Scopus
YÖKSİS Eşleşti
Classification of bread wheat genotypes by machine learning algorithms
Journal of Food Composition and Analysis · Haziran 2023
YÖKSİS Kayıtları
Classification of bread wheat genotypes by machine learning algorithms
Journal of Food Composition and Analysis · 2023 SCI-Expanded
DOÇENT ALİ YAŞAR →
Classification of bread wheat genotypes by machine learning algorithms
Elsevier BV · 2023 SCI-Expanded
DOÇENT ALİ YAŞAR →
Classification of bread wheat genotypes by machine learning algorithms
Elsevier BV · 2023 SCI
DOÇENT ADEM GÖLCÜK →
Makale Bilgileri
DergiJournal of Food Composition and Analysis
Yayın TarihiHaziran 2023
Cilt / Sayfa119
Scopus ID2-s2.0-85149226142
Özet
Bread wheat, one of the staple food products, is a grain that forms the main ingredient of flour used in bakery products, especially in bread. Wheat has a large market in the world. The correct classification of bread wheat seeds is of great importance in order for the farmers to obtain an efficient harvest from bread wheat and to earn high income. In this study, a data set was created by taking 8354 images from certified 'Ayten Abla', 'Bayraktar 2000', 'Hamitbey', 'Şanlı' and 'Tosunbey' bread wheat varieties. Classification of wheat genotypes was carried out in 4 stages using images of bread wheat genotypes. In the first stage, 90 colors (C), 4 shapes (S) and 12 morphological (M) features were extracted from the images in this data set by image processing and feature selection method. The features obtained in the second stage were combined in different combinations. In the third stage, in the selection of the features that were effective in classification performance, feature selection was made from all the features combined with the Artificial Bee Colony (ABC) algorithm. Finally, bread wheat genotypes were classified by using these features, determined in three stages, as Support Vector Machines (SVM), Decision Tree (DT) and Quadratic Discriminant (QD) classifier which were machine learning algorithms. To make the classification process more accurate and objective, 10 fold cross validation was performed. The most successful classification process was obtained with SVM. The success rates obtained using 46, 94, 106, 102 and 90 features with SVM were 96.28 %, 95.81 %, 95.77 %, 95.66 % and 95.34 %, respectively.
Yazarlar (2)
1
Adem Golcuk
ORCID: 0000-0002-6734-5906
2
Ali Yasar
Anahtar Kelimeler
Artificial bee colony
Bread wheat
Classification
Machine learning
Kurumlar
Selçuk Üniversitesi
Selçuklu Turkey
Metrikler
11
Atıf
2
Yazar
4
Anahtar Kelime