CoChat

Variational Quantum Classifier for Binary Classification: Real vs Synthetic Dataset

Open access
Maheshwari, Danyal, Sierra-Sosa, Daniel, Garcia-Zapirain, Begonya · 2022 · IEEE Access

The DOI matches its Crossref record; 47 of the 47 references it cites were found in a registry or an index; 6 of the 18 sources its claims cite were checked for support.

Abstract

Nowadays, quantum-enhanced methods have been widely studied to solve machine learning related problems. This article presents the application of a Variational Quantum Classifier (VQC) for binary classification. We utilized three datasets: a synthetic dataset with randomly generated values between 0 and 1, the publicly available University of California Intelligence Machine learning (UCI) sonar dataset consisting of mining data, and a proprietary diabetes dataset related to diabetes with acute diseases and diabetes without acute disease. To deal with the limitation of noisy intermediate-scale quantum systems (NISQ), we used a pre-processing method to enhance the prediction rate when applying the VQC method. The process includes feature selection and state preparation. Quantum state preparation is critical for obtaining a functioning pipeline in a quantum machine learning (QML) model. Amplitude encoding is a state preparation approach that enhances the performance of data encoding and the learning of quantum models. As a result, our proposed methods achieved accuracies of 75%, 71.4%, and 68.73% by using VQC model and in contrast, the amplitude encoding-based VQC achieved 98.40%, 67.3%, and 74.50% accuracies on the synthetic, sonar, and diabetes dataset, respectively.

Overview

CoChat Summary

TL;DR

The paper evaluates variational quantum classifier (VQC) binary classification on three datasets—synthetic, UCI Sonar, and a proprietary diabetes dataset—and compares basis encoding with amplitude encoding. Amplitude encoding improved performance on the synthetic and diabetes datasets, but not on Sonar.

Key findings

  • The paper reports VQC accuracies of 75% on the synthetic dataset, 71.4% on Sonar, and 68.73% on diabetes.
  • With amplitude encoding-based VQC, the reported accuracies were 98.40% on the synthetic dataset, 67.3% on Sonar, and 74.50% on diabetes.
  • On the synthetic dataset, classical SVM achieved 100% accuracy, compared with 94% for QSVM and 75% for VQC; the amplitude-encoding VQC reached 98.40%.
  • On Sonar, classical SVM achieved 85.71% accuracy, versus 76.19% for QSVM and 71.4% for VQC; on diabetes, SVM achieved 75.32% versus 74.19% for QSVM and 68.73% for VQC.

Methods

  • The study uses three datasets: a synthetic dataset with 500 samples and 25 attributes (balanced 250/250), the UCI Sonar dataset with 208 samples and 60 attributes (111 metal cylinder, 97 rock), and a proprietary diabetes dataset derived from Osakidetza EHRs and the PREST database.
  • A preprocessing pipeline is applied: recursive feature elimination / feature selection, then min-max normalization to the 0–1 range, then quantum state preparation using basis encoding or amplitude encoding.
  • The main model is a Variational Quantum Classifier (VQC) implemented in IBM Qiskit, using feature maps such as FirstOrderExpansion, SecondOrderExpansion, and SecondOrderPauliExpansion, with COBYLA optimization; the data split is 80% training / 20% testing.

Limitations

  • The paper itself notes that NISQ device limitations constrain QML techniques and motivate preprocessing; this is stated explicitly in the Methods section.
  • The paper says the amplitude encoding VQC improved synthetic and diabetes results but had little influence on Sonar performance.
  • Evident from the text: the diabetes dataset is proprietary, and the paper does not provide full raw dataset details beyond aggregated counts and variable descriptions, which limits reproducibility.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1109/access.2021.3139323

Cites

47 of 47 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Figures

FIGURE 1 Feature Selection Flow diagram.
FIGURE 1 Feature Selection Flow diagram.CC-BY · From the PDF
FIGURE 2 Amplitude Encoding VQC Circuit.
FIGURE 2 Amplitude Encoding VQC Circuit.CC-BY · From the PDF
FIGURE 3 Support Vector Machine.
FIGURE 3 Support Vector Machine.CC-BY · From the PDF
FIGURE 4 Variational Quantum Classifier.
FIGURE 4 Variational Quantum Classifier.CC-BY · From the PDF
FIGURE 5 A typical VQC full circuit with feature map and variational form.
FIGURE 5 A typical VQC full circuit with feature map and variational form.CC-BY · From the PDF
FIGURE 6 An encoding circuit with CNOT, RY and RZ gates.
FIGURE 6 An encoding circuit with CNOT, RY and RZ gates.CC-BY · From the PDF
FIGURE 7 The accuracy of the proposed model against the selected number of epochs.
FIGURE 7 The accuracy of the proposed model against the selected number of epochs.CC-BY · From the PDF
Image 8
CC-BY · From the PDF
Image 9
CC-BY · From the PDF
Image 10
CC-BY · From the PDF

Verification

Claims the paper makes

5 Valid · 0 Not valid · 10 Not checked · 35 Own results and interpretations

24 more claims

Create a free account to see all 50 claims and to verify the 10 references still open.

See all claims — free account
  • Probably not a substantial claim. 15
  • The quote only partly states this claim. 1
  • It may state two separate claims as one. 9

Create a free account to see these claims.

Citations

Cites

Research works printed but not linked: 3

  1. 2021, QPU Topology—Ocean Documentation 3.1.1 Documentation
  2. International Diabetes Federation—Facts & Figures
  3. Abraham, 2021, Qiskit 0.34.0 Documentation

Cited by

See all 108

Metadata

Authors
Maheshwari, D., Sierra-Sosa, D., & Garcia-Zapirain, B.
Affiliations
  • Universidad de Deusto (ES)
  • Hood College (US)
Venue
IEEE Access
Published
2022
Volume
10
Pages
3705-3715
ISSN
2169-3536 (ISSN-L)
OpenAlex
W4206799920
Cited by
108
References
47
Citations by year
2026: 18 · 2025: 38 · 2024: 28 · 2023: 16 · 2022: 8
FWCI
4.60
Type
journal article
Language
en
Open access
Locations
  • IEEE Access (publishedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
eVIDA Research Group, University of Deusto, Bilbao, Spain, through the Basque Government’s (IT 905-16)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Quantum Computing Algorithms and Architecture
  • Physical Sciences › Physics and Astronomy › Atomic and Molecular Physics, and Optics › Quantum Information and Cryptography
  • Physical Sciences › Physics and Astronomy › Atomic and Molecular Physics, and Optics › Quantum many-body systems
Keywords
variational quantum classifier, binary classification, quantum machine learning, amplitude encoding, quantum state preparation, feature selection, diabetes dataset, synthetic data

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

The claim verdicts this report counts are experimental: their accuracy is not yet measured.

A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.