Yazar "Karkinli, Ahmet Emin" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    A clustering-based approach to land valuation in land consolidation projects
    (Elsevier Sci Ltd, 2021) Ertunc, Ela; Karkinli, Ahmet Emin; Bozdag, Asli
    Land valuation is a comprehensive assessment process that aims to assign the agricultural value of all parcels in the land consolidation area, based on soil quality and land productivity (using a relative non-dimensional score). Thus, the land value represents a critical parameter that directly influences the monetary interests of landowners. This process should be managed in a reliable, correct, and fair manner. Furthermore, the traditional land valuation process is time-consuming and costly, and its results may be inconsistent because those who determine the value cannot take into account and compare the land valuation parameters required for all parcels. The solution to these deficiencies requires a new valuation approach. After land consolidation in the project area, the value of the existing parcels must be determined according to certain criteria in order to give to the enterprise land with the equal value to its previous land. In this study, a new land valuation model was developed with the help of clustering algorithms (K-means, K-medoids, Fuzzy C-means) and Weighted Differential Evolution, a heuristic optimization algorithm, using the most basic nine different parameters affecting the land value. The clustering method used in this model performs the valuation by clustering the parcels with common characteristics according to the parameter values. The method in which the cumulative sum of the distances of parcels to the cluster centers is the shortest exhibits the best clustering performance. In this study, the best clustering performance was obtained with the WDE-based clustering algorithm. When compared with the other algorithm results by mapping the classical valuation results, it was determined that the clustering method results evaluated the parcels more precisely. The study contributes to the literature in terms of including in the developed method parameters other than those used in the existing methods and determining the land value more precisely, fairly, and reliably with the help of heuristic algorithms.
  • Küçük Resim Yok
    Öğe
    Detection of object boundary from point cloud by using multi-population based differential evolution algorithm
    (Springer London Ltd, 2023) Karkinli, Ahmet Emin
    The problem-solving success of an Evolutionary Computing algorithm is too sensitive to the structures of mutation and crossover operators it uses. The mutation operator generates the trial vectors necessary for the relevant Evolutionary Computing method to perform efficient global and local search in the search space. Partial elitist mutation operators can produce more efficient trial vectors than isotropic mutation strategies. Another numerical genetic operator that affects the process of producing efficient trial vectors is crossover. Due to the dominant effect of the Evolutionary Computing algorithms of mutation and crossover operators on problem solving capacity, new numerical-genetic operators are constantly being developed. When solving a problem with the Differential Evolution Algorithm determining the ideal mutation operator and setting the initial values of the internal parameters of the crossover operator is quite time-consuming and difficult. In this paper, the Multi-population Based Differential Evolution Algorithm (MDE) has been proposed to solve real-valued numerical optimization problems with its convergence proof. The mutation operator of MDE is partial-elitist and its crossover operator is parameter-free, in practice. In this paper, 28 benchmark problems of CEC2013 with Dim = 20 and one real-world geometric optimization problem have been used in the experiments performed to examine the numerical problem-solving success of MDE. MDE's success in solving related benchmark problems has been statistically compared with ABC, CK, SOS and GWO. Statistical analysis of the results obtained from the experiments exposed that MDE is statistically more successful than comparison methods in solving numerical optimization problems used.