http://dspace.beu.edu.tr:8080/xmlui/handle/123456789/13957 2026-04-23T06:58:29Z http://dspace.beu.edu.tr:8080/xmlui/handle/123456789/14916 3BResNet: A Novel Residual Block-Based ResNet Model Approach for COVID19 Detection KILINÇ, Ekrem Eşref; AKA, Fahrettin; METLEK, Sedat In recent years, upper respiratory tract infections that have affected the whole world have caused the death of millions of people. It is predicted that similar infections may occur in the coming years. Therefore, it is necessary to develop methods that can be used widely, especially during epidemic periods. The study developed a decision support system for use in upper respiratory tract infections. At this stage, first, the ResNet models in the literature were examined and an application was developed on the SARS-CoV-2 Ct dataset. Next stage, the block structure in the ResNet models in the literature was changed, the number of layers was reduced, and a new model was proposed that provides higher success with fewer parameters. With the proposed model, the values 0.97, 0.97, 0.94, and 0.98 were achieved for accuracy, F1 score, precision and sensitivity on the SARS-CoV-2 Ct dataset, respectively. When the obtained values are compared to state of the art methods in the literature, it has been determined that they are at a competitive level with much fewer parameters. Hardware-related problems encountered in the training of ResNet models at low hardware levels were solved with the proposed model, resulting in a higher success rate. Furthermore, the proposed model can be widely used in different decision support systems that are urgently needed in adverse conditions such as pandemics due to its lightweight structure and high-performance results. As a result of the study, a new model that can provide higher performance with much lower layer structure than existing ResNet models has been introduced into the literature with the proposed model. 2023-01-01T00:00:00Z http://dspace.beu.edu.tr:8080/xmlui/handle/123456789/14915 Human Energy Expenditure in High-Level Order Picking BİNİCİ, Murat; YENİSEY, Mehmet Mutlu Order picking is one of the most significant components of the warehouse management. More than 50% of the cost incurred in warehouses is due to the order picking process. Although this process has mostly been considered within the framework of economic objectives, in recent years the ergonomic perspective has become increasingly visible. Order picking studies regarding ergonomic objectives have mostly focused on low-level order picking systems, but the human factor has been ignored in high-level order picking. In order to fill this gap, this study focuses on the order picking process of a single block high-level warehouse with a special focus on human factor. For this purpose, a capacity-constrained mathematical model based on order batching and routing for the minimization of human energy expenditure is proposed. In this three-dimensional (3D) warehouse system, the distances and travel times between locations were first determined using Manhattan distance-based Tchebychev formulas in order to calculate the human energy expenditure between order locations. Then, human energy matrices between order locations were created using human energy calculation formulas based on time and item weight. These matrices, which were created for three different randomly generated sample data sets, were used in the mathematical model solution and the optimum batches and routes were determined. In order to compare the results, Firstcome First-serve (FCFS) batching and S-shaped routing, which are simple and common batching and routing methods used in practice, were applied for the sample problem data sets and it was observed that the mathematical model gave better results. 2023-01-01T00:00:00Z http://dspace.beu.edu.tr:8080/xmlui/handle/123456789/14914 Studies on the Ennominae Fauna and Taxonomy of the Dağlıca (Geometridae, Lepidoptera)* UÇAK, Hanife; KEMAL, Muhabbet Ennominae is an important group in the Geometridae family that contains problematic species with very similar external morphological characters. In this study, Ennominae species collected from Yüksekova Dağlıca town of Hakkari Province between April and September 2017 were evaluated from a faunistic and taxonomic perspective. 28 species were identified in the study. Charissa onustaria, C. subtaurica and Crocallis tusciaria species were identified for the first time from Hakkari Province. C. loebeli, Neognopharmia cataleucaria, and Ramitia kufrana were detected in the region are also important endemic taxa for the Turkish fauna. Rhoptria mardinata and Eumera hoferi, known only in Türkiye and Iran, are other rare species found in the region. R. mardinata was presented with photographs of male genitalia for the first time. Morphological and taxonomic aspects of the species under the genera Dicrognophos, Gnopharmia, Crocallis, Bellachima, Charissa, Synopsia and Nychiodes are discussed 2023-01-01T00:00:00Z http://dspace.beu.edu.tr:8080/xmlui/handle/123456789/14913 Determination of Energy Absorption Capabilities of Shear Thickening Fluid Impregnated Aramid Fiber Fabrics for Ballistic Applications AYTEN, Ali İmran The low-velocity impact behavior of shear thickening fluid (STF) impregnated aramid fabric having different numbers of layers was investigated throughout this study to determine a relationship between the number of layers and perforation energy. Firstly, STF solutions, including polyethylene glycol, silica nanoparticles, and ethanol, were prepared by mixing with a homogenizer. Solutions containing 5%, 10%, and 20% silica nanoparticles by weight were prepared, and rheological analysis was performed. 20% weight fraction solution showed the optimum thickening behavior among the three solutions. After thickening behavior and the critical shear rate were determined from rheological analysis, the solution was impregnated into the aramid fabric. Then, specimens with different numbers of layers, from 1 to 8, were prepared for low-velocity impact experiments. A drop-weight impact test was applied at different energy levels from 20 J to 240 J, and perforation energy was determined. Finally, an equation that has a form of power function was fitted to use it for potential energy absorption applications such as ballistic impact. 2023-01-01T00:00:00Z