Yazar "Uzun, Can" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • [ X ]
    Öğe
    A statistical assessment of Sinan's central domed mosques
    (2022) Uzun, Can
    This paper uses a statistical approach to assess the proportional relations between 47 central-domed mosque plans of the architect Sinan. The statistical method is a feature selection method that demonstrates both the significant as well as the redundant features within a dataset by conducting correlation and lasso regression analyses. The analysis dataset contains 16 building elements present in each central domed mosque plan, selected according to Sinan's mosque ontology. The correlation analysis demonstrates 72 significant correlations; the lasso regression shows seven essential features in relation to the area of the central space. The study contributes to the field with an evaluation of both Sinan's high- and low-level design decisions by presenting a statistical assessment methodology of a historical architectural dataset. Results show that Sinan sees the design of a mosque as both a structural and architectural design problem.
  • [ X ]
    Öğe
    An ontological assessment proposal for architectural outputs of generative adversarial network
    (Emerald Publishing, 2023) Uzun, Can; Cangür, Raşit Eren
    Purpose: This study presents an ontological approach to assess the architectural outputs of generative adversarial networks. This paper aims to assess the performance of the generative adversarial network in representing building knowledge. Design/methodology/approach: The proposed ontological assessment consists of five steps. These are, respectively, creating an architectural data set, developing ontology for the architectural data set, training the You Only Look Once object detection with labels within the proposed ontology, training the StyleGAN algorithm with the images in the data set and finally, detecting the ontological labels and calculating the ontological relations of StyleGAN-generated pixel-based architectural images. The authors propose and calculate ontological identity and ontological inclusion metrics to assess the StyleGAN-generated ontological labels. This study uses 300 bay window images as an architectural data set for the ontological assessment experiments. Findings: The ontological assessment provides semantic-based queries on StyleGAN-generated architectural images by checking the validity of the building knowledge representation. Moreover, this ontological validity reveals the building element label-specific failure and success rates simultaneously. Originality/value: This study contributes to the assessment process of the generative adversarial networks through ontological validity checks rather than only conducting pixel-based similarity checks; semantic-based queries can introduce the GAN-generated, pixel-based building elements into the architecture, engineering and construction industry.