Compare the classification performances of convolutional neural networks and capsule networks on the Coswara dataset

dc.authorid0000-0002-0673-1408en_US
dc.authorid0000-0002-9913-5946en_US
dc.authorid0000-0002-0060-1880en_US
dc.contributor.authorMuhammad, Abdulaziz
dc.contributor.authorArserim, Muhammet Ali
dc.contributor.authorTürk, Ömer
dc.date.accessioned2023-07-04T06:12:42Z
dc.date.available2023-07-04T06:12:42Z
dc.date.issued2023en_US
dc.departmentDicle Üniversitesi, Mühendislik Fakültesi, Elektrik Elektronik Mühendisliği Bölümüen_US
dc.description.abstractSince the beginning of the COVID-19 pandemic, researchers have developed numerous machine learning models to distinguish between positive and negative COVID-19 sounds. The aim of this study is to compare the classification performances of convolutional neural networks (CNN) and capsule networks (CapsNet) on the Coswara dataset, which includes 1404 healthy subjects and 522 COVID-19 positive subjects, each containing nine different types of sounds. The dataset was preprocessed by using oversampling and normalization techniques after feature extraction. k-fold cross-validation was used (where k=10) to train and evaluate the models. The CNN classifiers achieved a 94% ACC, while the CapsNet classifiers achieved an 90% ACC. Furthermore, when using leave-one-out cross-validation, the CNN classifier achieved an ACC of 99%. we also compared the performance of the CNN and CapsNet networks on the Coswara dataset without preprocessing. Without oversampling techniques, the CNN classifiers achieved an 93% ACC, compared to 54% for the CapsNet classifiers. When normalization techniques were not applied, the CNN classifiers achieved an 86% ACC, while the CapsNet classifiers achieved a 26% ACC.en_US
dc.identifier.citationMuhammad, A., Arserim, M. A. ve Türk, Ö. (2023). Compare the classification performances of convolutional neural networks and capsule networks on the Coswara dataset. Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi, 14(2), 265-271en_US
dc.identifier.doi10.24012/dumf.1270429
dc.identifier.endpage271en_US
dc.identifier.issn1309-8640
dc.identifier.issn2146-4391
dc.identifier.issue2en_US
dc.identifier.startpage265en_US
dc.identifier.urihttps://dergipark.org.tr/tr/download/article-file/3033184
dc.identifier.urihttps://hdl.handle.net/11468/12157
dc.identifier.volume14en_US
dc.institutionauthorMuhammad, Abdulaziz
dc.institutionauthorArserim, Muhammet Ali
dc.language.isoenen_US
dc.publisherDicle Üniversitesi Mühendislik Fakültesien_US
dc.relation.ispartofDicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectCOVID-19en_US
dc.subjectCNNen_US
dc.subjectCapsNeten_US
dc.subjectK-folden_US
dc.subjectLeave-one-outen_US
dc.titleCompare the classification performances of convolutional neural networks and capsule networks on the Coswara dataseten_US
dc.titleCompare the classification performances of convolutional neural networks and capsule networks on the Coswara dataset
dc.typeArticleen_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Yükleniyor...
Küçük Resim
İsim:
Compare the classification performances of convolutional neural networks and.pdf
Boyut:
568.59 KB
Biçim:
Adobe Portable Document Format
Açıklama:
Makale dosyası
Lisans paketi
Listeleniyor 1 - 1 / 1
[ X ]
İsim:
license.txt
Boyut:
1.44 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama: