Yazar "Cengiz, Enes" seçeneğine göre listele

Listeleniyor 1 - 6 / 6
  • [ X ]
    Öğe
    A Comparison of Multi-Layer Perceptron and Inverse Kinematic for RRR Robotic Arm
    (Gazi Univ, 2024) Aysal, Faruk Emre; Celik, Ibrahim; Cengiz, Enes; Oguz, Yuksel
    In this study, the position control simulation of a 3 Degree of Freedom (3DOF) robot arm was compared with machine learning and inverse kinematic analysis separately. The considered robot arm is designed in RRR pattern. In the inverse kinematic analysis of the robot arm, the geometric approach and the analytical approach are used together. Multi-Layer Perceptron (MLP) was used as a machine learning method. Some of the coordinate data that the robot arm can reach in the working space are selected and the MLP model is trained with these data. When training was done with MLP machine learning method, the correlation coefficient (R2) was obtained as 1. Coordinates of 3 different geometric models (helix, star and daisy) that can be included in the working space are used as test data of the MLP model. These tests are simulated in 3D in MATLAB environment. The simulation results were compared with the inverse kinematics analysis data. As a result, Mean Relative Error (MRE) values for helix, star and daisy shapes were calculated as 0.0007, 0.0033 and 0.0011, respectively, in the tests performed. Mean Squared Error (MSE) values were obtained as 0.0034, 0.0065 and 0.0040, respectively. This confirms that the proposed MLP model can operate this system at the desired stability.
  • [ X ]
    Öğe
    A new evolutionary optimization algorithm with hybrid guidance mechanism for truck-multi drone delivery system
    (Pergamon-Elsevier Science Ltd, 2024) Yilmaz, Cemal; Cengiz, Enes; Kahraman, Hamdi Tolga
    Synchronization of the Traveling Salesman Problem with Drone (TSP-D) is one of the most complex NP-hard combinatorial routing problems in the literature. The speeds, capacities and optimization constraints of the truck-drone pair are different from each other. These differences lead to the search space of TSP-D having a high geometric complexity and a large number of local solution traps. Being able to avoid local solution traps in the search space of TSP-D and accurately converge to the global optimal solution is the main challenge for evolutionary search algorithms. The way to overcome this challenge is to dynamically adapt exploitation and exploration behaviors during the search process and maintain these two in a balanced manner depending on the geometric structure of TSP-D's search space. To overcome this challenge, research consisting of three steps was conducted in this article: (i) three different guide selection methods, namely greedy, random and FDB-score based, were used to provide exploitation, exploration and balanced search capabilities, (ii) by hybridizing these three methods at different rates, guide selection strategies with different search capabilities were developed, (iii) by associating these hybrid guide selection strategies with different stages of the search process, the guidance mechanism was given a dynamic behavioral ability. Thus, the Fitness-Distance Balance-based evolutionary search algorithm (FDB-EA) was designed to achieve a sustainable exploitation-exploration balance in the search space of TSP-D and stably avoid local solution traps. To test the performance of the FDB-EA, the number of delivery points was set to 30, 50, 60, 80, and 100 and compared with twenty-seven powerful and current competing algorithms. According to the non-parametric Wilcoxon pairwise comparison results, FDB-EA outperformed all competing algorithms in all five different TSP-D problems. According to the results obtained from the stability analysis, the success rates and calculation times of FDB-EA, EA and AGDE algorithms were 88.00% (6308.79 sec), 58.40% (7377.43 sec) and 13.460% (34664.19 sec) respectively.
  • [ X ]
    Öğe
    Assessment of soil classification using soft computing approaches for Erenler (Afyonkarahisar) region
    (Springer Heidelberg, 2025) Isoglu, Sami Serkan; Yildiz, Ahmet; Mutluturk, Mahmut; Cengiz, Enes
    The Casagrande chart is traditionally used for determining soil classes. However, processing samples individually on this chart is time-consuming, and human error, particularly at the classification boundaries, can lead to incorrect soil classification. To address these issues, this study employs machine learning algorithms to classify different soil types more efficiently and accurately. The primary goal is to integrate machine learning into engineering geology studies, leveraging technological advancements. As part of the study, field and experimental work was conducted, beginning with the collection of 272 soil samples from the designated study area to represent the entire region. The initial physical properties of these samples were then determined. The soil samples were carefully double-bagged and transported to the laboratory to prevent any degradation. Upon arrival, the water content of the samples was determined first. Subsequently, sieve analysis, consistency limits, and specific gravity tests were conducted in sequence. For the classification of soil types, machine learning methods, including Decision Tree (DT), Support Vector Machines (SVM), K-Nearest Neighbor (k-NN), and Artificial Neural Networks (ANN), were employed. Among these, the DT model demonstrated the highest performance, achieving a success rate of 91.5% across five different soil classifications. The ANN, SVM, and k-NN models followed, with success rates of 89.0%, 89.0%, and 86.0%, respectively. In addition, the hyperparameter optimisation of the models used in the study was provided and the minimum classification error analysis was presented. This study significantly contributes to the effective and efficient analysis of experimental data, demonstrating that soil classification can be successfully performed by integrating machine learning methods with numerical data.
  • [ X ]
    Öğe
    Cherry Tree Detection with Deep Learning
    (Institute of Electrical and Electronics Engineers Inc., 2022) Ozer, Tolga; Akdogan, Cemalettin; Cengiz, Enes; Kelek, Muhammed Mustafa; Yildirim, Kasim; Oguz, Yuksel; Akkoc, Hasan
    In recent years, many studies have been conducted on artificial intelligence. Artificial-intelligence-based applications appear in many fields, such as the defense industry, agriculture, transportation, and health. Food production and supply are critical with the increase in the world population and global warming. For this reason, it is seen that various artificial-intelligence-based applications in agriculture are increasing today. In this study, artificial-intelligence-based Cherry tree detection was carried out using the deep learning method. A DJI Mavic air drone collected images of cherry trees in the Afyonkarahisar. A cherry tree dataset was created using these images. The training was carried out with YOLOv5m, YOLOv5s, and YOLOv5x models. As a result of the training, F1 scores of 94.20%, 98.0%, and 95.9% were obtained. The experimental results obtained as a result of the training of the models were shared comparatively. © 2022 IEEE.
  • [ X ]
    Öğe
    Real-Time Application of Traffic Sign Recognition Algorithm with Deep Learning
    (2022) Aysal, Faruk Emre; Yıldırım, Kasım; Cengiz, Enes
    Autonomous vehicles are one of the increasingly widespread application areas in automotive technology. These vehicles show significant potential in improving transportation systems, with their ability to communicate, coordinate and drive autonomously. These vehicles, which move from source to destination without human intervention, appear to be a solution to various problems caused by people in traffic, such as accidents and traffic jams. Traffic accidents and traffic jams are largely due to driver faults and non-compliance with traffic rules. For this reason, it is predicted that integrating artificial intelligence (AI)-based systems into autonomous vehicles will be a solution to such situations, which are seen as a problem in social life. Looking at the literature, VGGNet, ResNet50, MobileNetV2, NASNetMobile, Feed Forward Neural Networks, Recurrent Neural Networks, Long-Short Term Memory, and Gate Recurrent Units It is seen that deep learning models such as these are widely used in traffic sign classification studies. Unlike previous studies, in this study, a deep learning application was made for the detection of traffic signs and markers using an open-source data set and models of YOLOv5 versions. The original data set was prepared and used in the study. Labeling of this data set in accordance with different AI models has been completed. In the developed CNN models, the training process of the data set containing 15 different traffic sign classes was carried out. The results of these models were systematically compared, and optimum performance values were obtained from the models with hyperparameter changes. Real-time application was made using the YOLOv5s model. As a result, a success rate of 98-99% was achieved.
  • [ X ]
    Öğe
    Tarım Alanında İlaçlamaya Yönelik Yapay Zekâ Tabanlı Drone Tasarımı Ve Uygulaması
    (2022) Özer, Tolga; Cengiz, Enes; Akkoç, Hasan; Oğuz, Yüksel; Kelek, Muhammed Mustafa; Akdoğan, Cemalettin
    Dünya nüfusu hızlı bir şekilde artış göstermektedir ve buna bağlı olarak gıda talebinde de artış yaşanmaktadır. Bu sebeple gıda talebini karşılayabilmek için tarımsal arazilerde ürün verimliliğinin artırılması gerekmektedir. Tarımsal arazilerde bitkileri olumsuz yönde etkileyecek böcek ve haşere gibi maddelere ?pestisit? adı verilmektedir. Bitkilerin pestisitlerden temizlenmesi için kimyasal ilaçlanmaya ihtiyaç duyulmaktadır. Tarımsal ürünlerde kimyasal ilaçlamanın ürün verimini %60 arttırdığı yapılan çalışmalar ile görülmektedir. Manuel püskürtmenin en büyük dezavantajı, bu gübreleri püskürten insana solunum rahatsızlıkları, kalp hastalıkları vb. sağlık sorununa neden olabilmesidir. Bu nedenle ilaçlamanın dengeli ve mümkün olduğunca insan gücü kullanılmadan gerçekleştirilmesi gerekmektedir. Bu riskten kaçınmak ve pestisitleri eşit bir şekilde püskürtmek için tarımsal arazilerin ilaçlanması bir drone tarafından gerçekleştirilebilmektedir. Dronelar manuel yöntemlere kıyasla kısa sürede verimli bir ilaçlama yapabilmektedir. Yapılan bu çalışma ile kiraz ağaçlarının yapay zekâ desteği ile otonom bir şekilde ilaçlanması gerçekleştirilmektedir. Yapay zekâ uygulamasının çalıştırılması için NVIDIA Jetson NANO geliştirme kiti kullanılmıştır. Kiraz ağaçlarının tespiti için doğruluğu yüksek olması sebebi ile YOLOv5 modeli tercih edilmiştir. Drone Hexacopter gövde yapısına sahip altı motorlu olacak şekilde SOLIDWORKS programı kullanılarak modellenmiştir ve ANSYS programı ile analizleri gerçekleştirilmiştir. Drone 1150mm gövde uzunluğuna, 5 litre ilaç kapasitesine ve 12 dakika uçuş süresine sahip ilaçlama drone?u geliştirilmiştir. Geliştirilen Hexacopter drone sayesinde tarım arazilerinin ilaçlanması otonom bir şekilde gerçekleştirilmektedir. Yüksekten uçmaları sebebi ile homojen bir ilaçlama gerçekleştirilerek ürünlerin verimi artırılmaktadır. Aynı zamanda gerekli insan gücü ve ilaçlama süresini azaltmakla kalmayarak insan sağlığını olumsuz etkileyen etkileri de azaltacaktır. Bu çalışmanın sonuçlarına göre derin öğrenme modelinin F1-skor değeri 0,980 olarak belirlenmiştir. İlaçlama yöntemi için otonom (sürekli) ilaçlama ve yapay zekâ tabanlı ilaçlama yöntemi karşılaştırıldığında yapay zekâ tabanlı ilaçlama yönteminde %53 daha az ilaç, ilaçlama sisteminde ise %50 daha az enerji kullanımı gerçekleşmiştir. Sunduğu avantajlar sayesinde kiraz ağaçlarının ilaçlanmasında yapay zekâ tabanlı sistemlerin kullanılması önerilmiştir.