Browsing by Author "Karadag, I"

Now showing 1 - 7 of 7
  • No Thumbnail Available
    Item
    Machine Learning for Pedestrian-Level Wind Comfort Analysis
    Gür, M; Karadag, I
    (1) Background: Artificial intelligence (AI) and machine learning (ML) techniques are being more widely employed in the field of wind engineering. Nevertheless, there is a scarcity of research on the comfort of pedestrians in terms of wind conditions with respect to building design, particularly in historic sites. (2) Objectives: This research aims to evaluate ML- and computational fluid dynamics (CFD)-based pedestrian wind comfort (PWC) analysis outputs using a novel method that relies on the sophisticated handling of image data. The goal is to propose a novel assessment method to enhance the efficiency of AI models over different urban scenarios. (3) Methodology: The stages include the analysis of climate data, CFD analysis with OpenFOAM, ML analysis using Autodesk Forma, and comparisons of the CFD and ML results using a novel image similarity assessment method based on the SSIM, MSE, and PSNR metrics. (4) Conclusions: This study effectively demonstrates the considerable potential of utilizing ML as a supplementary tool for evaluating PWC. It maintains a high degree of accuracy and precision, allowing for rapid and effective assessments. The methodology for precise comparison of two visual outputs in the absence of numerical data allows for more objective and pertinent comparisons, as it eliminates any potential distortions. (5) Recommendations: Additional research can explore the integration of ML models with climate data and different case studies, thus expanding the scope of wind comfort studies.
  • No Thumbnail Available
    Item
    Reciprocal style and information transfer between historical Istanbul Pervititch Maps and satellite views using machine learning
    Alaçam, S; Karadag, I; Güzelci, OZ
    Historical maps contain significant data on the cultural, social, and urban character of cities. However, most historical maps utilize specific notation methods that differ from those commonly used today and converting these maps to more recent formats can be highly labor-intensive. This study is intended to demonstrate how a machine learning (ML) technique can be used to transform old maps of Istanbul into spatial data that simulates modern satellite views (SVs) through a reciprocal map conversion framework. With this aim, the Istanbul Pervititch Maps (IPMs) made by Jacques Pervititch in 1922-1945 and current SVs were used to test and evaluate the proposed framework. The study consists of a style and information transfer in two stages: (i) from IPMs to SVs, and (ii) from SVs to IPMs using CycleGAN (a type of generative adversarial network). The initial results indicate that the proposed framework can transfer attributes such as green areas, construction techniques/ materials, and labels/tags.
  • No Thumbnail Available
    Item
    Numerical evaluation of pedestrian-level wind and indoor thermal comfort of a historical monument, Mugla, Turkey
    Gençer, F; Karadag, I
    Purpose The study aims to analyze both thermal and wind comfort conditions of a historical mosque's interior and outdoor spaces for the planning of further conservation decisions. Design/methodology/approach The method is composed of two steps. First, thermal comfort analyses are conducted via Design-Builder Software. The predicted mean vote (PMV) and predicted percentage of dissatisfied indices were calculated and evaluated using the ASHRAE 55-2010 standard. Thermal comfort conditions are analyzed with the proposed three operations. Second, wind comfort analyses are conducted via computational fluid dynamics (CFD) software. Outdoor thermal comfort conditions are predicted by air temperature, mean radiant temperature, wind speed and relative humidity. Findings The (PMV) in the harim was calculated as -1.83 (cool) which corresponds to a predicted percentage of dissatisfaction (PPD) equal to 68.54%. Thermal comfort was provided by daytime and continuous operations; however, intermittent operations did not provide thermal comfort. The wind velocities around the mosque are well below the 5 m/s limit value for standing defined by NEN 8100 wind nuisance standard. Moreover, the limit value of 2.5 m/s for sitting was also satisfied with more than 80% of the semi-enclosed area around the entrance of the mosque. Last comer's hall remains in a slight cold stress range, the rest of the areas have no thermal stress. Originality/value This two-stage study creates a base for further improvements to provide comfort conditions in a historical building without interfering with its original features.
  • No Thumbnail Available
    Item
    Machine learning for conservation of architectural heritage
    Karadag, I
    Purpose Accurate documentation of damaged or destroyed historical buildings to protect cultural heritage has been on the agenda of architecture for many years. In that sense, this study uses machine learning (ML) to predict missing/damaged parts of historical buildings within the scope of early ottoman tombs. Design/methodology/approach This study uses conditional generative adversarial networks (cGANs), a subset of ML to predict missing/damaged parts of historical buildings within the scope of early Ottoman tombs. This paper discusses that using GAN as a ML framework is an efficient method for estimating missing/damaged parts of historical buildings. The study uses the plan drawings of nearly 200 historical buildings, which were prepared one by one as a data set for the ML process. Findings The study contributes to the field by (1) generating a mixed methodological framework, (2) validating the effectiveness of the proposed framework in the restitution of historical buildings and (3) assessing the contextual dependency of the generated data. The paper provides insights into how ML can be used in the conservation of architectural heritage. It suggests that using a comprehensive data set in the process can be highly effective in getting successful results. The findings of the research will be a reference for new studies on the conservation of cultural heritage with ML and will make a significant contribution to the literature. Research limitations/implications A reliable outcome has been obtained concerning the interpretation of documented data and the generation of missing data at the macro level. The framework is remarkably effective when it comes to the identification and re-generation of missing architectural components like walls, domes, windows, doors, etc. on a macro level without details. On the other hand, the proposed methodological framework is not ready for advanced steps of restitution since every case of architectural heritage is very detailed and unique. Therefore, the proposed framework for re-generation of missing components of heritage buildings is limited by the basic geometrical form which means the architectural details of the mentioned components including ornaments, materials, identification of construction layers, etc. are not covered. Originality/value The generic literature as to ML models used in architecture mostly constitutes design exploration and floor plan/urban layout generation. More specific studies in the conservation of architectural heritage by using ML mostly focus on architectural component recognition over 3D point cloud data (1) or superficial damage detection of heritage buildings (2). However, we propose a mixed methodological framework for the interpretation of documented architectural data and the regeneration of missing parts of historical buildings. In addition, the methodology and the results of this paper constitute a guide for further research on ML and consequently contribute to architects in the early phases of restitution.
  • No Thumbnail Available
    Item
    EDU-AI: a twofold machine learning model to support classroom layout generation
    Karadag, I; Güzelci, OZ; Alaçam, S
    Purpose This study aims to present a twofold machine learning (ML) model, namely, EDU-AI, and its implementation in educational buildings. The specific focus is on classroom layout design, which is investigated regarding implementation of ML in the early phases of design. Design/methodology/approach This study introduces the framework of the EDU-AI, which adopts generative adversarial networks (GAN) architecture and Pix2Pix method. The processes of data collection, data set preparation, training, validation and evaluation for the proposed model are presented. The ML model is trained over two coupled data sets of classroom layouts extracted from a typical school project database of the Ministry of National Education of the Republic of Turkey and validated with foreign classroom boundaries. The generated classroom layouts are objectively evaluated through the structural similarity method (SSIM). Findings The implementation of EDU-AI generates classroom layouts despite the use of a small data set. Objective evaluations show that EDU-AI can provide satisfactory outputs for given classroom boundaries regardless of shape complexity (reserved for validation and newly synthesized). Originality/value EDU-AI specifically contributes to the automation of classroom layout generation using ML-based algorithms. EDU-AI's two-step framework enables the generation of zoning for any given classroom boundary and furnishing for the previously generated zone. EDU-AI can also be used in the early design phase of school projects in other countries. It can be adapted to the architectural typologies involving footprint, zoning and furnishing relations.
  • No Thumbnail Available
    Item
    Efficacy of subsequent treatments in patients with hormone-positive advanced breast cancer who had disease progression under CDK 4/6 inhibitor therapy (vol 23, 136, 2023)
    Karacin, C; Oksuzoglu, B; Demirci, A; Keskinkiliç, M; Baytemür, NK; Yilmaz, F; Selvi, O; Erdem, D; Avsar, E; Paksoy, N; Demir, N; Göksu, SS; Türker, S; Bayram, E; Çelebi, A; Yilmaz, H; Kuzu, ÖF; Kahraman, S; Gökmen, I; Sakin, A; Alkan, A; Nayir, E; Ugrakli, M; Acar, Ö; Ertürk, I; Demir, H; Aslan, F; Sönmez, Ö; Korkmaz, T; Celayir, ÖM; Karadag, I; Kayikçioglu, E; Sakalar, T; Öktem, IN; Eren, T; Erul, E; Mocan, EE; Kalkan, Z; Yildirim, N; Ergün, Y; Akagündüz, B; Karakaya, S; Kut, E; Teker, F; Demirel, BÇ; Karaboyun, K; Almuradova, E; Ünal, OÜ; Oyman, A; Isik, D; Okutur, K; Öztosun, B; Gülbagci, BB; Kalender, ME; Sahin, E; Seyyar, M; Özdemir, Ö; Selçukbiricik, F; Kanitez, M; Dede, I; Gümüs, M; Gökmen, E; Yaren, A; Menekse, S; Ebinç, S; Aksoy, S; Imamoglu, GI; Altinbas, M; Çetin, B; Uluç, BO; Er, Ö; Karadurmus, N; Erdogan, AP; Artaç, M; Tanriverdi, Ö; Çiçin, I; Sendur, MAN; Oktay, E; Bayoglu, IV; Paydas, S; Aydiner, A; Salim, DK; Geredeli, Ç; Yavuzsen, T; Dogan, M; Hacibekiroglu, I
  • No Thumbnail Available
    Item
    Efficacy of subsequent treatments in patients with hormone-positive advanced breast cancer who had disease progression under CDK 4/6 inhibitor therapy
    Karacin, C; Oksuzoglu, B; Demirci, A; Keskinkiliç, M; Baytemür, NK; Yilmaz, F; Selvi, O; Erdem, D; Avsar, E; Paksoy, N; Demir, N; Göksu, SS; Türker, S; Bayram, E; Çelebi, A; Yilmaz, H; Kuzu, ÖF; Kahraman, S; Gökmen, I; Sakin, A; Alkan, A; Nayir, E; Ugrakli, M; Acar, Ö; Ertürk, I; Demir, H; Aslan, F; Sönmez, Ö; Korkmaz, T; Celayir, ÖM; Karadag, I; Kayikçioglu, E; Sakalar, T; Öktem, IN; Eren, T; Urul, E; Mocan, EE; Kalkan, Z; Yildirim, N; Ergün, Y; Akagündüz, B; Karakaya, S; Kut, E; Teker, F; Demirel, BÇ; Karaboyun, K; Almuradova, E; Ünal, OÜ; Oyman, A; Isik, D; Okutur, K; Öztosun, B; Gülbagci, BB; Kalender, ME; Sahin, E; Seyyar, M; Özdemir, Ö; Selçukbiricik, F; Kanitez, M; Dede, I; Gümüs, M; Gökmen, E; Yaren, A; Menekse, S; Ebinç, S; Aksoy, S; Imamoglu, GI; Altinbas, M; Çetin, B; Uluç, BO; Er, Ö; Karadurmus, N; Erdogan, AP; Artaç, M; Tanriverdi, Ö; Çiçin, I; Sendur, MAN; Oktay, E; Bayoglu, IV; Paydas, S; Aydiner, A; Salim, DK; Geredeli, Ç; Yavuzsen, T; Dogan, M; Hacibekiroglu, I
    Background There is no standard treatment recommended at category 1 level in international guidelines for subsequent therapy after cyclin-dependent kinase 4/6 inhibitor (CDK4/6) based therapy. We aimed to evaluate which subsequent treatment oncologists prefer in patients with disease progression under CDKi. In addition, we aimed to show the effectiveness of systemic treatments after CDKi and whether there is a survival difference between hormonal treatments (monotherapy vs. mTOR-based). Methods A total of 609 patients from 53 centers were included in the study. Progression-free-survivals (PFS) of subsequent treatments (chemotherapy (CT, n:434) or endocrine therapy (ET, n:175)) after CDKi were calculated. Patients were evaluated in three groups as those who received CDKi in first-line (group A, n:202), second-line (group B, n: 153) and >= 3rd-line (group C, n: 254). PFS was compared according to the use of ET and CT. In addition, ET was compared as monotherapy versus everolimus-based combination therapy. Results The median duration of CDKi in the ET arms of Group A, B, and C was 17.0, 11.0, and 8.5 months in respectively; it was 9.0, 7.0, and 5.0 months in the CT arm. Median PFS after CDKi was 9.5 (5.0-14.0) months in the ET arm of group A, and 5.3 (3.9-6.8) months in the CT arm (p = 0.073). It was 6.7 (5.8-7.7) months in the ET arm of group B, and 5.7 (4.6-6.7) months in the CT arm (p = 0.311). It was 5.3 (2.5-8.0) months in the ET arm of group C and 4.0 (3.5-4.6) months in the CT arm (p = 0.434). Patients who received ET after CDKi were compared as those who received everolimus-based combination therapy versus those who received monotherapy ET: the median PFS in group A, B, and C was 11.0 vs. 5.9 (p = 0.047), 6.7 vs. 5.0 (p = 0.164), 6.7 vs. 3.9 (p = 0.763) months. Conclusion Physicians preferred CT rather than ET in patients with early progression under CDKi. It has been shown that subsequent ET after CDKi can be as effective as CT. It was also observed that better PFS could be achieved with the subsequent everolimus-based treatments after first-line CDKi compared to monotherapy ET.