Yazar "Safi, Hayder H." seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • [ X ]
    Öğe
    An efficient multi-objective memetic genetic algorithm for medical image handling and health safety to support systems in medical internet of things
    (Amer Scientific Publishers, 2020) Safi, Hayder H.; Uçan, Osman Nuri; Bayat, Oğuz
    Over the most recent couple of decades, the Evolutionary Algorithms (EA) have been considered as a typical dynamic research zone in the field of medicinal picture preparing and wellbeing administrations. This is a direct result of the presence of numerous streamlining issues in this field which can be comprehended utilizing developmental calculations. Besides, numerous certifiable streamlining issues in the restorative picture handling and wellbeing administrations have more than one target work, and for the most part the issue goals are in struggle with one another. The traditional multi-objective transformative calculations perform well when the streamlining issue has less than three goal functions, where the execution of these calculations altogether degrades when the improvement issue has high number of destinations. To deal with this issue, there is a requirement for growing new versatile transformative streamlining mechanisms which can handle the high target capacities in the medicinal picture preparing and wellbeing administrations advancement issues. In this paper, we propose a new developmental calculation dependent on the NSGA-II calculation to productively take care of the many-target enhancement issues. The proposed calculation adds three plans to improve the capacity of NSGA-II calculation when managing with high objective dimensional streamlining issues. Another productive arranging strategy, savvy file and straightforward nearby pursuit are utilized to accelerate the solutions combination procedure to the POF and upgrade the decent variety of the arrangements. The proposed calculation is contrasted and the cutting edge multi-target advancement calculations utilizing five DTLZ test issues. The outcomes demonstrate that our proposed calculation essentially beats alternate calculations when the quantity of target capacities is high. Moreover, we applied our proposed algorithm on medical imaging health problem which is the melanoma recognition problem to enhance the early detection of melanoma disease.
  • [ X ]
    Öğe
    Minimize the cost function in multiple objective optimization by using NSGA-II
    (Springer Verlag, 2019) Safi, Hayder H.; Mohammed, Tareq Abed; Al-Qubbanchi, Z.F.
    This study proposes a new framework to minimize the cost function of multi-objective optimization problems by using NSGA-II in economic environments. For multi-objective improvements, the most generally used developmental algorithms such as NSGA-II, SPEA2 and PESA-II can be utilized. The economical optimization framework includes destinations, requirements, and parameters which continuously can change with time. The minimization of the cost function issue is one of the most important issues as in the case of stationary optimization problems. In this paper, we propose a framework that can possibly reduce the high cost of all functions that used in economic environments. Our algorithm uses a set of linear equations as inputs which depend on multi-objective algorithm that based on a Non-Dominated Sorting Genetic Algorithm (NSGA-II). The results of our experimental study show that the proposed framework can efficiently be used to reduce the cost and time of optimizing the economical problems. © Springer Nature Switzerland AG 2019.
  • [ X ]
    Öğe
    On the real world applications of many-objective evolutionary algorithms
    (Assoc Computing Machinery, 2018) Safi, Hayder H.; Uçan, Osman Nuri; Bayat, Oğuz
    Recently, many-objective evolutionary algorithms have been studied by many researchers. Most of research works were concentrated on developing new methods that can deal with the high number of objective functions of such complex problems. Proposing new scalable benchmarks and valid performance metrics are another two commonly discussed domains in many-objective optimization problems. Most of proposed algorithms have been used to solve different real-world problems from several domains and applications. There are many research papers were published to review and compare the performance of current many-objective evolutionary algorithms. On the other hand there is no work that presented to highlight and review the usage of such algorithms in real problems and applications. Therefore there is an increasing significance for analyzing and reviewing of the complex real world problems that solved using many-objective optimization evolutionary algorithm. In this paper, we review the recently research work that have been done in the domain of solving complex real-world problems using many objective evolutionary algorithms. In addition, the most important issues of metrics, benchmarks and algorithms will be discussed briefly.
  • [ X ]
    Öğe
    Study the effect of high dimensional objective functions on multi-objective evolutionary algorithms
    (Association for Computing Machinery, 2018) Safi, Hayder H.; Uçan, Osman Nuri; Bayat, Oğuz
    Multi-objective Evolutionary Algorithms (MOEAs) have been widely studied by many researchers and they have been used to solve different real-world applications that have more than one objective function. However, most MOEAs work well only when the number of objective functions is small such as two or three. The performance of MOEAs starts degrading significantly when number of objective functions increases. Therefore, there is increasing importance for studying and analyzing the effect of increasing the number of objective functions on the performance of current multi objective evolutionary algorithms. In this paper, the performance of three state-of-the-art multi objective evolutionary algorithms is investigated when increasing the number of objective functions. The tested algorithms are analyzed using test DTLZ test suit. The results show that SMPSO and NSGA-II algorithms are the best two algorithms for high number of objective functions. In addition, the results show that the running time of SMPSO and GDE3 algorithms was effected and increased much when the number of objective functions is large. © Copyright 2018 ACM.