Yazar "Unlersen, M. Fahri" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    CLASSIFICATION OF DIFFERENT FOREST TYPES W ITH MACHINE LEARNING ALGORITHMS
    (Latvia Univ Life Sciences & Technologies, 2016) Sabanci, Kadir; Unlersen, M. Fahri; Polat, Kemal
    In this study, forest type mapping data set taken from UCI (University of California, Irvine) machine learning repository database has been classified using different machine learning algorithms including Multilayer Perceptron, k-NN, J48, Naive Bayes, Bayes Net and KStar. In this dataset, there are 27 spectral values showing the type of three different forests (Sugi, Hinoki, mixed broadleaf). As the performance measure criteria, the classification accuracy has been used to evaluate the classifier algorithms and then to select the best method. The best classification rates have been obtained 90.43% with MLP, and 89.1013% with k-NN classifier (for k=5). As can be seen from the obtained results, the machine learning algorithms including MLP and k-NN classifier have obtained very promising results in the classification of forest type with 27 spectral features.
  • Küçük Resim Yok
    Öğe
    A CNN-SVM study based on selected deep features for grapevine leaves classification
    (Elsevier Sci Ltd, 2022) Koklu, Murat; Unlersen, M. Fahri; Ozkan, Ilker Ali; Aslan, M. Fatih; Sabanci, Kadir
    The main product of grapevines is grapes that are consumed fresh or processed. In addition, grapevine leaves are harvested once a year as a by-product. The species of grapevine leaves are important in terms of price and taste. In this study, deep learning-based classification is conducted by using images of grapevine leaves. For this purpose, images of 500 vine leaves belonging to 5 species were taken with a special self-illuminating system. Later, this number was increased to 2500 with data augmentation methods. The classification was conducted with a state-of-art CNN model fine-tuned MobileNetv2. As the second approach, features were extracted from pre-trained MobileNetv2 ' s Logits layer and classification was made using various SVM kernels. As the third approach, 1000 features extracted from MobileNetv2 ' s Logits layer were selected by the Chi-Squares method and reduced to 250. Then, classification was made with various SVM kernels using the selected features. The most successful method was obtained by extracting features from the Logits layer and reducing the feature with the Chi-Squares method. The most successful SVM kernel was Cubic. The classification success of the system has been determined as 97.60%. It was observed that feature selection increased the classification success although the number of features used in classification decreased.