Yazar "Sabanci, Kadir" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim
    Öğe
    The classification of diseased trees by using kNN and MLP classification models according to the satellite imagery
    (2016) Unlersen, Muhammed Fahri; Sabanci, Kadir
    In this study, the Japanese Oak and Pine Wilt in forested areas of Japan was classified into two group as diseased trees and all other land cover area according to the 6 attributes in the spectral data set of the forest. The Wilt Data Set which was obtained from UCI machine learning repository database was used. Weka (Waikato Environment for Knowledge Analysis) software was used for classification of areas in the forests. The classification success rates and error values were calculated and presented for classification data mining algorithms just as Multilayer Perceptron (MLP) and k-Nearest Neighbor (kNN). In MLP neural networks the classification performance for various numbers of neurons in the hidden layer was presented. The highest success rate was obtained as 86.4% when the number of neurons in the hidden layer was 10. The classification performance of kNN method was calculated for various counts of neighborhood. The highest success rate was obtained as 72% when the count of neighborhood number was 2
  • Küçük Resim Yok
    Öğe
    IMAGE PROCESSING BASED INTELLIGENT SPRAYING ROBOT FOR WEED CONTROL
    (PARLAR SCIENTIFIC PUBLICATIONS (P S P), 2016) Sabanci, Kadir; Aydin, Cevat
    At weed control, physico-mechanical is the most commonly used method in chemical weeding in the world and in our country despite genetic, biological and biotechnical methods. Pesticide use in agriculture has increased in recent years. Because of the difficulty in finding farm workers and damage to sugar beets caused by farm workers due to their carelessness during hoeing, the use of chemicals has increased. However, because the pesticide used in chemical weeding affect human health, the environment and the natural balance negatively and because of increased production costs pesticides should be applied precisely, cautiously and with the minimum agricultural pesticide loss. In this study, image processing based intelligent spraying robot was developed. Variable levelled herbicide was applied on weed by using image processing techniques. The covering rate of the spraying liquid applied on the weeds was determined for 8 different speed values of robot when nozzle height of the spraying robot is 50 and 30 cm. A reduction of 40% led to a decrease of 9.42% for 4 weed averagely in the covering value of the spraying liquid to the weed.
  • Küçük Resim Yok
    Öğe
    Image Processing Based Precision Spraying Robot
    (ANKARA UNIV, FAC AGR, 2014) Sabanci, Kadir; Aydin, Cevat
    Hoeing as mechanically and the use of herbicide as chemically are the most effective methods in controlling weed in sugar beet farming. Excessive use of chemical tussle results in serious environmental problems in the world. In addition, it affects human and animal health adversely. The weeds between rows in sugar beet fields were determined by using image processing techniques and a model of variable level herbicide application was applied on them with precision spraying robot developed during the study. When the nozzle height of precision spraying robot is 30 cm and the speed of it is 8.928 cm s(-1), a value of 55.22% saving of drugs was achieved when compared to conventional pesticide applications in a pesticide application on an area of 1.6 m(2). The amount of spraying liquid applied on weeds by precision spraying robot with 8 different speeds was measured. It was found that increasing the speed of the spraying robot causes a decrease in the amount of spraying liquid applied on weeds.