance medical imaging tasks.
Abstract Mental stress detection through electroencephalography (EEG) signals faces difficulties because EEG signals display non-stationary behavior and are vulnerable to artifact interference. The research introduces a hybrid deep-quantum learning framework which combines a one-dimensional convolutional neural network (1D-CNN) with a quantum support vector classifier (QSVC) to differentiate between stress and calm states. The CNN functions as a trainable feature extractor which converts raw EEG time-series data into compressed latent representations that undergo mapping to a quantum Hilbert space through ZZFeatureMap before being classified by a quantum kernel. The research demonstrates through experiments on a multi-subject EEG dataset that the hybrid model reaches its highest accuracy of (81.00%) (F1: 0.81) under optimal configuration using 8-dimensional features with MinMax scaling to [0,1] and 1000 training samples because it surpasses both the classical SVM (76.80%) and end-to-end CNN (78.85%) baselines. The analysis demonstrates that quantum kernel performance depends on feature dimensionality and scaling because lower dimensions (F-4) lack expressivity while higher dimensions (F-12) reach a performance limit and scaling to [-1,1] causes accuracy loss of 16 percentage points when compared to [0,1] scaling. The quantum classifier shows good sample efficiency because it gains more from additional training data compared to the traditional model. The research demonstrates that hybrid deep-quantum architectures function in the NISQ era while creating a performance standard for quantum-based physiological signal processing.
This study presents a hybrid quantum-classical model for classifying waste images from the TrashNet dataset. TrashNet is a publicly accessible dataset of waste classifications. A classical convolutional neural network is used to extract and reduce image features. These features are then passed into a variational quantum circuit with 4 qubits and a circuit depth of 3. The quantum layer performs the final classification. The system is implemented using PyTorch and PennyLane and trained on a simulated quantum backend. The hybrid model achieves 87.4% test accuracy using fewer than 300 trainable parameters. In comparison, a baseline classical Convolutional Neural Network (CNN) with similar accuracy required more than 11,260 parameters. Furthermore, the quantum model provides 1.6 times faster estimation and converges more faster during training. These results indicate that quantum models can reduce parameter calculations and improve computational efficiency. This work highlights the potential of quantum machine learning for low-resource, sustainable AI applications.