Yazar "Hakli, Huseyin" seçeneğine göre listele
Listeleniyor 1 - 11 / 11
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Artificial bee colony algorithm with variable search strategy for continuous optimization(ELSEVIER SCIENCE INC, 2015) Kiran, Mustafa Servet; Hakli, Huseyin; Gunduz, Mesut; Uguz, HarunThe artificial bee colony (ABC) algorithm is a swarm-based optimization technique proposed for solving continuous optimization problems. The artificial agents of the ABC algorithm use one solution update rule during the search process. To efficiently solve optimization problems with different characteristics, we propose the integration of multiple solution update rules with ABC in this study. The proposed method uses five search strategies and counters to update the solutions. During initialization, each update rule has a constant counter content. During the search process performed by the artificial agents, these counters are used to determine the rule that is selected by the bees. Because the optimization problems and functions have different characteristics, one or more search strategies are selected and are used during the iterations according to the characteristics of the numeric functions in the proposed approach. By using the search strategies and mechanisms proposed in the present study, the artificial agents learn which update rule is more appropriate based on the characteristics of the problem to find better solutions. The performance and accuracy of the proposed method are examined on 28 numerical benchmark functions, and the obtained results are compared with various classical versions of ABC and other nature-inspired optimization algorithms. The experimental results show that the proposed algorithm, integrated and improved with search strategies, outperforms the basic variants and other variants of the ABC algorithm and other methods in terms of solution quality and robustness for most of the experiments. (C) 2015 Elsevier Inc. All rights reserved.Öğe Comparison of designed different land reallocation models in land consolidation: A case study in Konya/Turkey(ELSEVIER SCI LTD, 2015) Uyan, Mevlut; Cay, Tayfun; Inceyol, Yasar; Hakli, HuseyinLand consolidation (LC) is the most favorable land management approach for solving agricultural land degradation. LC is essential for ensuring the economic viability of rural areas, facilitating environmental management, or rationalizing urban growth. LC projects consist of various steps. Land reallocation is the most important stage of LC studies and a tool which rearranges proprietary rights. For fast and efficient progress in projects, usage of computer technology has been essential. In this case study, designed two different land reallocation models (SDSS-based and GA-based land reallocation models) is compared for LC projects in reallocation of newly created regular size parcels to landowners. As a result of these comparisons, the GA-based model is some successful than the SDSS-based model in terms of average parcel size, number of parcels and average number of parcels per land-owner. The benefits derived from both models are much higher than conventional models. (C) 2014 Elsevier B.V. All rights reserved.Öğe The energy demand estimation for Turkey using differential evolution algorithm(SPRINGER INDIA, 2017) Beskirli, Mehmet; Hakli, Huseyin; Kodaz, HalifeThe energy demand estimation commands great importance for both developing and developed countries in terms of the economy and country resources. In this study, the differential evolution algorithm ( DE) was used to forecast the long-term energy demand in Turkey. In addition to being employed for solving regular optimization problems, DE is also a global, meta-heuristic algorithm that enables fast, reliable and operative stochastic searches based on population. Considering the correlation between the increase in certain economic indicators in Turkey and the increase of energy consumption, two equations were used-one applying the linear form and the other the quadratic form. Turkey's long-term energy demand from 2012 to 2031 was estimated through the DE method in three different scenarios and in terms of the gross domestic product, import, export and population. To prove the success of the DE method in addressing the energy demand problem, the DE method was compared to other methods found in the literature. Results showed that the proposed DE method was more successful than the other methods. Furthermore, the future projections of energy demand obtained using the proposed method were compared to the indicators of energy demand estimated and observed by the Ministry of Energy and Natural Resources.Öğe Genetic algorithm supported by expert system to solve land redistribution problem(WILEY, 2018) Hakli, Huseyin; Uguz, Harun; Cay, TayfunLand 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.Öğe Modeling of reallocation in land consolidation with a hybrid method(ELSEVIER SCI LTD, 2018) Ertunc, Ela; Cay, Tayfun; Hakli, HuseyinLand consolidation is one of the important tool of increasing productivity in agricultural production. Land consolidation not only consolidates fragmented land, but also improves the standards of landowners in agriculture, technical, social and cultural areas. Land consolidation projects consist of various stages. The most important, complicated and time-consuming part of these stages is land reallocation. Land reallocation is a process which requires a long time and high operating costs and in which there frequently arise disputes between landowners. For these reasons, it is inevitable to use computer technology to optimize this process. In this study, a hybrid method including genetic algorithm and fuzzy logic techniques which enable reallocation to be done automatically in land consolidation has been used. The crossover rate and the operation of the genetic algorithm (GA) method have been realized as a self-adaptive structure using fuzzy logic techniques A similar study used for the land reallocation problem in the literature, the results of reallocation plans obtained by the technician and the results obtained by the hybrid method have been compared. When the experimental results are evaluated, it has been found that the hybrid method used is more successful and efficient than similar studies in the literature and also has a better reallocation plan.Öğe A new algorithm based on artificial bee colony algorithm for energy demand forecasting in Turkey(IEEE, 2015) Uguz, Harun; Hakli, Huseyin; Baykan, Omer K.In this study, an energy demand forecasting algorithm based on the Artificial Bee Colony with Variable Search Strategies (ABCVSS) method was proposed in order to determine Turkey's long-term energy demand. Linear and quadratic equations were used for energy demand forecasting and the coefficients of the equations were determined by means of the ABCVSS method. With the ABCVSS method, an attempt was made to enhance the local and global searching capacity of the ABC algorithm by using five different search strategies. GDP, population, imports and exports data of the period from 1979 to 2005 were chosen as the input parameters for the proposed method. Long-term energy demand was predicted through one scenario and the obtained performance from the proposed method was compared to those obtained from PSO, ACO and HAP algorithms in the literature. It was determined that the proposed method is statistically more successful than the other methods.Öğe A new approach for automating land partitioning using binary search and Delaunay triangulation(ELSEVIER SCI LTD, 2016) Hakli, Huseyin; Uguz, Harun; Cay, TayfunOne of the most important, yet time-consuming steps of the land consolidation process, which is related to pooling fragmented lands together, is the production of land partitioning plans. After the land redistribution process is finished, the land partitioning process begins. In that process, the locations of parcels within the blocks are determined. Due to the non-uniform geometric shapes of the blocks, the areas of the parcels cannot be divided directly. The production of an ideal land partitioning plan is not suitable automatically unless a quick, accurate process to divide the lands is secured. In this study, production of a pre-land partitioning plan is realized using both the binary search method and the Delaunay triangulation method, taking into consideration shape, size, value and road access criteria. The result of the experimental study shows that the proposed approach for dividing the parcels makes the process take place more quickly. Thus, a solid base for creating an automatic land partitioning plan-one that is closest to an ideal plan-will be provided with this study. (C) 2016 Elsevier B.V. All rights reserved.Öğe A new optimization algorithm for solving wind turbine placement problem: Binary artificial algae algorithm(PERGAMON-ELSEVIER SCIENCE LTD, 2018) Beskirli, Mehmet; Koc, Ismail; Hakli, Huseyin; Kodaz, HalifeThe wind turbine has grown out to be one of the most common renewable energy sources around the world in recent years. As wind energy becomes more important, the significance of wind turbine placement also increases. This study was intended to position the wind turbines on a wind farm to achieve the highest performance possible. The turbine placement operation was designed for a 2 km x 2 km area. The surface of the area was calculated by dividing it into a 10 x 10 grid and a 20 x 20 grid with the use of binary coding. The calculation revealed ten different new binary algorithms using ten different transfer functions of the Artificial Algae Algorithm (AAA) that has been successfully applied to solve continuous optimization problems. These algorithms were applied to the turbine placement problem, and the algorithm that obtained the best result was called the Binary Artificial Algorithm (BinAAA). The results of the proposed algorithm for the binary turbine placement optimization problem were compared with those of other well-known algorithms in the relevant literature. The algorithm that was proposed in the study is an efficient algorithm for the placement problem of wind turbines since it optimized the binary search space and achieved the most successful result (C) 2017 Elsevier Ltd. All rights reserved.Öğe A novel approach for automated land partitioning using genetic algorithm(PERGAMON-ELSEVIER SCIENCE LTD, 2017) Hakli, Huseyin; Uguz, HarunLand consolidation is an important tool to prevent land fragmentation and enhance agricultural productivity. Land partitioning is one of the most significant problems within the land consolidation process. This process is related to the subdivision of a block having non-uniform geometric shapes. Land partitioning determines the location of new land parcels and is a complex problem containing many conflicting demands, so conventional programming techniques are not sufficient for this NP optimization problem. Therefore, it is necessary to have an intelligent system with a standard decision-making mechanism capable of processing many criteria simultaneously and evaluating a number of different solutions in a short time. To overcome this problem and accelerate the land partitioning process, we proposed automated land partitioning using a genetic algorithm (ALP-GA). Besides the parcel's size, shape and land value, the proposed method evaluates fixed facilities, and the degree and location of cadastral parcels to generate a land partitioning plan. The proposed method automated the land partitioning process using an intelligent system and was implemented over a real project area, Experimental study shows that the proposed method is more successful and efficient than the designer with respect to the results meeting the objective function. In addition, the land partition process is greatly simplified by the proposed method. (C) 2017 Elsevier Ltd. All rights reserved.Öğe A novel particle swarm optimization algorithm with Levy flight(ELSEVIER SCIENCE BV, 2014) Hakli, Huseyin; Uguz, HarunParticle swarm optimization (PSO) is one of the well-known population-based techniques used in global optimization and many engineering problems. Despite its simplicity and efficiency, the PSO has problems as being trapped in local minima due to premature convergence and weakness of global search capability. To overcome these disadvantages, the PSO is combined with Levy flight in this study. Levy flight is a random walk determining step size using Levy distribution. Being used Levy flight, a more efficient search takes place in the search space thanks to the long jumps to be made by the particles. In the proposed method, a limit value is defined for each particle, and if the particles could not improve self-solutions at the end of current iteration, this limit is increased. If the limit value determined is exceeded by a particle, the particle is redistributed in the search space with Levy flight method. To get rid of local minima and improve global search capability are ensured via this distribution in the basic PSO. The performance and accuracy of the proposed method called as Levy flight particle swarm optimization (LFPSO) are examined on well-known unimodal and multimodal benchmark functions. Experimental results show that the LFPSO is clearly seen to be more successful than one of the state-of-the-art PSO (SPSO) and the other PSO variants in terms of solution quality and robustness. The results are also statistically compared, and a significant difference is observed between the SPSO and the LFPSO methods. Furthermore, the results of proposed method are also compared with the results of well-known and recent population-based optimization methods. (C) 2014 Elsevier B.V. All rights reserved.Öğe Support vector machines classification based on particle swarm optimization for bone age determination(ELSEVIER, 2014) Guraksin, Gur Emre; Hakli, Huseyin; Uguz, HarunThe evaluation of bone development is a complex and time-consuming task for the physicians since it may cause intraobserver and interobserver differences. In this study, we present a new training algorithm for support vector machines in order to determine the bone age in young children from newborn to 6 years old. By the new algorithm, we aimed to assist the radiologists so as to eliminate the disadvantages of the methods used in bone age determination. To achieve this purpose, primarily feature extraction procedure was performed to the left hand wrist X-ray images by using image processing techniques and the features related with the carpal bones and distal epiphysis of radius bone were obtained. Then these features were used for the input arguments of the classifier. In the classification process, a new training algorithm for support vector machines was proposed by using particle swarm optimization. When training support vector machines, particle swarm optimization was used for generating a new training instance which will represent the whole training set of the related class by using the training set. Finally, these new instances were used as the support vectors and classification process was carried out by using these new instances. The performance of the proposed method was compared with the naive Bayes, k-nearest neighborhood, support vector machines and C4.5 algorithms. As a result, it was determined that the proposed method was found successful than the other methods for bone age determination witha classification performance of 74.87%. (C) 2014 Elsevier B.V. All rights reserved.
