Yazılım Mühendisliği Bölümü Bildiri Koleksiyonu

Bu koleksiyon için kalıcı URI

Güncel Gönderiler

Listeleniyor 1 - 6 / 6
  • Öğe
    Metaheuristic algorithms in IoT: optimized edge node localization
    (springer link, 2022) Kiani, Farzad; Seyyedabbasi, Amir
    In this study, a new hybrid method is proposed by using the advantages of Grey Wolf Optimizer (GWO) and Moth-Flame Optimization (MFO) algorithms. The proposed hybrid metaheuristic algorithm tries to find the near-optimal solution with high efficiency by using the advantage of both algorithms. At the same time, the shortcomings of each will be eliminated. The proposed algorithm is used to solve the edge computing node localization problem, which is one of the important problems on the Internet of Things (IoT) systems, with the least error rate. This algorithm has shown a successful performance in solving this problem with a smooth and efficient position update mechanism. It was also applied to 30 famous benchmark functions (CEC2015 and CEC2019) to prove the accuracy and general use of the proposed method. It has been proven from the results that it is the best algorithm with a success rate of 54% and 57%, respectively. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
  • Öğe
    Embryonic aortic arch material properties obtained by optical coherence tomography-guided micropipette aspiration
    (Elsevier, 2022) Lashkarinia, S.Samaneh; Çoban, Gürsan; Banu Siddiqui, Hummaira; Hwai Yap, Choon; Pekkan, Kerem
    It is challenging to determine the in vivo material properties of a very soft, mesoscale arterial vesselsof size ? 80 to 120 ?m diameter. This information is essential to understand the early embryonic cardiovascular development featuring rapidly evolving dynamic microstructure. Previous research efforts to describe the properties of the embryonic great vessels are very limited. Our objective is to measure the local material properties of pharyngeal aortic arch tissue of the chick-embryo during the early Hamburger-Hamilton (HH) stages, HH18 and HH24. Integrating the micropipette aspiration technique with optical coherence tomography (OCT) imaging, a clear vision of the aspirated arch geometry is achieved for an inner pipette radius of Rp = 25 ?m. The aspiration of this region is performed through a calibrated negatively pressurized micro-pipette. A computational finite element model is developed to model the nonlinear behaviour of the arch structure by considering the geometry-dependent constraints. Numerical estimations of the nonlinear material parameters for aortic arch samples are presented. The exponential material nonlinearity parameter (a) of aortic arch tissue increases statistically significantly from a = 0.068 ± 0.013 at HH18 to a = 0.260 ± 0.014 at HH24 (p = 0.0286). As such, the aspirated tissue length decreases from 53 ?m at HH18 to 34 ?m at HH24. The calculated NeoHookean shear modulus increases from 51 Pa at HH18 to 93 Pa at HH24 which indicates a statistically significant stiffness increase. These changes are due to the dynamic changes of collagen and elastin content in the media layer of the vessel during development. © 2022 Elsevier Ltd
  • Öğe
    Estimating the effect of renewable energy rolicies on the republic of Turkey's gross national product by using artificial intelligence
    (IEEE, 2022) Beken, Murat; Kurt, Nursaç; Eyecioglu, Onder
    Today, most of the states in the energy field, especially the developed countries in the world, continue to increase the rate of use of renewable energy. The Republic of Turkey is one of these states. This study aimed to examine the effect of the renewable energy transformation process on the gross national product with artificial intelligence in the action plan of the Republic of Turkey in the process of moving away from fossil fuel-based energy sources. We deployed artificial neural networks to estimate Turkey's gross national product. As a result of the study, because of the policy of increasing the use of renewable energy sources by 7% annually and reducing the use of fossil derivative fuels by 8% annually in the next twenty years, the energy distributions in 2043 and their effect on Turkey's gross national product are shown. © 2022 IEEE.
  • Öğe
    Data preprocessing strategy in constructing convolutional neural network classifier based on constrained particle swarm optimization with fuzzy penalty function
    (Elsevier, 2022) Zhou, Kun; Oh, Sung-Kwun; Pedrycz, Witold; Qiu, Jianlong
    Convolutional neural networks (CNNs) have attracted increasing attention in recent years because of their powerful abilities to extract and represent spatial/temporal information. However, for general data, its features are assumed to have weak or no correlation, and directly applying CNN to classify such data could result in poor classification performance. To address this problem, a combined technique of original data representation method of fuzzy penalty function-based constrained particle swarm optimization (FCPSO) and CNN, so-called FCPSO-CNN is designed to effectively solve the classification problems for generic dataset and applied to recognize (classify) black plastic wastes in recycling problems. In more detail, CPSO is introduced to optimize feature reordering matrix under constraints and the construction of this matrix is driven by fitness function of CNN that quantifies classification performance. The Mamdani type fuzzy inference system (FIS) is employed to realize the fuzzy penalty function (FPF) which is utilized to realize the constrained problems of CPSO as well as alleviate the issues of the original penalty function method suffering from the lack of robustness. Experimental results demonstrate that FCPSO-CNN achieves the best classification accuracy on 13 out of 17 datasets; the statistical analysis also confirms the superiority of FCPSO-CNN. An interesting point is worth to mention that some feature reordering matrices in the infeasible space come with better classification accuracy. It has been found that the proposed method results in more accurate solution than one-dimensional CNN, random reordering feature-based CNN and some well-known classifiers (e.g., Naive Bayes, Multilayer perceptron, Support vector machine).
  • Öğe
    variant interpreter and genetic analysis summary generator
    (Nature Publishing Group, 2019) Görmez, Zeliha; Erserim, I.; Erdoğan, D.
    We have developed a software that generates genetic analysis summary report by using VCF files are standard output files of variant identification programs. GenerAVI programmed by using java. It can be run on three must common operating systems: Windows, Linux, Mac-OSX. There is no installation requirement.
  • Öğe
    Identification of the post-zygotic mosaic nonsense mutation in WDR45gene leading to beta-propeller protein-associated neurodegeneration and defining sex chromosomal mosaicism at whole exome sequencing
    (Nature Publishing Group, 2019) Akcakaya, Nihan Hande; Salman, Barış; Argüden, Yelda Tarkan; Görmez, Zeliha; Dönmez, R.; Çolakoğlu, Berril Dönmez; Yapıcı, Zuhal; Hacıhanefioğlu, Seniha; Özbek, Uğur; İşeri, Sibel Aylin Uğur
    [No Abstract Available]