The analysis and optimization of CNN Hyperparameters with fuzzy tree model for image classification
Yazarlar (3)
Doç. Dr. İlker Ali Özkan Selçuk Üniversitesi, Türkiye
Dr. Öğr. Üyesi Kübra Uyar Selçuk Üniversitesi, Türkiye
Prof. Dr. Şakir TAŞDEMİR Selçuk Üniversitesi, Türkiye
| Makale Türü |
Özgün Makale
(SSCI, AHCI, SCI, SCI-Exp dergilerinde yayınlanan tam makale)
|
||
| Dergi Adı | Turkish Journal of Electrical Engineering and Computer Sciences (Q4) | ||
| Dergi ISSN | 1300-0632 Dergi Bilgileri (2022) | ||
| Dergi Tarandığı Indeksler | SCI | ||
| Makale Dili | İngilizce | Basım Tarihi | 01-2022 |
| Cilt / Sayı / Sayfa | 30 / 3 / 961–977 | DOI | 10.55730/1300-0632.3821 |
| Makale Linki | https://journals.tubitak.gov.tr/elektrik/vol30/iss3/30/ | ||
| UAK Araştırma Alanları |
Yapay Zeka
Görüntü İşleme
Bulanık Mantık
|
||
| Özet |
| The meaningful performance of convolutional neural network (CNN) has enabled the solution of various state-of-the-art problems. Although CNNs achieve satisfactory results in computer-vision problems, they still have some difficulties. As the designed CNN models are deepened to achieve much better accuracy, computational cost and complexity increase. It is significant to train CNNs with suitable topology and training hyperparameters that include initial learning rate, minibatch size, epoch number, filter size, number of filters, etc. because the initialization of hyperparameters affects classification results. On the other hand, it is not possible to make a definite inference for the hyperparameter initialization and there is uncertainty. This study is carried out to model uncertainty using fuzzy inference system (FIS). The designed fuzzy model provides estimation of classification result depending on CNN topology and training hyperparameters. GoogleNet and Inceptionv3 that contain inception-modules, ShuffleNet that contains shuffleblocks, DenseNet201 that contains dense-blocks, EfficientNet, ResNet18, ResNet50, ResNet101, and MobileNetv2 that contain residual-blocks, and InceptionResNetv2 that includes both inception-modules and residual-blocks were evaluated as CNN models. Test sample dataset was obtained by training CNN models with various training hyperparameter combinations. CNN models were trained on Animal Diagnostics Lab (ADL) which is a histopathological dataset includes healthy and inflamed kidney, lung, and spleen images. A new FIS tree model that is more computationally efficient and easier to understand than a … |
| Anahtar Kelimeler |
| Classification | convolutional neural network | fuzzy logic | histopathological data | hyperparameter |
BM Sürdürülebilir Kalkınma Amaçları
| Atıf Sayıları | |
| Web of Science | 3 |
| Scopus | 6 |
| Google Scholar | 8 |