Mühendislik Fakültesi / Faculty of Engineering
Permanent URI for this collectionhttps://hdl.handle.net/11727/1401
Browse
734 results
Search Results
Item Deep Generative Models İn Medical İmaging : A Literature Review(Başkent Üniversitesi Mühendislik Fakültesi, 2024-06-16) Sener, BegumDeep learning has been used extensively in recent years in numerous studies across many disciplines, including medical imaging. GANs (Generative Adversarial Networks) have started to be widely used in the medical field due to their ability to generate realistic images. Recent research has concentrated on three different deep generative models for improving medical images, and a review of deep learning architectures for data augmentation has been done. In this article, other generative models are emphasized, given the dominance of GANs in the field. Studies have conducted a literature review comparing different deep generative models for medical image data augmentation, without focusing solely on GANs or traditional data augmentation methods. In contrast to variational autoencoders, generative adversarial networks (GANs) are the generative model that is most frequently employed for enhancing medical image data. Recent studies have shown that diffusion models have received more attention in recent years compared to variational autoencoders and GANs for medical image data augmentation. This trend is thought to be related to the fact that many GAN-related research directions have previously been investigated, making it more challenging to advance these architectures' current applications.Item Autonomous Landing Of A Quadrotor On A Moving Platform Using Motion Capture System(Başkent Üniversitesi Mühendislik Fakültesi, 2024-06-08) Qassab, Ayman; Khan, Muhammad Umer; Irfanoglu, BulentThis paper investigates the challenging problem of the autonomous landing of a quadrotor on a moving platform in a non-cooperative environment. The limited sensing ability of quadrotors often hampers their utilization for autonomous landing, especially in GPS-denied areas. The performance of motion capture systems (MCSs) in many application areas is the motivation to utilize them for the autonomous take-off and landing of the quadrotor in this research. An autonomous closed-loop vision-based navigation, tracking, and control system is proposed for quadrotors to perform landing based upon Model Predictive Control (MPC) by utilizing multi-objective functions. The entire process is posed as a constrained tracking problem to minimize energy consumption and ensure smooth maneuvers. The proposed approach is fully autonomous from take-off to landing; whereas, the movements of the landing platform are pre-defined but still unknown to the quadrotor. The landing performance of the quadrotor is tested and evaluated for three different movement patterns: static, square-shaped, and circular-shaped. Through experimental results, the pose error between the quadrotor and the platform is measured and found to be less than 30 cm. Introducing a holistic vision system for quadrotor navigation, tracking, and landing on stationary/moving platforms. Proposing an energy-efficient, smooth, and stable MPC controller validated by Lyapunov analysis. Validating the adept tracking and safe landings of the quadrotor on stationary/moving platforms through three diverse experiments.Item Unleashing the Potential of a Hybrid 3D Hydrodynamic Monte Carlo Risk Model for Maritime Structures' Design in the Imminent Climate Change Era(Başkent Üniversitesi Mühendislik Fakültesi, 2024-07-04) Ugurlu, Arif; Balas, Egemen Ander; Balas, Can Elmar; Akbas, Sami OguzhanSubmarine pipelines have become integral for transporting resources and drinking water across large bodies. Therefore, ensuring the stability and reliability of these submarine pipelines is crucial. Incorporating climate change impacts into the design of marine structures is paramount to assure their lifetime safety and serviceability. Deterministic design methods may not fully consider the uncertainties and risks related to climate change compared to risk-based design models. The latter approach considers the future risks and uncertainties linked to climate and environmental changes, thus ensuring infrastructure sustainability. This study pioneers a Hybrid 3D Hydrodynamic Monte Carlo Simulation (HMCS) Model to improve the reliability-based design of submarine pipelines, incorporating the effects of climate change. Current design approaches may follow deterministic methods, which may not systematically account for climate change's comprehensive uncertainties and risks. Similarly, traditional design codes often follow a deterministic approach, lacking in the comprehensive integration of dynamic environmental factors such as wind, waves, currents, and geotechnical conditions, and may not adequately handle the uncertainties, including the long-term effects of climate change. Nowadays, most countries are developing new design codes to modify the risk levels for climate change's effects, such as sea-level rises, changes in precipitation, or changes in the frequency/intensity of winds/storms/waves in coastal and marine designs. Our model may help these efforts by integrating a comprehensive risk-based approach, utilizing a 3D hydrodynamic model to correlate diverse environmental factors through Monte Carlo Simulations (MCS). The hybrid model can promise the sustainability of marine infrastructure by adapting to future environmental changes and uncertainties. Including such advanced methodologies in the design, codes are encouraged to reinforce the resilience of maritime structures in the climate change era. The present design codes should inevitably be reviewed according to climate change effects, and the hybrid risk-based design model proposed in this research should be included in codes to ensure the reliability of maritime structures. The HMCS model represents a significant advancement over existing risk models by incorporating comprehensive environmental factors, utilizing advanced simulation techniques, and explicitly addressing the impacts of climate change. This innovative approach ensures the development of more resilient and sustainable maritime infrastructure capable of withstanding future environmental uncertainties.Item Involution Generators Of The Big Mapping Class Group(Başkent Üniversitesi Mühendislik Fakültesi, 2024-06-09) Altunoz, Tulin; Pamuk, Mehmetcik; Yildiz, OguzLet S = S(n) denote the infinite-type surface with n ends, n is an element of N, accumulated by genus. For n >= 6, we show that the mapping class group of S is topologically generated by five involutions. When n >= 3, it is topologically generated by six involutions.Item Joshi-Malafarina-Narayan Singularity In Weak Magnetic Field(Başkent Üniversitesi Mühendislik Fakültesi, 2024-06-07) Azreg-Ainou, Mustapha; Acharya, Kauntey; Joshi, Pankaj S.The importance and significance of magnetic fields in the astrophysical scenario is well known. Many domains of astrophysical black hole physics such as polarized shadow image, high energy emitting processes and jet formation are dependent on the behavior of the magnetic fields in the vicinity of the compact objects. In light of this, we determine the master equation and master differential equation that determine the spatial behavior of the magnetic field inside a matter distribution or vacuum region, of general spherically symmetric metric, which is immersed in a test magnetic field. We also investigate here the case of JMN-1 singularity immersed in a uniform weak magnetic field and determine the behavior of magnetic fields by defining electromagnetic four potential vector. We find that the tangential component of the magnetic field is discontinuous at the matching surface of the JMN-1 singularity with the external Schwarzschild metric, resulting in surface currents. We define the covariant expression of surface current density in this scenario. We also analyze the behavior of center-of-mass energy of two oppositely charged particles in the geometry of the magnetized JMN-1 singularity. We briefly discuss the possible scenarios which would possess a discontinuous magnetic field and implications of the same and future possibilities in the realm of astrophysics are indicated.Item A Plasma Arc-Based Electromechanical System Designed for Microchannel Processing(Başkent Üniversitesi Mühendislik Fakültesi, 2024-05-31) Akin, Fevzi; Ersoy, Ece; Idil, Deniz; Ozsimitci, Melih; Serdaroglu, Dilek Cokeliler; Ic, Yusuf Tansel; Atalay, Kumru Didem; Kocum, Cengiz; Okat, KemalPlasma technology is based on a simple physical principle. When more energy enters the gas, it ionizes and becomes the fourth state of matter, the energy-dense plasma. The studies carried out within the scope of this study were designed to create microchannels on lamellar glass using an improved redesign of the current plasma arc device, which is the main subject of the paper. The created microchannel is examined at the microscale. Experimental analysis was conducted considering the effect of plasma on the effect of microchannel quality. We performed an experimental design study to determine the optimal parameter levels for improving microchannel quality. The predicted results have been validated with the experimental results. An experimental design study provides useful results, such as information about the distance between the probes, pulse duration, and material temperature, which enhances the channel dimensions. The improved device can be utilized effectively to establish microchannel processing in practice.Item Computer-Aided Colorectal Cancer Diagnosis: Ai-Driven Image Segmentation And Classification(Başkent Üniversitesi Mühendislik Fakültesi, 2024-05-31) Erdas, Cagatay BerkeColorectal cancer is an enormous health concern since it is among the most lethal types of malignancy. The manual examination has its limitations, including subjectivity and data overload. To overcome these challenges, computer -aided diagnostic systems focusing on image segmentation and abnormality classi fi cation have been developed. This study presents a two -stage approach for the automatic detection of fi ve types of colorectal abnormalities in addition to a control group: polyp, low-grade intraepithelial neoplasia, high-grade intraepithelial neoplasia, serrated adenoma, adenocarcinoma. In the fi rst stage, UNet3+ was used for image segmentation to locate the anomalies, while in the second stage, the Cross -Attention Multi -Scale Vision Transformer deep learning model was used to predict the type of anomaly after highlighting the anomaly on the raw images. In anomaly segmentation, UNet3+ achieved values of 0.9872, 0.9422, 0.9832, and 0.9560 for Dice Coef fi cient, Jaccard Index, Sensitivity, Speci fi city respectively. In anomaly detection, the Cross -Attention Multi -Scale Vision Transformer model attained a classi fi cation performance of 0.9340, 0.9037, 0.9446, 0.8723, 0.9102, 0.9849 for accuracy, F1 score, precision, recall, Matthews correlation coef fi cient, and speci fi city, respectively. The proposed approach proves its capacity to alleviate the overwhelm of pathologists and enhance the accuracy of colorectal cancer diagnosis by achieving high performance in both the identi fi cation of anomalies and the segmentation of regions.Item Investigation of the Additional Powder Effect on the Strength of Joined Aluminum Alloy Plates in Friction Stir Welding Using the Topsis-Game Theory Model(Başkent Üniversitesi Mühendislik Fakültesi, 2024-05-03) Yurdakul, Mustafa; Ulke, Ibrahim; Tansel, Yusuf I. C.Friction stir welding (FSW) is a process that can join many materials by causing minimal internal stress without the need for a direct electric current, contrary to traditional welding methods. The effects of SiC and Al2O3 reinforcing powders on the joining of AA6061-T6 and AA7075-T6 plates, which are difficult to join with conventional welding methods by FSW, are investigated in this study. The metallurgical properties of the combined samples are examined in terms of strength characteristics to investigate the effects of the reinforcement powder. In addition, elemental analysis is carried out for the mixing behavior of the powders. Finally, we used the TOPSIS method to select the most appropriate powder types to improve welding quality. Furthermore, a game theory application is presented to determine which powder type is suitable considering the joined aluminum plate's strength expectations.Item Comprehensive Data Analysis Of White Blood Cells With Classification And Segmentation By Using Deep Learning Approaches(Başkent Üniversitesi Mühendislik Fakültesi, 2024-04-05) Ozcan, Seyma Nur; Uyar, Tansel; Karayegen, GokayDeep learning approaches have frequently been used in the classification and segmentation of human peripheral blood cells. The common feature of previous studies was that they used more than one dataset, but used them separately. No study has been found that combines more than two datasets to use together. In classification, five types of white blood cells were identified by using a mixture of four different datasets. In segmentation, four types of white blood cells were determined, and three different neural networks, including CNN (Convolutional Neural Network), UNet and SegNet, were applied. The classification results of the presented study were compared with those of related studies. The balanced accuracy was 98.03%, and the test accuracy of the train-independent dataset was determined to be 97.27%. For segmentation, accuracy rates of 98.9% for train-dependent dataset and 92.82% for train-independent dataset for the proposed CNN were obtained in both nucleus and cytoplasm detection. In the presented study, the proposed method showed that it could detect white blood cells from a train-independent dataset with high accuracy. Additionally, it is promising as a diagnostic tool that can be used in the clinical field, with successful results in classification and segmentation.Item Examination of Speech Analysis to Predict Suicidal Behavior in Depression(Başkent Üniversitesi Mühendislik Fakültesi, 2024-10-12) Yunden, S.; Ak, M.; Sert, M.; Gica, S.; Cinar, O.; Acar, Y. A.