Middle East Technical University Research Information System
Not a member yet
104897 research outputs found
Sort by
Performance evaluation of a scramjet engine utilizing varied cavity aft wall divergence with parallel injection in a reacting flow field
No full textThe effect of implications of the dual cavity with aft wall divergence in a parallel injection reacting flow has been numerically investigated. This research intends to emphasize the behaviour of the supersonic flow under varying divergence angles of the cavity aft wall. A two-dimensional Reynolds-Averaged Navier-Stokes (RANS) equation and an SST k-ω turbulence model with a single-step chemical reaction for hydrogen-air are utilized for the simulation. Followed by the strut injector, the cavities are positioned symmetrically inside the combustor. The bottom cavity aft wall divergence varies, whereas the top wall is mounted with a rectangular cavity. The performance of cavity locations is compared with the baseline DLR model. From the evaluation of numerical outcomes along with different cavity configurations, it has been noted that the 15-degree cavity divergence angle enhances the recirculation zone which leads to improved mixing performance. Also, the cavity improves the combustion stability by increasing the flow residence time. From this numerical analysis, it is associated that an almost 20 % reduction in combustor length is achieved, however, an 18 % rise in the pressure loss is noted because of emanating shock waves from the cavity edges
Brain Tumor Classification using Deep Learning: Robustness Against Adversarial Attacks and Defense Strategies
No full textIn this paper, we propose a custom convolutional neural network (C-CNN) and a ResNet-50 based transfer learning model to classify three different types of brain tumors: meningioma, glioma, and pituitary-using the open-source brain tumor dataset Figshare. We assess the robustness of both C-CNN and ResNet-50 by applying six different types of adversarial attacks that simulate real-world challenges encountered in MRI scans of brain tumors: Fast Gradient Sign Method (FGSM), Motion Blur, Partial Occlusion, JPEG Compression Artifacts, Gaussian Noise Artifacts, and Adversarial Boundary Noise. To improve the model's robustness against these adversarial attacks, we designed a defensive strategy which is known as Adversarial attack-driven data augmentation, where we integrate adversarially attacked images into our dataset and evaluate the model on test and validation datasets. Our C-CNN and ResNet-50 obtained the test accuracy of 94.42% and 98.03%, respectively on a clean dataset with a data split of 15% for the test, 15% for the validation, and 70% for the training dataset. After implementing the defensive strategy for C-CNN and ResNet-50, we evaluated both models using two different approaches. The first approach includes random distribution of attacked and clean images among the test, validation, and training sets, we achieved the test accuracies for C-CNN and ResNet-50 of 97.15% and 98.3% respectively. The second approach includes the distribution with a fixed 16:84 ratio of attacked to clean images across all three test, validation, and training datasets, accuracies of both models dropped to 95.82% and 97.63%, respectively
Comparative energy performance analysis of electrochromic and conventional glazing types by varied facade orientations of office buildings in different climates
No full textNitel Araştırmada Öznel Deneyimin Anlaşılması: Yorumlayıcı Fenomenolojik Analiz Çalışmaları
No full texthttps://books.akademisyen.net/index.php/akya/catalog/download/3722/11136/81747?inline=1</p
TÜBİTAK 4004 Doğa Eğitimi ve Bilim Okulları Projesi Kapsamında Ortaokul Öğrencilerinin Kompostlama Temasını Kullanarak Kodlamaya Yönelik Bilgi ve Farkındalıklarının İncelenmesi
No full textExploring the use of natural polysaccharide based aerogels for the drug delivery of biotechnological drugs
No full text
