FPGA implementation of deep learning model utilizing different normalization algorithms for COVID-19 diagnosis

Basit Öğe Kaydı
dc.contributor.authorZİREKGÜR, MERVE
dc.contributor.authorKarakaya, Barış
dc.date.accessioned2025-10-24T18:03:42Z
dc.date.available2025-10-24T18:03:42Z
dc.date.issued2024
dc.departmentMalatya Turgut Özal Üniversitesi
dc.description.abstractNormalization is utilized to remove outliers from the dataset and address network bias. In this research, Mean-Variance-Softmax-Rescale (MVSR) and Min-Max normalizations are employed in various combinations for the diagnosis of COVID-19 using a Convolutional Neural Network (CNN)-based Deep Learning (DL) model, aimed at enhancing network accuracy. To accomplish this, the CNN model is developed within the Google Colab environment and trained using a publicly available dataset consisting of chest X-ray images related to COVID-19. The dataset is normalized using different combinations of the MVSR and Min-Max normalization algorithms to compare model accuracy. Each normalized dataset is used for model training, and subsequently, each trained model has been saved as a .h5 file and loaded into the Kria KV260 Vision AI Starter Kit FPGA for the testing phase. The most accurate results are obtained when MVSR and Min-Max normalizations are applied simultaneously. This high-performing scenario is re-evaluated with COVID-19 and normal X-ray images on FPGA configuration. Experimentally, the highest accuracy is achieved in real-time with the MVSR+Min-Max scenario, reaching 93%. The model's precision, recall, and F1-Score values are determined as 0.91, 0.96, and 0.93, respectively.
dc.identifier.doi10.28948/ngumuh.1427827
dc.identifier.endpage916
dc.identifier.issn2564-6605
dc.identifier.issue3
dc.identifier.startpage905
dc.identifier.trdizinid1249735
dc.identifier.urihttps://doi.org/10.28948/ngumuh.1427827
dc.identifier.urihttps://search.trdizin.gov.tr/tr/yayin/detay/1249735
dc.identifier.urihttps://hdl.handle.net/20.500.12899/2399
dc.identifier.volume13
dc.indekslendigikaynakTR-Dizin
dc.language.isoen
dc.relation.ispartofNiğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi
dc.relation.publicationcategoryMakale - Ulusal Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzTR-Dizin_20251023
dc.subjectMikroskopi
dc.subjectTıbbi İnformatik
dc.subjectMühendislik
dc.subjectElektrik ve Elektronik
dc.subjectBilgisayar Bilimleri
dc.subjectYazılım Mühendisliği
dc.subjectNormalization
dc.subjectDeep Learning
dc.subjectArtificial Intelligence
dc.subjectImage Processing
dc.titleFPGA implementation of deep learning model utilizing different normalization algorithms for COVID-19 diagnosis
dc.typeArticle

Dosyalar

Koleksiyon

TR-Dizin İndeksli Yayınlar Koleksiyonu