A New Lightweight Hybrid Model for Pistachio Classification Using Transformers and EfficientNet

Basit Öğe Kaydı
dc.contributor.authorCakmak, Muhammet
dc.date.accessioned2026-04-25T14:20:14Z
dc.date.available2026-04-25T14:20:14Z
dc.date.issued2025
dc.departmentSinop Üniversitesi
dc.description.abstractIn recent years, Vision Transformers (ViTs) have gained prominence as a highly effective method for image classification, often outperforming traditional Convolutional Neural Networks (CNNs). However, their relatively slow processing speed limits their practical use, particularly in real-time applications. Conversely, CNN-based transfer learning models provide faster inference but may struggle with classification accuracy on complex datasets. To address these challenges, Temporal Coordinate Attention (TCA) modules have been introduced to optimize efficiency and performance. This study proposes a hybrid architecture combining EfficientNet, Vision Transformer, and Temporal Channel Attention modules that integrates the accuracy of ViTs, the computational efficiency of CNNs, and the enhancement capabilities of TCA modules. The model is designed to classify Siirt and Kirmizi pistachio varieties with high precision. It achieves outstanding results, including 99.07% accuracy, 99.12% recall, and a Cohen's Kappa score of 98.10%. These findings highlight the model's robustness, demonstrating its ability to perform reliable classifications with minimal bias, making it well-suited for real-world applications.
dc.identifier.doi10.1109/ACCESS.2025.3567774
dc.identifier.endpage85872
dc.identifier.issn2169-3536
dc.identifier.orcid0000-0002-3752-6642
dc.identifier.scopus2-s2.0-105004908278
dc.identifier.scopusqualityQ1
dc.identifier.startpage85857
dc.identifier.urihttps://doi.org/10.1109/ACCESS.2025.3567774
dc.identifier.urihttps://hdl.handle.net/11486/8441
dc.identifier.volume13
dc.identifier.wosWOS:001492129400023
dc.identifier.wosqualityQ2
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.institutionauthorCakmak, Muhammet
dc.language.isoen
dc.publisherIeee-Inst Electrical Electronics Engineers Inc
dc.relation.ispartofIeee Access
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzKA_WOS_20260420
dc.subjectAccuracy
dc.subjectComputational modeling
dc.subjectTransformers
dc.subjectConvolutional neural networks
dc.subjectRandom forests
dc.subjectComputer vision
dc.subjectArtificial intelligence
dc.subjectMachine learning
dc.subjectFeature extraction
dc.subjectImage classification
dc.subjectClassification
dc.subjectvision transformer
dc.subjectEfficientNet
dc.subjectTCA
dc.subjectmachine learning
dc.titleA New Lightweight Hybrid Model for Pistachio Classification Using Transformers and EfficientNet
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu