Yazar "Kocer, Baris" seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • Küçük Resim Yok
    Öğe
    Bollinger bands approach on boosting ABC algorithm and its variants
    (ELSEVIER, 2016) Kocer, Baris
    In this study, a new algorithm that will improve the performance and the solution quality of the ABC (artificial bee colony) algorithm, a swarm intelligence based optimization algorithm is proposed. ABC updates one parameter of the individuals before the fitness evaluation. Bollinger bands is a powerful statistical indicator which is used to predict future stock price trends. By the proposed method an additional update equation for all ABC-based optimization algorithms is developed to speed up the convergence utilizing the statistical power of the Bollinger bands. The proposed algorithm was tested against classical ABC algorithm and recent ABC variants. The results of the proposed method show better performance in comparison with ABC-based algorithm with one parameter update in convergence speed and solution quality. (C) 2016 Elsevier B.V. All rights reserved.
  • Küçük Resim Yok
    Öğe
    Repeating Successful Movement Strategy for ABC Algorithm
    (UNIV SUCEAVA, FAC ELECTRICAL ENG, 2017) Kocer, Baris
    ABC is a well-known nature inspired algorithm. In short ABC algorithm mimics the foraging behavior of the bee colonies. ABC is very intensively worked algorithm. It has many variants. The base algorithm and most of the variants uses an update equation to improve the solutions. The update equation finds a feasible movement based on neighbor solutions and adds that movement to current to create a mutant solution. If the mutant solution is better than the original one then original solution is updated. None of the ABC variant use a successful movement again. In this work when a successful move found then it is used again. Proposed approach is applied to ABCVSS algorithm which is a recently proposed ABC variant and that modified ABCVSS algorithm (ABCVSSRSM) is tested on numerical benchmark functions and results compared the well-known ABC variants. Results show that proposed method is superior under multiple criteria.
  • Küçük Resim Yok
    Öğe
    A single-objective genetic-fuzzy approach for multi-objective fuzzy problems
    (IOS PRESS, 2013) Kaya, Ersin; Kocer, Baris; Arslan, Ahmet
    In this paper, a genetic algorithm-based search method, which builds ideal rule set for fuzzy rule-based classification systems (FRBCSs), is developed. In FRBCSs, ideal rule set means a set of rules which ensure high classification accuracy with small rule count and small rule length. The related studies in the literature point out that rule set grows exponentially with input attribute count. This growth complicates the searching process and lowers the success rate. Through the proposed method, successive results are obtained for datasets with large input attribute counts using a special coding technique. The proposed method is tested for various datasets and results are compared against the method which uses candidate rule set.
  • Küçük Resim Yok
    Öğe
    Transferring object allocation model over time
    (TAYLOR & FRANCIS LTD, 2015) Kocer, Baris; Arslan, Ahmet
    All the state-of-the-art techniques that try to solve packing problems focus on placing predetermined objects into predetermined areas. However, in real life the size and the number of objects to be placed may change in time and in a manufacturing process a new object allocation model should be built very quickly in order not to interrupt crucial processes. While classical methods begin the solution from scratch, the model transfer method proposed here utilises old allocation model to quickly adapt to the changing conditions in time. The results from this research show that the proposed method is much more efficient than the classical method as the parameters of the nesting problem change frequently.