Bildiri Koleksiyonu
Bu koleksiyon için kalıcı URI
Güncel Gönderiler
Öğe Integrated spherical fuzzy - critic and spherical fuzzy – topsis method in prioritizing earthquake risks and planning: an overview in disaster management(2024) Tarakçı, Emin; Eti, Serkan; Can, EmineDisaster management is a critical field that plays a pivotal role in assessing and planning for earthquake risks to enhance community resilience. In this context, spherical fuzzy method has emerged as an effective tool for improving decision-making processes in complex and uncertain environments. In this study, SF-Critic fuzzy TOPSİS methods are used for the optimization of expert opinions in prioritizing major post-earthquake risks. The case study consists of three main and nine sub-criteria and five decision makers for prioritizing earthquake risks and necessary planning studies. In the evaluation of these criteria, various parameters ranging from urban landscape, road planning, industrial settlements, evacuation plans, energy and communication networks and infrastructure are used.Öğe A research on determining the degree of risk by using ResNet(ISRES Publishing, 2023) Tepe, Serap; Eti, SerkanRisk analysis, considered one of the most crucial building blocks of occupational safety with a multidisciplinary approach, is an area that requires quick solutions with proactive methods, has high operational costs, and a low error tolerance level. Utilizing image classification and enabling learning is the main goal of this study to achieve objective outcomes in risk analysis, reduce costs, increase efficiency, and ensure standardization. For the proposed paper, 325 labeled images were collected from the field, standardized to a resolution of 224x224, and a separate file was created for each category after labeling. Python's TensorFlow Keras libraries were used, and the model employed was a semi-learned ResNet model. While 501,765 parameters were learned, 23,587,712 parameters were trained from the data. The total parameter count was 24,089,477. Categorical cross-entropy was used as the loss function, Adam optimization algorithm was preferred for parameter optimization, and the Accuracy Rate metric was used to evaluate the model's quality. The learning success of the model reached 58% in 100 steps, and the maximum accuracy rate observed was determined to be 67%. Traditional risk analysis methods rely on statistical analysis of historical data to obtain results, while machine learning-based approaches allow for the evaluation of complex and multidimensional data. Machine learning-based image classification methods assist in effectively performing risk analysis in situations involving visual information. These techniques make valuable contributions to identifying and managing potential risks in different sectors. As research and applications in this field continue to grow in the future, the role of image classification in risk analysis will gain even more importance.
