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

Quantum Science and Technology

QBioBench: benchmark of quantum machine learning for peripheral biosignals on real hardware

Marek Sokol, Jan Hejda, Petr Volf, Patrik Kutílek

Published Oct 21, 2026• 0 citations
PDF (CC BY)Publisher

Abstract

Abstract Claims of quantum advantage in machine learning often rest on classical comparators that lack the same features, on simulation alone, and on unreported hardware cost. QBioBench is a benchmark of quantum machine learning on peripheral biosignals that holds quantum and classical models to the same features and reports calibration and hardware cost. It comprises three clinical tasks, 12-lead ECG diagnosis (PTB-XL), single-lead apnea detection (Apnea-ECG), and wearable stress detection, each reduced to six to eight shared dimensions. A factorial grid of projected and fidelity quantum kernels and variational classifiers is screened in noisy simulation, and the promoted configurations are evaluated in an exploratory study on an IBM Nighthawk r2 processor on the full test pools of 510 apnea minutes and 512 PTB-XL records. Every prediction is recovered from the device records, intervals resample recordings or patients, and classical baselines are trained on the same units and tested on the same executed inputs. No quantum model reaches its matched support vector machine in ROC-AUC on either primary task, and none is separably better in balanced accuracy. The angle-encoded fidelity and projected kernels reach ROC-AUC 0.697 and 0.693 on apnea, paired differences of − 0.127 and − 0.119 to the support vector machine, and both are classical by construction, since the entangling layer of the encoding cancels from the fidelity kernel and leaves closed-form local expectations in the projected kernel. A variational classifier comes closest, reaching 0.797 on apnea (difference − 0.012 , 95% interval [ − 0.052 , + 0.027 ] ), and falls to chance without its two-qubit gates. Test sets of the size that circuit budgets favor are unreliable, as random 80-minute subsets of the apnea pool give the fidelity kernel a central 95% range of ROC-AUC from 0.589 to 0.797. Readout mitigation changed ROC-AUC by at most 0.015.

DOI
10.1088/2058-9565/aeb71e

Related papers

Matched but Not Better: An Equivalence-Tested Benchmark of Quantum Machine Learning on Six Clinical Datasets and the QML-Health-READY Reporting Framework

Mohammed Siraj B, Gousia Habib, Ruban S

Background: Quantum machine learning (QML) is promoted for clinical prediction, but comparisons with classical models are rarely paired or tested for equivalence. Methods: We compared a quantum-kernel support vector machine (QSVM; 4 qubits, tuned bandwidth) and a variational quantum classifier (VQC) with five tuned classical models across six public clinical datasets. All models used identical four-component inputs and 25 cross-validation splits. Paired AUROC differences were assessed using a corrected resampled t-test, Holm-adjusted equivalence tests (margins: +/-0.02 and +/-0.05), and random-effects pooling. Ablation, noise, finite-shot, and implementation-fault analyses were conducted. We propose QML-Health-READY, an eight-domain reporting framework. Results: Neither quantum model significantly outperformed any classical comparator. Pooled across datasets, QSVM differed from the kernel-matched radial basis function (RBF) SVM by -0.006 AUROC (95% CI: -0.017 to +0.004), equivalent to +/-0.02. VQC differed from the best classical model by -0.007 (95% CI: -0.019 to +0.004). QSVM was equivalent to RBF SVM within +/-0.05 in four of six datasets but was significantly worse than the best classical model on NHANES 2017-18 (-0.076). A classically trivial product-state kernel performed as well as the entangling kernel. With depolarizing noise (p = 0.01) and 1,024 shots per kernel entry, QSVM AUROC decreased by 0.054 (95% CI: 0.036 to 0.071). Untuned bandwidth produced near-chance AUROC (0.48-0.59). Conclusions: Correctly configured quantum classifiers approached but did not exceed tuned classical models. Finite-shot estimation, rather than gate noise, was their main practical cost, while configuration errors could reverse conclusions. QML-Health-READY defines reporting requirements for credible claims.

arXiv:2611.05442•Nov 3, 2026•0 citations

Benchmarking Quantum Kernel Support Vector Machines Against Classical Baselines on Tabular Data: A Rigorous Empirical Study with Hardware Validation

Siavash Kakavand, Christoph Strohmeyer, Michael Schlotter

Quantum kernel methods have been proposed as a promising approach for leveraging near-term quantum computers for supervised learning, yet rigorous benchmarks against strong classical baselines remain scarce. We present a comprehensive empirical study of quantum kernel support vector machines (QSVMs) across nine binary classification datasets, four quantum feature maps, three classical kernels, and multiple noise models, totalling 970 experiments with strict nested cross-validation. Our analysis spans four phases: (i) statistical significance testing, revealing that none of 29 pairwise quantum-classical comparisons reach significance at $α= 0.05$; (ii) learning curve analysis over six training fractions, showing steeper quantum slopes on six of eight datasets that nonetheless fail to close the gap to the best classical baseline; (iii) hardware validation on IBM ibm_fez (Heron r2), demonstrating kernel fidelity $r \geq 0.976$ across six experiments; and (iv) seed sensitivity analysis confirming reproducibility (mean CV 1.4%). A Kruskal-Wallis factorial analysis reveals that dataset choice dominates performance variance ($\varepsilon^2 = 0.73$), while kernel type accounts for only 9%. Spectral analysis offers a mechanistic explanation: current quantum feature maps produce eigenspectra that are either too flat or too concentrated, missing the intermediate profile of the best classical kernel, the radial basis function (RBF). Quantum kernel training (QKT) via kernel-target alignment yields the single competitive result -- balanced accuracy 0.968 on breast cancer -- but with ~2,000x computational overhead. Our findings provide actionable guidelines for quantum kernel research. The complete benchmark suite is publicly available to facilitate reproduction and extension.

quant-pharXiv:2604.18837•Apr 22, 2026•6 citations

Optimized Quantum Classifiers for the Prevention of Anxiety Disorders Using Wearable Data

Spyridon Papamentzelopoulos, Sotiris Nikoletseas

Quantum machine learning (QML) provides a framework for benchmarking wearable biosignal classification relevant to stress detection. Motivated by the burden of stress-related conditions, this study compares three quantum classifiers with seven classical baselines using heart rate and respiration rate features as inputs under noise-free and noisy conditions. Uncertainty was quantified using Nadeau–Bengio-corrected confidence intervals and percentile bootstrap (B=1000). The variational quantum classifier (VQC) achieved an accuracy of 99.47%/97.30% (noise-free/noisy), the quantum support vector classifier (QSVC) achieved 99.90%/99.37%, and PegasosQSVC achieved 99.80%/99.70%. Additionally, under the assessed proof-of-concept conditions, statistical equivalence between the QSVC and the best-performing classical model was established at Δ=1 pp; PegasosQSVC under noise achieved equivalence at Δ=2 pp with accuracy degradation of less than 0.10 pp. The time feature was identified as the primary separability driver in a post hoc classical ablation. Tree-based models were robust on physiological features alone. The surveyed methods provide a reproducible, noise-aware benchmark for wearable physiological signal classification; however, the reported high accuracies are based on a deliberately separable proof-of-concept benchmark and do not demonstrate clinical utility or a quantum advantage.

Applied Sciences•Jun 17, 2026•1 citation

A Noiseless-Simulation Reference Baseline for ECG Arrhythmia Classification: Quantum-Kernel SVM and Variational Quantum Classifier vs. Classical Models on MIT-BIH

Seung-Hong Oh, Ji‐Young Yeo, Sungkwan Youm

This study constructs a reproducible head-to-head comparison between two intermediate-scale quantum (NISQ) classifier families and three classical baselines for binary heartbeat classification on the MIT–BIH Arrhythmia Database, evaluated as a noiseless-simulation reference. From twenty MIT–BIH records a balanced set of three hundred Normal and premature ventricular contraction (PVC) beats is extracted with six morphological features per beat. A quantum-kernel support vector machine using a ZZFeatureMap fidelity kernel, a variational quantum classifier with an EfficientSU2 ansatz, and three classical baselines (RBF support vector machine, logistic regression, random forest) are evaluated on identical splits and then improved across six improvement rounds plus a seventh audit round, which sweep the feature map and the SVM cost, average the Gram matrices of three feature-map instances that resolve to two distinct encoders, add a projected quantum kernel and multiple-kernel learning, widen the embedding to eight qubits with two derived features and light angle-space augmentation, stack quantum and classical heads, and re-run the best recipe over five seeds. On a ninety-sample held-out test set the classical baselines reach 0.989 accuracy at millisecond wall clock, while the best quantum head at the baseline configuration trails by 22.2 accuracy points. The eight-qubit augmented kernel-sum head reaches 0.911 accuracy, and a five-seed audit of the same recipe gives 0.869±0.035, so the residual gap is stable but not closed. Per-round results, resource accounting and calibration analyses are reported in the body.

IEEE Access•Jan 1, 2026•0 citations

Hardware Robustness of Quantum Machine Learning Kernels for Malware Detection

Mary L. Cotrupi, Allison Aurilio, Sean Sanpietro +4 more

Quantum Machine Learning (QML) is beginning to show promise as an emerging technology for cybersecurity tasks. One such task is malware detection, which remains a difficult and critical problem for both individuals and today's organizations. While there is a growing literature on applying QML to malware analysis, many studies remain confined to simulators, leaving open the question of how simulation results translate to the Noisy Intermediate-Scale Quantum (NISQ) machines that exist today. In this paper, we compare quantum-kernel classification across four execution environments---exact statevector evaluation, ideal shot-based Qiskit Aer, noisy Aer, and the IBM Quantum System One housed at Rensselaer Polytechnic Institute---and include matched classical baselines. Our contributions are twofold: first, we benchmark the full pipeline on real NISQ hardware; second, we provide a reproducible case study quantifying how hardware noise affects quantum-kernel geometry and downstream classification accuracy. Although we do not demonstrate quantum advantage, hardware-minus-exact balanced accuracy remained within two percentage points under the tested conditions despite substantial kernel distortion for the wider circuits. This is evidence of empirical stability, not formal statistical equivalence. Feature compression using principal component analysis (PCA) substantially reduced hardware-induced kernel distortion, although its effect on predictive accuracy was dataset dependent. Our results provide a grounded benchmark for cybersecurity practitioners evaluating NISQ-ready QML pipelines.

Proceedings of the AAAI Symposium Series•Nov 6, 2026•0 citations

Quantum Machine Learning Approaches

Lukas Dubois

Quantum machine learning sits at the intersection of quantum computing and artificial intelligence, seeking to exploitquantum mechanical phenomena -- superposition, entanglement, and interference -- to achieve computationaladvantages for learning tasks. This study presents a systematic evaluation of five quantum ML approaches -- variationalquantum classifiers (VQC), quantum kernel methods, quantum reservoir computing, quantum Boltzmann machines, andhybrid quantum-classical neural networks -- benchmarked against classical counterparts on both simulated quantumhardware (up to 30 qubits) and real NISQ devices (IBM Quantum, 27 qubits). Evaluations spanned four task categories:binary classification on structured datasets (6 UCI benchmarks), quantum chemistry property prediction (QM9 molecularenergies), generative modelling (learning probability distributions), and optimisation (Max-Cut on random graphs). A totalof 1,920 experiments were conducted. On classical structured datasets, no quantum method outperformed the bestclassical baseline (XGBoost or SVM) at any problem size accessible to current quantum hardware (up to 30 features),with quantum kernel methods achieving parity at 0.4 +- 0.8% accuracy difference but at 100-1000x higher computationalcost. On quantum chemistry, variational quantum eigensolvers showed a genuine advantage for small molecules (H2,LiH, BeH2): achieving chemical accuracy (1 kcal/mol) with 4-12 qubits where classical methods required exponentiallymore compute for equivalent accuracy. Noise on real NISQ devices degraded all quantum ML methods by 8.4-22.6%relative to noiseless simulation, with error mitigation recovering 42-68% of the noise-induced loss. The quantumadvantage threshold -- the problem size at which quantum methods become faster than classical for equivalent accuracy-- was estimated at 50-100 logical qubits for quantum chemistry and 200+ logical qubits for general ML tasks, placingpractical quantum ML advantage beyond current NISQ capabilities but within plausible reach of fault-tolerant devices. Apractical assessment framework mapping task type, problem structure, and available quantum hardware to expectedquantum advantage is proposed.

Bio-QI Journal•Jul 23, 2023•0 citations
Abstract Claims of quantum advantage in machine learning often rest on classical comparators that lack the same features, on simulation alone, and on unreported hardware cost. QBioBench is a benchmark of quantum machine learning on peripheral biosignals that holds quantum and classical models to the same features and reports calibration and hardware cost. It comprises three clinical tasks, 12-lead ECG diagnosis (PTB-XL), single-lead apnea detection (Apnea-ECG), and wearable stress detection, each reduced to six to eight shared dimensions. A factorial grid of projected and fidelity quantum kernels and variational classifiers is screened in noisy simulation, and the promoted configurations are evaluated in an exploratory study on an IBM Nighthawk r2 processor on the full test pools of 510 apnea minutes and 512 PTB-XL records. Every prediction is recovered from the device records, intervals resample recordings or patients, and classical baselines are trained on the same units and tested on the same executed inputs. No quantum model reaches its matched support vector machine in ROC-AUC on either primary task, and none is separably better in balanced accuracy. The angle-encoded fidelity and projected kernels reach ROC-AUC 0.697 and 0.693 on apnea, paired differences of − 0.127 and − 0.119 to the support vector machine, and both are classical by construction, since the entangling layer of the encoding cancels from the fidelity kernel and leaves closed-form local expectations in the projected kernel. A variational classifier comes closest, reaching 0.797 on apnea (difference − 0.012 , 95% interval [ − 0.052 , + 0.027 ] ), and falls to chance without its two-qubit gates. Test sets of the size that circuit budgets favor are unreliable, as random 80-minute subsets of the apnea pool give the fidelity kernel a central 95% range of ROC-AUC from 0.589 to 0.797. Readout mitigation changed ROC-AUC by at most 0.015.
Background: Quantum machine learning (QML) is promoted for clinical prediction, but comparisons with classical models are rarely paired or tested for equivalence. Methods: We compared a quantum-kernel support vector machine (QSVM; 4 qubits, tuned bandwidth) and a variational quantum classifier (VQC) with five tuned classical models across six public clinical datasets. All models used identical four-component inputs and 25 cross-validation splits. Paired AUROC differences were assessed using a corrected resampled t-test, Holm-adjusted equivalence tests (margins: +/-0.02 and +/-0.05), and random-effects pooling. Ablation, noise, finite-shot, and implementation-fault analyses were conducted. We propose QML-Health-READY, an eight-domain reporting framework. Results: Neither quantum model significantly outperformed any classical comparator. Pooled across datasets, QSVM differed from the kernel-matched radial basis function (RBF) SVM by -0.006 AUROC (95% CI: -0.017 to +0.004), equivalent to +/-0.02. VQC differed from the best classical model by -0.007 (95% CI: -0.019 to +0.004). QSVM was equivalent to RBF SVM within +/-0.05 in four of six datasets but was significantly worse than the best classical model on NHANES 2017-18 (-0.076). A classically trivial product-state kernel performed as well as the entangling kernel. With depolarizing noise (p = 0.01) and 1,024 shots per kernel entry, QSVM AUROC decreased by 0.054 (95% CI: 0.036 to 0.071). Untuned bandwidth produced near-chance AUROC (0.48-0.59). Conclusions: Correctly configured quantum classifiers approached but did not exceed tuned classical models. Finite-shot estimation, rather than gate noise, was their main practical cost, while configuration errors could reverse conclusions. QML-Health-READY defines reporting requirements for credible claims.
Quantum kernel methods have been proposed as a promising approach for leveraging near-term quantum computers for supervised learning, yet rigorous benchmarks against strong classical baselines remain scarce. We present a comprehensive empirical study of quantum kernel support vector machines (QSVMs) across nine binary classification datasets, four quantum feature maps, three classical kernels, and multiple noise models, totalling 970 experiments with strict nested cross-validation. Our analysis spans four phases: (i) statistical significance testing, revealing that none of 29 pairwise quantum-classical comparisons reach significance at α=0.05α= 0.05α=0.05; (ii) learning curve analysis over six training fractions, showing steeper quantum slopes on six of eight datasets that nonetheless fail to close the gap to the best classical baseline; (iii) hardware validation on IBM ibm_fez (Heron r2), demonstrating kernel fidelity r≥0.976r \geq 0.976r≥0.976 across six experiments; and (iv) seed sensitivity analysis confirming reproducibility (mean CV 1.4%). A Kruskal-Wallis factorial analysis reveals that dataset choice dominates performance variance (ε2=0.73\varepsilon^2 = 0.73ε2=0.73), while kernel type accounts for only 9%. Spectral analysis offers a mechanistic explanation: current quantum feature maps produce eigenspectra that are either too flat or too concentrated, missing the intermediate profile of the best classical kernel, the radial basis function (RBF). Quantum kernel training (QKT) via kernel-target alignment yields the single competitive result -- balanced accuracy 0.968 on breast cancer -- but with ~2,000x computational overhead. Our findings provide actionable guidelines for quantum kernel research. The complete benchmark suite is publicly available to facilitate reproduction and extension.
Quantum machine learning (QML) provides a framework for benchmarking wearable biosignal classification relevant to stress detection. Motivated by the burden of stress-related conditions, this study compares three quantum classifiers with seven classical baselines using heart rate and respiration rate features as inputs under noise-free and noisy conditions. Uncertainty was quantified using Nadeau–Bengio-corrected confidence intervals and percentile bootstrap (B=1000). The variational quantum classifier (VQC) achieved an accuracy of 99.47%/97.30% (noise-free/noisy), the quantum support vector classifier (QSVC) achieved 99.90%/99.37%, and PegasosQSVC achieved 99.80%/99.70%. Additionally, under the assessed proof-of-concept conditions, statistical equivalence between the QSVC and the best-performing classical model was established at Δ=1 pp; PegasosQSVC under noise achieved equivalence at Δ=2 pp with accuracy degradation of less than 0.10 pp. The time feature was identified as the primary separability driver in a post hoc classical ablation. Tree-based models were robust on physiological features alone. The surveyed methods provide a reproducible, noise-aware benchmark for wearable physiological signal classification; however, the reported high accuracies are based on a deliberately separable proof-of-concept benchmark and do not demonstrate clinical utility or a quantum advantage.
This study constructs a reproducible head-to-head comparison between two intermediate-scale quantum (NISQ) classifier families and three classical baselines for binary heartbeat classification on the MIT–BIH Arrhythmia Database, evaluated as a noiseless-simulation reference. From twenty MIT–BIH records a balanced set of three hundred Normal and premature ventricular contraction (PVC) beats is extracted with six morphological features per beat. A quantum-kernel support vector machine using a ZZFeatureMap fidelity kernel, a variational quantum classifier with an EfficientSU2 ansatz, and three classical baselines (RBF support vector machine, logistic regression, random forest) are evaluated on identical splits and then improved across six improvement rounds plus a seventh audit round, which sweep the feature map and the SVM cost, average the Gram matrices of three feature-map instances that resolve to two distinct encoders, add a projected quantum kernel and multiple-kernel learning, widen the embedding to eight qubits with two derived features and light angle-space augmentation, stack quantum and classical heads, and re-run the best recipe over five seeds. On a ninety-sample held-out test set the classical baselines reach 0.989 accuracy at millisecond wall clock, while the best quantum head at the baseline configuration trails by 22.2 accuracy points. The eight-qubit augmented kernel-sum head reaches 0.911 accuracy, and a five-seed audit of the same recipe gives 0.869±0.035, so the residual gap is stable but not closed. Per-round results, resource accounting and calibration analyses are reported in the body.
Quantum Machine Learning (QML) is beginning to show promise as an emerging technology for cybersecurity tasks. One such task is malware detection, which remains a difficult and critical problem for both individuals and today's organizations. While there is a growing literature on applying QML to malware analysis, many studies remain confined to simulators, leaving open the question of how simulation results translate to the Noisy Intermediate-Scale Quantum (NISQ) machines that exist today. In this paper, we compare quantum-kernel classification across four execution environments---exact statevector evaluation, ideal shot-based Qiskit Aer, noisy Aer, and the IBM Quantum System One housed at Rensselaer Polytechnic Institute---and include matched classical baselines. Our contributions are twofold: first, we benchmark the full pipeline on real NISQ hardware; second, we provide a reproducible case study quantifying how hardware noise affects quantum-kernel geometry and downstream classification accuracy. Although we do not demonstrate quantum advantage, hardware-minus-exact balanced accuracy remained within two percentage points under the tested conditions despite substantial kernel distortion for the wider circuits. This is evidence of empirical stability, not formal statistical equivalence. Feature compression using principal component analysis (PCA) substantially reduced hardware-induced kernel distortion, although its effect on predictive accuracy was dataset dependent. Our results provide a grounded benchmark for cybersecurity practitioners evaluating NISQ-ready QML pipelines.
Quantum machine learning sits at the intersection of quantum computing and artificial intelligence, seeking to exploitquantum mechanical phenomena -- superposition, entanglement, and interference -- to achieve computationaladvantages for learning tasks. This study presents a systematic evaluation of five quantum ML approaches -- variationalquantum classifiers (VQC), quantum kernel methods, quantum reservoir computing, quantum Boltzmann machines, andhybrid quantum-classical neural networks -- benchmarked against classical counterparts on both simulated quantumhardware (up to 30 qubits) and real NISQ devices (IBM Quantum, 27 qubits). Evaluations spanned four task categories:binary classification on structured datasets (6 UCI benchmarks), quantum chemistry property prediction (QM9 molecularenergies), generative modelling (learning probability distributions), and optimisation (Max-Cut on random graphs). A totalof 1,920 experiments were conducted. On classical structured datasets, no quantum method outperformed the bestclassical baseline (XGBoost or SVM) at any problem size accessible to current quantum hardware (up to 30 features),with quantum kernel methods achieving parity at 0.4 +- 0.8% accuracy difference but at 100-1000x higher computationalcost. On quantum chemistry, variational quantum eigensolvers showed a genuine advantage for small molecules (H2,LiH, BeH2): achieving chemical accuracy (1 kcal/mol) with 4-12 qubits where classical methods required exponentiallymore compute for equivalent accuracy. Noise on real NISQ devices degraded all quantum ML methods by 8.4-22.6%relative to noiseless simulation, with error mitigation recovering 42-68% of the noise-induced loss. The quantumadvantage threshold -- the problem size at which quantum methods become faster than classical for equivalent accuracy-- was estimated at 50-100 logical qubits for quantum chemistry and 200+ logical qubits for general ML tasks, placingpractical quantum ML advantage beyond current NISQ capabilities but within plausible reach of fault-tolerant devices. Apractical assessment framework mapping task type, problem structure, and available quantum hardware to expectedquantum advantage is proposed.