Yazar "Altuntas, Yahya" seçeneğine göre listele

Listeleniyor 1 - 5 / 5
  • Küçük Resim Yok
    Öğe
    Classification of Haploid and Diploid Maize Seeds by Using Image Processing Techniques and Support Vector Machines
    (Ieee, 2018) Altuntas, Yahya; Kocamaz, Adnan Fatih; Cengiz, Rahime; Esmeray, Mesut
    In vivo maternal haploid technique is now widely used in advanced maize breeding programs. This technique shortens the breeding period and increases the efficiency of breeding. One of the important processes in this breeding technique is the selection of haploid seeds. The fact that this selection is performed manually reduces the selection success and causes time and labor loss. For this reason, it is a need to develop automatic selection methods that will save time and labor and increase selection success. In this study, a method was proposed to classify haploid and diploid maize seeds by using image processing techniques and support vector machines. Firstly, each maize seed is segmented from its original image. Secondly, five different features were extracted for each maize seed. Finally, obtained features vector is classified by using support vector machines. The proposed method performance was tested by 10-fold cross-validation method. As a result of the test, the success rate of haploid maize seed classification was calculated as 94.25% and the success rate of diploid maize seed classification was 77.91%.
  • Küçük Resim Yok
    Öğe
    Determination of Individual Investors' Financial Risk Tolerance by Machine Learning Methods
    (Ieee, 2020) Altuntas, Yahya; Kocamaz, Adnan Fatih; Ulkgun, Abdullah Mert
    Financial risk tolerance refers to the amount of risk that an investor is willing to take in order to obtain returns. In this study, it was aimed to heuristically determine the individual investor financial risk tolerance by using demographic and socioeconomic variables. For this purpose, a questionnaire consisting of two parts was applied to blond University Computer Engineering Department students and administrative and academic staff. In the first part of the questionnaire, demographic and socioeconomic information of the participants were taken, and in the second part, 13 questions aiming to measure the financial risk tolerance were asked. The participants were labeled as risk-averse, risk-neutral and risk-loving according to their answers. The obtained data were classified by decision tree, k-nearest neighbor and support vector machine methods. 10-fold cross-validation method was used to determine model performances. According to the results of the experiment, the best classification performance was obtained with a overall accuracy value of 66.67% using the decision tree classifier.
  • Küçük Resim Yok
    Öğe
    Identification of Apricot Varieties Using Leaf Characteristics and KNN Classifier
    (Ieee, 2019) Altuntas, Yahya; Kocamaz, Adnan Fatih; Yeroglu, Celaleddin
    Apricot variety identification is an important issue for both plant breeders, seedling producers and conservation of biodiversity. Leaf, which contains important information about the plant to which it belongs, is used for species identification and plant disease diagnosis as well as for variety identification. In this study, the possibilities of identification of apricot varieties were investigated by using leaf characteristics. Within the scope of the study, a dataset consisting of 339 leaf images belonging to 10 apricot varieties was created. The proposed method consists of 3 main steps. In the segmentation step, the leaves were segmented from the background. 12 digital morphological features were obtained by using apricot leaf characteristics in the feature extraction step. In the classification step, the obtained feature vector was classified using the k-nearest neighbor classifier. 10-fold cross-validation method was used to determine classifier performance. The overall accuracy of the proposed method was measured as 79.05%.
  • Küçük Resim Yok
    Öğe
    Identification of haploid and diploid maize seeds using convolutional neural networks and a transfer learning approach
    (Elsevier Sci Ltd, 2019) Altuntas, Yahya; Comert, Zafer; Kocamaz, Adnan Fatih
    Maize is one of the most significant grains cultivated all over the world. Doubled-haploid is an important technique in terms of advanced maize breeding, modern crop improvement and genetic programs, since this technique shortens the breeding period and increases breeding efficiency. However, the selection of the haploid seeds is a major problem of this breeding technique. This process is frequently conducted manually, and this unreliable situation leads to loss of time and labor. Inspired by the recent successes of deep transfer learning, in this study, we approached this problem as a computer vision task to provide a nondestructive, rapid and low-cost model. To achieve this objective, we adopted convolutional neural networks (CNNs) to recognize haploid and diploid maize seeds automatically through a transfer learning approach. More specifically, AlexNet, VVGNet, GoogLeNet, and ResNet were applied for this specific task. The experimental study was carried out using a new dataset consisting of 1230 haploid and 1770 diploid maize seed images. The samples in the dataset were classified considering a marker-assisted selection, known as the R1-nj anthocyanin marker. To measure the success of the CNN models, we utilized several performance metrics, such as accuracy, sensitivity, specificity, quality index, and F-score derived from the confusion matrix and receiver operating characteristic curves. According to the experimental results, the CNN models ensured promising results, and we achieved the most efficient results via VGG-19. The accuracy, sensitivity, specificity, quality index, and F-score of VGG-19 were 94.22%, 94.58%, 93.97%, 94.27%, and 93.07%, respectively. Consequently, the experimental results proved that CNN models can be a useful tool in recognizing haploid maize seeds. Furthermore, we conclude that this approach is significantly superior to machine learning-based methods and conventional manual selection.
  • Küçük Resim Yok
    Öğe
    Identification of Haploid Maize Seeds using Gray Level Co-occurrence Matrix and Machine Learning Techniques
    (Ieee, 2018) Altuntas, Yahya; Kocamaz, Adnan Fatih; Comert, Zafer; Cengiz, Rahime; Esmeray, Mesut
    Doubled haploid (DH) technique is used effectively in maize breeding. This technique is superior to conventional maize breeding in terms of both time and homozygosity. One of the important processes in DH technique is the selection of haploid seeds. The most common method for selecting haploids is the RI-nj (Navajo) color marker. This color marker appears in the seed endosperm and embryo. Only endosperm color seeds are selected and continued to the germination stage This selection is usually done manually. The automation of haploid seed selection will increase success and reduce the labor and time In this study, we used 87 haploid and 326 diploid maize seeds as dataset. Texture features of maize seeds embryos were used These features were obtained from gray level co-occurrence matrix. The feature vectors are classified using decision trees, k-nearest neighbors and artificial neural networks. The classification performance of machine learning tecniques was tested by using 10 fold cross-validation method As a result of the test, the best performance was measured in decision tree with the classification success rate as 84.48%.