Browsing by Author "Inan, Mevlut"

Now showing 1 - 2 of 2

Applications and Comparisons of Optimization Algorithms Used in Convolutional Neural Networks
(Ieee, 2019) Seyyarer, Ebubekir; Uckan, Taner; Hark, Cengiz; Ayata, Faruk; Inan, Mevlut; Karci, Ali
Nowadays, it is clear that the old mathematical models are incomplete because of the large size of image data set. For this reason, the Deep Learning models introduced in the field of image processing meet this need in the software field In this study, Convolutional Neural Network (CNN) model from the Deep Learning Algorithms and the Optimization Algorithms used in Deep Learning have been applied to international image data sets. Optimization algorithms were applied to both datasets respectively, the results were analyzed and compared The success rate was approximately 96.21% in the Caltech 101 data set, while it was observed to be approximately 10% in the Cifar-100 data set.
UAV-Based Agricultural Spraying: A Study on Spiral Movements and Pesticide Optimization
(Elsevier B.V., 2025) Inan, Mevlut; Karcı, Ali
Unmanned aerial vehicles (UAVs) have become an essential component of precision agriculture, providing enhanced accuracy and operational efficiency in pesticide application. This study presents an innovative spraying protocol that integrates spiral flight trajectories with volumetric classification of olive trees, enhancing operational performance while reducing environmental impact. Using high-resolution UAV imagery in conjunction with advanced image processing, trees were categorized into small, medium, and large canopy-volume classes. For each group, optimized spiral patterns with predefined turn counts and flight altitudes were assigned to achieve uniform droplet deposition across complex canopy structures. Field experiments conducted in the Hekimhan district of Malatya, Türkiye, demonstrated an 85 % improvement in spraying efficiency, a 15 % reduction in chemical usage, and a 20 % decrease in operational time compared with conventional methods. The proposed approach significantly improved targeting precision and minimized off-target drift. These results clearly indicate that the proposed protocol is scalable, environmentally sustainable, and operationally efficient for pesticide application in orchards and other tree-based agricultural systems.This approach demonstrates considerable potential for widespread adoption in precision agriculture, offering a replicable and adaptable framework for enhancing the efficiency and sustainability of pesticide application in diverse orchard systems. © 2025 Elsevier B.V., All rights reserved.