Sample images of FruitQ dataset.

<div><p>This study investigates hybrid quantum neural networks for fruit quality assessment, with a focus on the impact of the entangling gate choice. Two architectures were developed: NNQEv1, utilizing controlled-NOT (CNOT) gates, and NNQEv2, employing controlled-phase (CZ) gates. A the...

Popoln opis

Shranjeno v:
Bibliografske podrobnosti
Glavni avtor: Danish ul Khairi (19660534) (author)
Drugi avtorji: Kamran Ahsan (10413151) (author), Syed Zeeshan Ali (19660531) (author), Wadee Alhalabi (11951405) (author), Somayah Albaradei (9041843) (author), Muhammad Shahid Anwar (19660537) (author)
Izdano: 2025
Teme:
Oznake: Označite
Brez oznak, prvi označite!
_version_ 1851480305996660736
author Danish ul Khairi (19660534)
author2 Kamran Ahsan (10413151)
Syed Zeeshan Ali (19660531)
Wadee Alhalabi (11951405)
Somayah Albaradei (9041843)
Muhammad Shahid Anwar (19660537)
author2_role author
author
author
author
author
author_facet Danish ul Khairi (19660534)
Kamran Ahsan (10413151)
Syed Zeeshan Ali (19660531)
Wadee Alhalabi (11951405)
Somayah Albaradei (9041843)
Muhammad Shahid Anwar (19660537)
author_role author
dc.creator.none.fl_str_mv Danish ul Khairi (19660534)
Kamran Ahsan (10413151)
Syed Zeeshan Ali (19660531)
Wadee Alhalabi (11951405)
Somayah Albaradei (9041843)
Muhammad Shahid Anwar (19660537)
dc.date.none.fl_str_mv 2025-12-10T18:30:45Z
dc.identifier.none.fl_str_mv 10.1371/journal.pone.0332528.g005
dc.relation.none.fl_str_mv https://figshare.com/articles/figure/Sample_images_of_FruitQ_dataset_/30852093
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Biological Sciences not elsewhere classified
Mathematical Sciences not elsewhere classified
Information Systems not elsewhere classified
level design choices
fruit quality assessment
experimental results align
aware noise considerations
achieving test accuracies
scarce apple dataset
stable training dynamics
entangling gate choice
based nnqev2 model
fruitq dataset
xlink ">
work presents
utilizing controlled
two architectures
theoretical justification
theoretical analysis
quantum circuits
gate decomposition
employing controlled
consistently showed
computational study
computational execution
based architecture
dc.title.none.fl_str_mv Sample images of FruitQ dataset.
dc.type.none.fl_str_mv Image
Figure
info:eu-repo/semantics/publishedVersion
image
description <div><p>This study investigates hybrid quantum neural networks for fruit quality assessment, with a focus on the impact of the entangling gate choice. Two architectures were developed: NNQEv1, utilizing controlled-NOT (CNOT) gates, and NNQEv2, employing controlled-phase (CZ) gates. A theoretical justification is provided, based on gate decomposition and hardware-aware noise considerations, suggesting the CZ-based architecture is likely to be more stable. The performance of the models was evaluated through the computational execution of their quantum circuits on classical hardware and compared against classical and state-of-the-art deep learning models. The proposed models demonstrated competitive performance, achieving test accuracies of 98.7% on MNIST, 98.6% on the FruitQ dataset, and 96.7% on a custom, data-scarce Apple dataset. The experimental results align with the theoretical analysis: the CZ-based NNQEv2 model, when compared to the CNOT-based NNQEv1, consistently showed more stable training dynamics and yielded tighter confidence intervals in cross-validation. This work presents a foundational, computational study on the role of gate-level design choices, intended to inform the development of future quantum machine learning algorithms.</p></div>
eu_rights_str_mv openAccess
id Manara_ada60d0e6918a5429f0c24d09f3de636
identifier_str_mv 10.1371/journal.pone.0332528.g005
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/30852093
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Sample images of FruitQ dataset.Danish ul Khairi (19660534)Kamran Ahsan (10413151)Syed Zeeshan Ali (19660531)Wadee Alhalabi (11951405)Somayah Albaradei (9041843)Muhammad Shahid Anwar (19660537)Biological Sciences not elsewhere classifiedMathematical Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedlevel design choicesfruit quality assessmentexperimental results alignaware noise considerationsachieving test accuraciesscarce apple datasetstable training dynamicsentangling gate choicebased nnqev2 modelfruitq datasetxlink ">work presentsutilizing controlledtwo architecturestheoretical justificationtheoretical analysisquantum circuitsgate decompositionemploying controlledconsistently showedcomputational studycomputational executionbased architecture<div><p>This study investigates hybrid quantum neural networks for fruit quality assessment, with a focus on the impact of the entangling gate choice. Two architectures were developed: NNQEv1, utilizing controlled-NOT (CNOT) gates, and NNQEv2, employing controlled-phase (CZ) gates. A theoretical justification is provided, based on gate decomposition and hardware-aware noise considerations, suggesting the CZ-based architecture is likely to be more stable. The performance of the models was evaluated through the computational execution of their quantum circuits on classical hardware and compared against classical and state-of-the-art deep learning models. The proposed models demonstrated competitive performance, achieving test accuracies of 98.7% on MNIST, 98.6% on the FruitQ dataset, and 96.7% on a custom, data-scarce Apple dataset. The experimental results align with the theoretical analysis: the CZ-based NNQEv2 model, when compared to the CNOT-based NNQEv1, consistently showed more stable training dynamics and yielded tighter confidence intervals in cross-validation. This work presents a foundational, computational study on the role of gate-level design choices, intended to inform the development of future quantum machine learning algorithms.</p></div>2025-12-10T18:30:45ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0332528.g005https://figshare.com/articles/figure/Sample_images_of_FruitQ_dataset_/30852093CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/308520932025-12-10T18:30:45Z
spellingShingle Sample images of FruitQ dataset.
Danish ul Khairi (19660534)
Biological Sciences not elsewhere classified
Mathematical Sciences not elsewhere classified
Information Systems not elsewhere classified
level design choices
fruit quality assessment
experimental results align
aware noise considerations
achieving test accuracies
scarce apple dataset
stable training dynamics
entangling gate choice
based nnqev2 model
fruitq dataset
xlink ">
work presents
utilizing controlled
two architectures
theoretical justification
theoretical analysis
quantum circuits
gate decomposition
employing controlled
consistently showed
computational study
computational execution
based architecture
status_str publishedVersion
title Sample images of FruitQ dataset.
title_full Sample images of FruitQ dataset.
title_fullStr Sample images of FruitQ dataset.
title_full_unstemmed Sample images of FruitQ dataset.
title_short Sample images of FruitQ dataset.
title_sort Sample images of FruitQ dataset.
topic Biological Sciences not elsewhere classified
Mathematical Sciences not elsewhere classified
Information Systems not elsewhere classified
level design choices
fruit quality assessment
experimental results align
aware noise considerations
achieving test accuracies
scarce apple dataset
stable training dynamics
entangling gate choice
based nnqev2 model
fruitq dataset
xlink ">
work presents
utilizing controlled
two architectures
theoretical justification
theoretical analysis
quantum circuits
gate decomposition
employing controlled
consistently showed
computational study
computational execution
based architecture