TR-Dizin İndeksli Yayınlar Koleksiyonu

Permanent URI for this collectionhttps://hdl.handle.net/20.500.12416/8652

Browse

Filters

2020 - 20225

Settings

Scopus Q: search.filters.scopusQuartile.Q3Subject: search.filters.subject.Bilgisayar Bilimleri, Yazılım Mühendisliği

Search Results

Now showing 1 - 5 of 5
  • Article
    Citation - Scopus: 20
    Evolutionary Mathematical Science, Fractional Modeling and Artificial Intelligence of Nonlinear Dynamics in Complex Systems
    (Akif AKGUL, 2022) Karaca, Yeliz; Baleanu, Dumitru
    Complex problems in nonlinear dynamics foreground the critical support of artificial phenomena so that each domain of complex systems can generate applicable answers and solutions to the pressing challenges. This sort of view is capable of serving the needs of different aspects of complexity by minimizing the problems of complexity whose solutions are based on advanced mathematical foundations and analogous algorithmic models consisting of numerous applied aspects of complexity. Evolutionary processes, nonlinearity and all the other dimensions of complexity lie at the pedestal of time, reveal time and occur within time. In the ever-evolving landscape and variations, with causality breaking down, the idea of complexity can be stated to be a part of unifying and revolutionary scientific framework to expound complex systems whose behavior is perplexing to predict and control with the ultimate goal of attaining a global understanding related to many branches of possible states as well as high-dimensional manifolds, while at the same time keeping abreast with actuality along the evolutionary and historical path, which itself, has also been through different critical points on the manifold. In view of these, we put forth the features of complexity of varying phenomena, properties of evolution and adaptation, memory effects, nonlinear dynamic system qualities, the importance of chaos theory and applications of related aspects in this study. In addition, processes of fractional dynamics, differentiation and systems in complex systems as well as the dynamical processes and dynamical systems of fractional order with respect to natural and artificial phenomena are discussed in terms of their mathematical modeling. Fractional calculus and fractional-order calculus approach to provide novel models with fractional-order calculus as employed in machine learning algorithms to be able to attain optimized solutions are also set forth besides the justification of the need to develop analytical and numerical methods. Subsequently, algorithmic complexity and its goal towards ensuring a more effective handling of efficient algorithms in computational sciences is stated with regard to the classification of computational problems. We further point out the neural networks, as descriptive models, for providing the means to gather, store and use experiential knowledge as well as Artificial Neural Networks (ANNs) in relation to their employment for handling experimental data in different complex domains. Furthermore, the importance of generating applicable solutions to problems for various engineering areas, medicine, biology, mathematical science, applied disciplines and data science, among many others, is discussed in detail along with an emphasis on power of predictability, relying on mathematical sciences, with Artificial Intelligence (AI) and machine learning being at the pedestal and intersection with different fields which are characterized by complex, chaotic, nonlinear, dynamic and transient components to validate the significance of optimized approaches both in real systems and in related realms.
  • Article
    Citation - WoS: 12
    Citation - Scopus: 19
    Artificial Intelligence Applications in Earthquake Resistant Architectural Design: Determination of Irregular Structural Systems With Deep Learning and Imageai Method
    (Gazi Univ, Fac Engineering Architecture, 2020) Bingol, Kaan; Akan, Asli Er; Ormecioglu, Hilal Tugba; Er, Arzu
    Although the architectural design process is carried out with the collaboration of experts who are experienced in many different areas from the main preferences to the detailing stage, the major decisions such as plan organization, mass design etc. are taken by the architect. Computer Aided Design (CAD) programs are generally effective after the major decisions of the design are taken. For this reason, it is common for the main decisions, taken during the design process, to be changed during the analysis of the structural system. In order to prevent this, in the early stages of architectural design, earthquake system awareness and structural system design should be included as an design input; as, the failure of the structural system which did not considered well in the architectural design phase leads to unexpected revisions in the implementation project phase and thus leads to serious losses in both time and cost. The aim of this study is to create an Irregularity Control Assistant (IC Assitant) that can provide architects general information about the appropriateness of structural system decisions to earthquake regulations in the early stages of design process by using the deep learning and image processing methods. In this way, correct decisions will be made in the early stages of the design and unexpected revisions that may occur during the implementation project phase will be prevented.
  • Article
    Citation - Scopus: 3
    Strength Prediction of Engineered Cementitious Composites With Artificial Neural Networks
    (MIM RESEARCH GROUP, 2021) Yesilmen, S.
    Engineered Cementitious composites (ECC) became widely popular in the last decade due to their superior mechanical and durability properties. Strength prediction of ECC remains an important subject since the variation of strength with age is more emphasized in these composites. In this study, mix design components and corresponding strengths of various ECC designs are obtained from the literature and ANN models were developed to predict compressive and flexural strength of ECCs. Error margins of both models were on the lower side of the reported error values in the available literature while using data with the highest variability and noise. As a result, both models claim considerable applicability in all ECC mixture types. © 2021 MIM Research Group. All rights reserved.
  • Article
    Citation - WoS: 1
    Citation - Scopus: 2
    Classification of Low Probability of Intercept Radar Waveforms Using Gabor Wavelets
    (Gazi Univ, Fac Engineering Architecture, 2021) Ergezer, Halit
    Low Probability of Intercept (LPI Radar) is a class of radar with specific technical characteristics that make it very difficult to intercept with electronic support systems and radar warning receivers. Because of their properties as low power, variable frequency, wide bandwidth, LPI radar waveforms are difficult to intercept by ESM systems. In recent years, studies on the classification of waveforms used by these types of radar have been accelerated. In this study, Time-Frequency Images (TFI) has been obtained from the LPI radars waveforms by using Choi-Williams Distribution method. From these images, feature vectors have been generated using Gabor Wavelet transform. In contrast to many methods in the literature, waveform classification has been performed by directly comparing the feature vectors obtained without using any machine learning method. With the method we propose, classification accuracies were obtained at intervals of 2 dB between -20 dB and 10 dB and performed at reasonable classification accuracy rates up to -8 dB SNR value. Better results than the best reported in the literature were obtained for some signal types. The results obtained for all waveform types are given in comparison with the results of the existing methods in the literature.
  • Article
    Artificial intelligence applications in earthquake resistant architectural design: Determination of irregular structural systems with deep learning and ImageAI method
    (2020) Bingöl, Kaan; Er Akan, Aslı; Ömercioğlu, Hilal Tuğba; Er, Arzu; Ormecıoglu, Hılal Tugba; Akan, Aslı Er
    Although the architectural design process is carried out with the collaboration of experts who are experienced in many different areas from the main preferences to the detailing stage, the major decisions such as plan organization, mass design etc. are taken by the architect. Computer Aided Design (CAD) programs are generally effective after the major decisions of the design are taken. For this reason, it is common for the main decisions, taken during the design process, to be changed during the analysis of the structural system. In order to prevent this, in the early stages of architectural design, earthquake system awareness and structural system design should be included as an design input; as, the failure of the structural system which did not considered well in the architectural design phase leads to unexpected revisions in the implementation project phase and thus leads to serious losses in both time and cost. The aim of this study is to create an Irregularity Control Assistant (IC Assitant) that can provide architects general information about the appropriateness of structural system decisions to earthquake regulations in the early stages of design process by using the deep learning and image processing methods. In this way, correct decisions will be made in the early stages of the design and unexpected revisions that may occur during the implementation project phase will be prevented.