Yazar "Unal, Zeynep" seçeneğine göre listele

Listeleniyor 1 - 6 / 6
  • Küçük Resim Yok
    Öğe
    Classification of hazelnut kernels with deep learning
    (Elsevier, 2023) Unal, Zeynep; Aktas, Hakan
    In this study a deep learning-based, highly accurate network structure was applied to discriminate the whole kernel of hazelnut from other classes such as damaged kernel, shell, and undersized, which are present in small quantities after mechanized sorting and later subject to manual sorting. An industrial setup was developed to generate datasets for these four classes, and 2094 images of each class were recorded. With the obtained datasets, EfficientNetB0- EfficientNetB1- EfficientNetB2-EfficientNetB3 and InceptionV3 network structures were first trained from scratch and the highest test accuracy was calculated as 97.85 % for the InceptionV3 network structure. To further increase in the test accuracy, the transfer learning structure was used by applying the Imagenet coefficients. As a result of the training using Imagenet weights, the highest test accuracy was calculated as 99.28 % for the EfficientNetB2 and EfficientNetB3 structures. Although both networks give the same result in the classification of four hazelnut classes, the success in discrimination of the whole kernel of hazelnut from other classes is a key solution to decrease economic loss due to incorrect classification. From this point of view, according to confusion matrixes, it was concluded that the EfficientNetB3 structure is four times more efficient than the EfficientNetB2 structure.
  • Küçük Resim Yok
    Öğe
    Classification of pistachios with deep learning and assessing the effect of various datasets on accuracy
    (Springer, 2022) Aktas, Hakan; Kizildeniz, Tefide; Unal, Zeynep
    Pistachio is a healthy and delicious snack with high economic value, especially when product consists of only open pistachios. For this reason, many studies have been carried out in the literature to classify Pistachio according to whether they are open or closed. In this study, the classification process of pistachios was carried out according to whether they are open or closed using deep learning techniques. The prominent aspect of the study is that the datasets obtained with an industrial experimental set-up are used in the training of the network in order to be suitable for industrial applications and to classify it with high accuracy. In this study, AlexNet and Inception V3 structure were trained and tested with this industrial data set, the test accuracy was calculated as 96.13% and 96.54%, respectively. In order to compare the industrial data set and the desktop data set, both data sets were created. As a result of training and testing the AlexNet structure with this desktop data set, the test accuracy was calculated as 100%. When the test images from industrial dataset are fed to the network structure trained with the desktop dataset, the test accuracy was obtained as 61.75%. On the contrary, when desktop data set is fed to Alexnet structure trained with industrial data set, test accuracy is calculated as 99.84%. This clearly demonstrates how accurately the industrial dataset performs in industrial classification applications, while the desktop dataset has poor accuracy in industrial applications.
  • Küçük Resim Yok
    Öğe
    Detection of bruises on red apples using deep learning models
    (Elsevier, 2024) Unal, Zeynep; Kizildeniz, Tefide; Ozden, Mustafa; Aktas, Hakan; Karagoz, Omer
    The detection and sorting of bruised apples after harvest play a crucial role in improving their economic value by eliminating surface defects. This also reduces the risk of contamination of infected apples during transport and storage. It can be done by using manual detection or machine vision techniques in red, green, and blue (RGB) colors to detect bruises on apples of various skin colors; however, in the early stages of bruising, it is challenging. Therefore, the main purpose of this study is determin of the effectiveness of Deep Learning models combined with the Near Infrared (NIR) imaging system for naturally bruised Super Chief red apples immediately after harvest. In total, 1000 images for the healthy class and 500 images for the bruised class were acquired from 500 apples. After the images were acquired with the RGB and NIR cameras, the data sets were divided into training (70 %), validation (15 %), and testing (15 %) sets. The Alexnet, the Inceptipon-V3, and the VGG16 network structures were trained using the training and validation data sets, and the trained network was evaluated using the test dataset. The VGG16 model achieved the highest test accuracy (86 %) when trained on the RGB data set, while the AlexNet model exhibited the lowest test accuracy (74.6 %). When the models were trained and tested with NIR datasets, 99.33 %, 100 % and 100 % accuracy rates were obtained for AlexNet, Inception V3, and VGG16, respectively. During the experiments, the VGG16 model trained with the NIR dataset achieved the lowest loss rate of 0.0002, whereas when trained and tested with the RGB dataset, the same VGG16 model also recorded the lowest loss rate of 0.353.These findings indicate that the deep learning models, particularly when trained with NIR data, demonstrate high accuracy rates in classifying apples as healthy or bruised, making them suitable for industrial classification applications. Therefore, the NIR data set is recommended for precise and reliable apple classification in industrial settings.
  • Küçük Resim Yok
    Öğe
    Exploring Transfer Learning for Enhanced Seed Classification: Pre-trained Xception Model
    (Springer International Publishing Ag, 2024) Gulzar, Yonis; Unal, Zeynep; Ayoub, Shahnawaz; Reegu, Faheem Ahmad
    Seed classification plays a crucial role in various agricultural and industrial applications, such as crop breeding, seed quality assessment, and plant disease identification. This study presents a novel deep-learning model for seed classification. In this study, a dataset of 15 seeds has been created, containing around 3018 RGB images, with the objective of developing an accurate and efficient deep learning-based model capable of classifying seeds with high precision. In this study, we explore the effectiveness of two distinct approaches for seed classification: training the Xception model from scratch and leveraging transfer learning with the Pre-trained Xception model. The experimental results offer a comprehensive comparative analysis of training, validation, and testing outcomes. Notably, the Pre-trained Xception model showcases superior performance across various metrics. It achieves remarkable accuracy, attaining a perfect 1.0000 on both validation and test sets. Additionally, this model demonstrates significantly lower loss values throughout the training phases, highlighting its enhanced predictive capabilities. Impressively, convergence is reached with fewer epochs and in shorter training duration, further underlining the efficiency and effectiveness of the Pre-trained Xception model.
  • Küçük Resim Yok
    Öğe
    Harnessing the Power of Transfer Learning in Sunflower Disease Detection: A Comparative Study
    (Mdpi, 2023) Gulzar, Yonis; Unal, Zeynep; Aktas, Hakan; Mir, Mohammad Shuaib
    Sunflower is an important crop that is susceptible to various diseases, which can significantly impact crop yield and quality. Early and accurate detection of these diseases is crucial for implementing appropriate management strategies. In recent years, deep learning techniques have shown promising results in the field of disease classification using image data. This study presents a comparative analysis of different deep-learning models for the classification of sunflower diseases. five widely used deep learning models, namely AlexNet, VGG16, InceptionV3, MobileNetV3, and EfficientNet were trained and evaluated using a dataset of sunflower disease images. The performance of each model was measured in terms of precision, recall, F1-score, and accuracy. The experimental results demonstrated that all the deep learning models achieved high precision, recall, F1-score, and accuracy values for sunflower disease classification. Among the models, EfficientNetB3 exhibited the highest precision, recall, F1-score, and accuracy of 0.979. whereas the other models, ALexNet, VGG16, InceptionV3 and MobileNetV3 achieved 0.865, 0.965, 0.954 and 0.969 accuracy respectively. Based on the comparative analysis, it can be concluded that deep learning models are effective for the classification of sunflower diseases. The results highlight the potential of deep learning in early disease detection and classification, which can assist farmers and agronomists in implementing timely disease management strategies. Furthermore, the findings suggest that models like MobileNetV3 and EfficientNetB3 could be preferred choices due to their high performance and relatively fewer training epochs.
  • Küçük Resim Yok
    Öğe
    Predicting High Technology Exports of Countries for Sustainable Economic Growth by Using Machine Learning Techniques: The Case of Turkey
    (Mdpi, 2024) Gulzar, Yonis; Oral, Ceren; Kayakus, Mehmet; Erdogan, Dilsad; Unal, Zeynep; Eksili, Nisa; Caylak, Pinar Celik
    In this study, the estimation of high-tech exports for Turkey's foreign trade target in line with sustainable development was carried out. The research was carried out for Turkey since it has been focusing on sustainable and environmentally friendly production and an export-oriented growth model, with a transformation in its economic growth strategy as of 2021, and high-tech products are a determining factor in the export target. In this research, three different machine learning techniques, namely artificial neural networks, logistic regression, and support vector regression, were used to determine a successful prediction method close to the ideal scenario. In the models, high technology exports for the period of 2007-2023 with data obtained from the World Bank were taken as the dependent variable, while the gross national product, number of patents, and research and development expenditures were taken as independent variables. By calculating the R2, MAPE, and MSE metrics, the success of the model with the least error was evaluated, and it was seen that artificial neural networks (ANNs) were the most successful model, with values of 94.2%, 0.011, and 0.073, respectively. The ANN model was followed by support regression and logistic regression.