Yazar "Uguz, Harun" seçeneğine göre listele

Listeleniyor 1 - 5 / 5
  • Küçük Resim Yok
    Öğe
    Comparing the performances of six nature-inspired algorithms on a real-world discrete optimization problem
    (Springer, 2022) Hakli, Huseyin; Uguz, Harun; Ortacay, Zeynep
    Many new, nature-inspired optimization algorithms are proposed these days, and these algorithms are gaining popularity day by day. These algorithms are frequently preferred for these real-world problems as they need less information, are reliable and robust, and have a structure that can easily be applied to discrete problems. Too many algorithms result in difficulty choosing the correct technique for the problem, and selecting an unwise method affects the solution quality. In addition, some algorithms cannot be reliable for some specific real-world problems but very successful for others. In order to guide and give insight into the practitioners and researchers about this problem, studies involving the comparison and evaluation of the performance of algorithms are needed. In this study, the performances of six nature-inspired methods, which included five new implementations of differential evolutionary algorithms (DE), scatter search (SS), equilibrium optimizer (EO), marine predators algorithm (MPA), and honey badger algorithm (HBA) applied to land redistribution problem and genetic algorithms (GA), were compared. In order to compare the algorithms in detail, various performance indicators were used as problem based and algorithm based. Experimental results showed that DE and SS algorithms have a more successful performance than the other methods by solution quality, robustness, and many problem-based indicators.
  • Küçük Resim Yok
    Öğe
    Failure Prediction of Aircraft Equipment Using Machine Learning with a Hybrid Data Preparation Method
    (Hindawi Ltd, 2020) Celikmih, Kadir; Inan, Onur; Uguz, Harun
    There is a large amount of information and maintenance data in the aviation industry that could be used to obtain meaningful results in forecasting future actions. This study aims to introduce machine learning models based on feature selection and data elimination to predict failures of aircraft systems. Maintenance and failure data for aircraft equipment across a period of two years were collected, and nine input and one output variables were meticulously identified. A hybrid data preparation model is proposed to improve the success of failure count prediction in two stages. In the first stage, ReliefF, a feature selection method for attribute evaluation, is used to find the most effective and ineffective parameters. In the second stage, aK-means algorithm is modified to eliminate noisy or inconsistent data. Performance of the hybrid data preparation model on the maintenance dataset of the equipment is evaluated by Multilayer Perceptron (MLP) as Artificial Neural network (ANN), Support Vector Regression (SVR), and Linear Regression (LR) as machine learning algorithms. Moreover, performance criteria such as the Correlation Coefficient (CC), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE) are used to evaluate the models. The results indicate that the hybrid data preparation model is successful in predicting the failure count of the equipment.
  • Küçük Resim Yok
    Öğe
    Genetic algorithm supported by expert system to solve land redistribution problem
    (Wiley, 2018) Hakli, Huseyin; Uguz, Harun; Cay, Tayfun
    Land redistribution, a real-world optimization problem, involves the distribution of land parcels in predetermined blocks based on the landowners' preferences. This process, measured in weeks or months, is usually performed manually by a technician with the support of computer software. Although various techniques have been developed in recent years to solve this complex problem, they all require improvement. This study aimed to develop a new technique and produce applicable redistribution plans using a genetic algorithm (GA) in combination with an expert system. Blocks of cadastral parcels were determined by a GA using a new objective function to consider the overflow and residual areas as well as the landowners' preferences. The expert system was employed to close (reduce to zero) the overflow or residual areas occurring after the GA distribution. To investigate the performance of the proposed method, the system was used on a real study area and the results were compared against those obtained for the same cadastral situation undertaken by a technician using a similar method from published literature. The experimental results showed that the method proposed in this study performed better than the other methods because it provided a successful and applicable redistribution plan for the study area in a much shorter time.
  • Küçük Resim Yok
    Öğe
    Implementation of meta-heuristic optimization algorithms for interview problem in land consolidation: A case study in Konya/Turkey
    (Elsevier Sci Ltd, 2021) Ozsari, Sifa; Uguz, Harun; Hakli, Huseyin
    The cultivation of soil for supply of nutritional products necessary for human life is called agriculture. Although agriculture is very important for human beings, it is getting more difficult day by day to cultivate soil efficiently for various reasons. One of the main causes, which significantly prevents sustainable agriculture, is land fragmentation. Land consolidation is one of the important measures taken in order to prevent further fragmentation of agricultural land and the decrease in yield obtained from agriculture. The land consolidation process consists of several time consuming steps. Interview, today conducted manually in Turkey, is the stage where preferences of landowners are taken. These preferences correspond to the blocks that enterprises want their parcels to be placed at the end of consolidation. The interview phase takes a long time as it is carried out manually by a technician. Various studies have been done to improve the land consolidation, but most of these studies focus on other stages of process. In this study, genetic algorithm, particle swarm optimization, non-dominated sorting genetic algorithm II and multi objective particle swarm optimization are applied on the interview problem. The interview problem is a discrete structure optimization problem, thus its solution with traditional methods is difficult and time consuming. Preference lists are generated automatically using optimization algorithms. These lists are compared with the actual interview lists created by the technician. The experimental results confirm the success of algorithms in solving the real world problem.
  • Küçük Resim Yok
    Öğe
    Implementation of the land reallocation problem using NSGA-II and PESA-II algorithms: a case study in Konya/Turkey
    (Taylor & Francis Ltd, 2023) Haber, Zeynep; Uguz, Harun; Hakli, Huseyin
    Land consolidation is one of the essential tools to increase productivity in agricultural production. The most important, complex, and time-consuming step is land allocation among the land consolidation stages. For these reasons, it is inevitable to use computer technology to optimize this process. This study used reallocation models based on PESA-II and NSGA-II optimization algorithms to solve the reallocation problem. The methods were compared with the optimization algorithms in the literature and the conventional method obtained by the technician. The applied algorithms have achieved successful results by parcel number, average parcel size, and reallocation cost.