Yazar "Bal, Fatih" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim
    Öğe
    Derin öğrenme yöntemi kullanarak tarımda verimliliği arttıran yeni bir hibrit model
    (Düzce Üniversitesi, 2023) Bal, Fatih; Kayaalp, Fatih
    Günümüzde tarım ürünlerinin üretimi ve bu üretimin devamlılığının sağlanması çok kritik bir öneme sahiptir. Bununla birlikte üretim aşamasındaki ürünlerin verimliliği çok önemlidir. Ürün veriminin yüksek olması çiftçinin ürün ve mali kaybını azaltacağı gibi tüketiciye de kaliteli ürün sağlayacaktır. Son yıllarda gelişen teknoloji ile birlikte tarım ürünlerinin verimliliğinin belirlenmesinde makine öğrenmesi ve derin öğrenme modelleriyle çalışmalar yapılmaktadır. Bu tez çalışmasında tarım ürünlerinin kalitesine göre verimliliğinin sınıflandırılması amacıyla derin öğrenme tabanlı yeni bir hibrit model tasarlanmıştır. Tasarlanan hibrit modelde bir derin öğrenme modeli olan CNN ile öznitelikleri çıkartılan görüntüler makine öğrenmesi modelleri ile sınıflandırılmıştır. Böylece en iyi hibrit model belirlenmiştir. Çalışma için Elma Veri Kümesi ve FruitsGB Veri Kümesi olmak üzere iki farklı veri kümesi kullanılmıştır. Elma Veri Kümesi dört farklı veri kümesi senaryosuna (Dataset_A, Dataset_B, Dataset_C, Dataset_D) ve aynı şekilde FruitsGB veri kümesi dört farklı veri kümesi senaryosuna (Meyve_A, Meyve_B, Meyve_C, Meyve_D) ayrılmıştır. Tüm modeller için doğruluk, hassasiyet, özgüllük, kesinlik, F1 skoru, dengeli doğruluk, Kappa skoru incelenmiş ve ROC analizleri yapılmıştır. Elma Veri Kümesi için en iyi sonucu veren hibrit model, %99,80 doğruluk oranı CNN-SVM (lineer) modeli ile Dataset_C veri kümesi senaryosunda elde edilmiştir. FruitsGB Veri Kümesi için en iyi sonucu veren hibrit model, %99,30 doğruluk oranı CNN-SVM (rbf) modeli ile Meyve_C veri kümesi senaryosunda elde edilmiştir. Çalışmanın sonuçlarına bakıldığında hibrit modelin etkili sonuçlar ortaya koyduğu gözlemlenmiştir.
  • Küçük Resim
    Öğe
    A Novel Deep Learning-Based Hybrid Method for the Determination of Productivity of Agricultural Products: Apple Case Study
    (Ieee-Inst Electrical Electronics Engineers Inc, 2023) Bal, Fatih; Kayaalp, Fatih
    The production of agricultural products and the high yield in these products are of critical importance for the continuation of human life. In recent years, machine learning and deep learning technologies have been widely used in determining agricultural productivity. The purpose of this study was to estimate the yield of apple fruit by using a novel deep learning-based hybrid method. First, by using images belonging to the golden and royal gala apple varieties, a classification was made with the help of a convolutional neural network (CNN) that was designed for the study. Then, using classical machine learning algorithms and bagging and boosting algorithms, a hybrid application was performed by classifying the images whose feature extractions were done with the designed CNN. The results of the study, presented on 4 separate datasets (Datasets A, B, C, and D), were evaluated based on accuracy, precision, recall, F-measure, and Cohen kappa scores. Considering the accuracy results for Datasets B, C, and D, it was determined that the hybrid model that gave the best result was the CNN-SVM model. For Dataset A, the CNN-SVM and CNN-Gradient Boosting hybrid models gave the best and same accuracy. Dataset C was determined as the most appropriate dataset in terms of the more balanced distribution of train, test, and validation size in the datasets, the results of the proposed hybrid CNN model, and the evaluation of the results of the model. For Dataset C, it was found that the accuracy of the hybrid model was 99.70%. Precision, recall, f-measure, and Cohen kappa scores were 99%. The results of the study revealed that the hybrid models showed effective results in determining the productivity of apple fruit through images belonging to the golden and royal gala varieties.
  • Küçük Resim
    Öğe
    Review of machine learning and deep learning models in agriculture
    (2021) Bal, Fatih; Kayaalp, Fatih
    Machine learning (ML) refers to the processes that enable computers to think based on variouslearning methods. It can be also called domain which is a subset of Artificial Intelligence (AI).Deep learning (DL) has been a promising, new and modern technique for data analysis in recentyears. It can be shown as the improved version of Artificial Neural Networks (ANN) which is oneof the popular AI methods of today. The population of the world is increasing day by day and theimportance of agriculture is also increasing in parallel. Because of this, many researchers havefocused on this issue and have tried to apply machine learning and deep learning methods inagriculture under the name of smart farm technologies both to increase agricultural production andto solve some challenges of agriculture. In this study, it is aimed to give detailed information aboutthese up-to-date studies. 77 articles based on machine learning and deep learning algorithms in theagriculture field and published in IEEE Xplore, ScienceDirect, Web of Science and Scopuspublication databases between 2016 and 2020 years were reviewed. The articles were classifiedunder five categories as plant recognition, disease detection, weed and pest detection, soilmapping-drought index, and yield forecast. They were examined in detail in terms of machinelearning/deep learning architectures, data sets, performance metrics (Accuracy, Precision, Recall,F-Score, R2, MAPE, RMSE, MAE), and the obtained experimental results. Based on the examinedarticles, the most popular methods, used data sets/types, chosen performance criteria, andperformance results among the existing studies are presented. It is seen that the number of AIbased applications related to agriculture is increasing compared to the past and the sustainabilityin productivity is so promising.