Konvolüsyonel sinir ağlarını kullanarak bitki türlerinin sınıflandırılması ve bitki hastalıklarının tanısı
Yükleniyor...
Dosyalar
Tarih
2022
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Tekirdağ Namık Kemal Üniversitesi
Erişim Hakkı
info:eu-repo/semantics/openAccess
Özet
Görüntü sınıflandırma, başta tarım, sağlık, ulaşım olmak üzere birçok alana hizmet sunmakla birlikte, insan gücü ile tahmin edilmesi güç problemlerde kullanmış olduğu yapay zeka mimarileriyle birlikte çok kısa sürede ve çok daha az maliyet ile gerçekleştirmektedir. Tarım alanında ise, bitki türlerinin belirlenmesi, bitki hastalıklarının tahminleri gibi süreçler insan gücü ile laboratuvar ortamlarında çok uzun süreçlerde gerçekleştirmekte olup, alınacak tedavide geç kalınabilmektedir. Derin öğrenme algoritmalarından olan konvolüsyonel sinir ağı, bitkilerin sınıflandırmaları ve sahip oldukları hastalıkların teşhislerinde çok kısa sürelerde çok başarılı sonuçlar sunmaktadır. Bu çalışmada, popüler bir veri seti olan Plantvillage veri seti ele alınmıştır ve bu veri setinden, büyük ölçekli ve küçük ölçekli durumlarının yanı sıra, çok sınıflı ve az sınıflı olmak üzere toplamda 8 adet yeni veri seti oluşturulmuştur. Oluşturulan bu veri setleri kullanılarak, bitki türlerinin sınıflandırılması, bitki hastalık tahmini ve bitki hastalıklarının sınıflandırılması için modelleme çalışmaları gerçekleştirilmiştir ve her bir sınıflandırma problemi için, geniş kapsamlı deneysel çalışmalar sonucunda en iyi modeller bulunmaya çalışılmıştır. İlk modelleme çalışmalarında, bitki türlerinin sınıflandırılması problemine yönelik hazırlanmış olan 6 farklı dengeli veri seti kullanılarak, Alexnet mimarisi uygulanmıştır ve en iyi model, % 99,88 test doğruluk başarısı elde edilmiştir. İkinci modelleme çalışmalarında, bitki hastalık tahmini problemine yönelik hazırlanmış olan, 2 sınıftan oluşan dengeli veri seti kullanılarak, literatür sonuçlarında gözlemlenen CNN'in en popüler 9 farklı derin öğrenme modelleri uygulanmıştır. Bitki hastalık tahmini için en iyi model, GoogleNet/Inception mimarisinin kullanıldığı model olmuştur ve 3 kez çapraz doğrulama ile %99,91 doğruluk başarısı elde edilmiştir. Son olarak, bitki hastalıklarının sınıflandırılması problemine yönelik, kullanılan veri seti ile DenseNet modeli en iyi model olarak bulunmuştur ve 10 kez çapraz doğrulama ile %99,14 doğruluk başarısı elde edilmiştir.
Image classification provides services in many fields, especially agriculture, health, transportation, and it performes in a very short time and with much less cost, with the artificial intelligence architectures used in man-powered problems. In the field of agriculture, processes such as determination of plant species and estimates of plant diseases are carried out in human lab in a very long period of time, and the treatment to be taken can be delayed. Convolutional neural network, which is one of the deep learning algorithms, offers very successful results in very short periods in the classification of plants and in the diagnosis of their diseases. Within the scope of the study, a total of 8 data sets, including large-scale and small-scale cases, as well as multi-class and low-class, were created using the Plantvillage dataset, which is open to the public. Modelling studies were carried out in which it was used as a classifier in 3 phases: classification of plant species, prediction of plant diseases and diagnosis of plant diseases. In the first phase, Alexnet's comparisons were made on 6 different balanced datasets prepared for the classification of plant species and a better model was tried to be obtained with the changes in padding values. In the second phase, the balanced data set consisting of 2 classes prepared for the plant disease prediction problem was applied as a classifier in the most popular 9 different deep learning models of CNN observed in the literature, and the results were compared and 99 for the 3 cross-validations (CV-3) part. With 91 test accuracy, the GoogleNet/Inception model was chosen as the most optimal model. In the last phase, it has been observed that there is a DenseNet model with the dataset for the plant diseases diagnosis problem and a DenseNet model with a test accuracy of 99.14 for the 10 cross-validations (CV-10) parts. In this study, the literature of which was also carried out, comparisons of different CNN models and the performance of the models rearranged with transfer learning were evaluated.
Image classification provides services in many fields, especially agriculture, health, transportation, and it performes in a very short time and with much less cost, with the artificial intelligence architectures used in man-powered problems. In the field of agriculture, processes such as determination of plant species and estimates of plant diseases are carried out in human lab in a very long period of time, and the treatment to be taken can be delayed. Convolutional neural network, which is one of the deep learning algorithms, offers very successful results in very short periods in the classification of plants and in the diagnosis of their diseases. Within the scope of the study, a total of 8 data sets, including large-scale and small-scale cases, as well as multi-class and low-class, were created using the Plantvillage dataset, which is open to the public. Modelling studies were carried out in which it was used as a classifier in 3 phases: classification of plant species, prediction of plant diseases and diagnosis of plant diseases. In the first phase, Alexnet's comparisons were made on 6 different balanced datasets prepared for the classification of plant species and a better model was tried to be obtained with the changes in padding values. In the second phase, the balanced data set consisting of 2 classes prepared for the plant disease prediction problem was applied as a classifier in the most popular 9 different deep learning models of CNN observed in the literature, and the results were compared and 99 for the 3 cross-validations (CV-3) part. With 91 test accuracy, the GoogleNet/Inception model was chosen as the most optimal model. In the last phase, it has been observed that there is a DenseNet model with the dataset for the plant diseases diagnosis problem and a DenseNet model with a test accuracy of 99.14 for the 10 cross-validations (CV-10) parts. In this study, the literature of which was also carried out, comparisons of different CNN models and the performance of the models rearranged with transfer learning were evaluated.
Açıklama
Anahtar Kelimeler
Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontrol, Computer Engineering and Computer Science and Control
