Mühendislik Fakültesi / Faculty of Engineering

Permanent URI for this collectionhttps://hdl.handle.net/11727/1401

Browse

Filters

Settings

Search Results

Now showing 1 - 10 of 742
  • No Thumbnail Available
    Item
    A Game-Changing Equation During The Etching Of Tuning Forks And Its Verification Through Experiments
    (Başkent Üniversitesi Mühendislik Fakültesi, 2024-08-05) Erbas, Kadir Can; Erdogan, Mebrure; Serdaroglu, Dilek cokeliler; Kocum, Ismail Cengiz
    Quartz tuning fork (QTF) sensors, characterized by simplicity, low cost, and high-quality factor, represent a significant subset. This study delves into the etching dynamics of QTF systems, crucial for sensor applications like quartz crystal microbalance (QCM). Both theoretical and experimental investigations into QTF etching, via methods like electro-etching for large-scale tuning forks (TF) and low-pressure radio frequency (RF) plasma treatment for QTFs, have been conducted. Surprisingly, post-etching measurements reveal a lower vibrational frequency for both large-scale TFs and QTFs compared to their bare counterparts, unlike QCM sensors. A novel formula correlating this frequency reduction to mass loss has been proposed and validated through lots of experiments. Notably, longitudinal homogeneity emerges as a pivotal factor influencing the accuracy of the proposed formula. In summary, the novel mathematical framework presented herein is poised to catalyze the widespread adoption of low-cost QTFs as mass-sensitive biosensors, marking a significant advancement in the field.
  • No Thumbnail Available
    Item
    Accelerated Evaluation of Blocking Flowshop Scheduling With Total Flow Time Criteria Using A Generalized Critical Machine-Based Approach
    (Başkent Üniversitesi Mühendislik Fakültesi, 2024-07-10) Han, Yuyan; Wang, Yuting; Pan, Quan-ke; Wang, Ling; Tasgetiren, Fatih
    Despite the considerable advances in the research of the blocking flowshop scheduling problem (BFSP), several unresolved challenges persist. Algorithmic complexity presents hurdles. Although the insertion-based method is considered to generate superior solutions, its high computational demand diminishes the efficiency of algorithms, especially within large-scale sequences. The existing accelerated evaluation methods cannot utilize the existing information to quickly calculate the total flow time or the total tardiness time of the changed sequence after the job insertion, but recalculates it from scratch. This does not significantly reduce computational effort and needs to be further improved. In this paper, we delve into the intrinsic features of these challenges, proposing a generalized accelerated critical machine-based evaluation tailored for the total flow time and tardiness criteria of the BFSP with and without sequence-dependent setup times. First, we propose three theorems, one corollary, and their proofs based on the critical machine. Second, we propose the accelerated evaluation procedure based on these theorems to calculate the objectives related to the total flow time. Third, we also extend the proposed accelerated evaluation method to the BFSP with sequence-dependent setup times, aiming to significantly reduce the time complexity. Finally, we conduct four experiments on five well-known benchmarks (a total of 3540 test instances). Through statistical analysis, it becomes evident that our computational efforts have significantly decreased in computing both the total flow time and the total tardiness time. This performance enhancement is superior to the effectiveness of existing acceleration techniques.
  • No Thumbnail Available
    Item
    Automated Detection of type 1 ROP, type 2 ROP and A-ROP Based on Deep Learning
    (Başkent Üniversitesi Mühendislik Fakültesi, 2024-07-02) Yenice, Esay Kiran; Kara, Caner; Erdas, Cagatay Berke
    PurposeTo provide automatic detection of Type 1 retinopathy of prematurity (ROP), Type 2 ROP, and A-ROP by deep learning-based analysis of fundus images obtained by clinical examination using convolutional neural networks.Material and methodsA total of 634 fundus images of 317 premature infants born at 23-34 weeks of gestation were evaluated. After image pre-processing, we obtained a rectangular region (ROI). RegNetY002 was used for algorithm training, and stratified 10-fold cross-validation was applied during training to evaluate and standardize our model. The model's performance was reported as accuracy and specificity and described by the receiver operating characteristic (ROC) curve and area under the curve (AUC).ResultsThe model achieved 0.98 accuracy and 0.98 specificity in detecting Type 2 ROP versus Type 1 ROP and A-ROP. On the other hand, as a result of the analysis of ROI regions, the model achieved 0.90 accuracy and 0.95 specificity in detecting Stage 2 ROP versus Stage 3 ROP and 0.91 accuracy and 0.92 specificity in detecting A-ROP versus Type 1 ROP. The AUC scores were 0.98 for Type 2 ROP versus Type 1 ROP and A-ROP, 0.85 for Stage 2 ROP versus Stage 3 ROP, and 0.91 for A-ROP versus Type 1 ROP.ConclusionOur study demonstrated that ROP classification by DL-based analysis of fundus images can be distinguished with high accuracy and specificity. Integrating DL-based artificial intelligence algorithms into clinical practice may reduce the workload of ophthalmologists in the future and provide support in decision-making in the management of ROP.
  • No Thumbnail Available
    Item
    Approximation Theorems Via Pp-statistical Convergence on Weighted Spaces
    (Başkent Üniversitesi Mühendislik Fakültesi, 2024-07-08) Yildiz, Sevda; Bayram, Nilay Sahin
    In this paper, we obtain some Korovkin type approximation theorems for double sequences of positive linear operators on two-dimensional weighted spaces via statistical type convergence method with respect to power series method. Additionally, we calculate the rate of convergence. As an application, we provide an approximation using the generalization of Gadjiev-Ibragimov operators for P-p-statistical convergence. Our results are meaningful and stronger than those previously given for two-dimensional weighted spaces.
  • No Thumbnail Available
    Item
    Asymptotic Derivation of Consistent thin Shell Equations for a Fluid-Loaded Elastic Annulus
    (Başkent Üniversitesi Mühendislik Fakültesi, 2024-07-08) Yucel, H.; Kaplunov, J.; Ege, N.; Erbas, B.
    The classical time-harmonic plane strain problem for a fluid-loaded cylindrical elastic shell is revisited. The results of the low-frequency asymptotic analysis, including explicit formulae for eigenfrequencies, are presented. A refined version of the semi-membrane shell theory is formulated. It is shown that the shell inertia does not affect significantly the lowest eigenfrequencies. It is also demonstrated that the ring stress component has a parabolic linear variation.
  • No Thumbnail Available
    Item
    Improving The Performance of a MEMS-IMU System Based On A False State-Space Model By Using A Fading Factor Adaptive Kalman Filter
    (Başkent Üniversitesi Mühendislik Fakültesi, 2024-06-29) Akbas, Eren Mehmet; Cifdaloz, Oguzhan; Ucuncu, Murat
    In this study, we introduce a novel algorithm, the low error rate adaptive fading Kalman filter (LERAFKF), designed to predict system states in the presence of uncertainty in both the system matrix and the model. The purpose of developing the LERAFKF is to address challenges arising from measurement difficulties, system parameter uncertainties, and state-space model inaccuracies. Several studies have utilized the Kalman filter (KF) and extended Kalman filter (EKF) algorithms to handle uncertainties in system parameters, corrupted measurements with unknown covariances, and incorrectly defined system modeling. Our work distinguishes itself by proposing a new approach that achieves lower error and deviation rates by combining the current Kalman estimation algorithm and the fading factor adaptive filter. To achieve this goal, we transformed the KF into an adaptive KF by introducing a forgetting factor, and the algorithm was subsequently reconfigured to calculate an optimized forgetting factor. In this study, we conducted simulations and measurements using both linear and nonlinear systems. The linear system represents the motion of an object, and the simulation involved measurements from the inertial navigation system (INS) sensor, specifically the Pololu IMU01b three-axis inertial measurement unit (IMU) sensor. We employed the SDI33 system with 9 degrees of freedom (DoF) mounted on a three-axis rotary table for the nonlinear system. This system simulates a missile as a 4th-order nonlinear system. Our findings demonstrate that the proposed LERAFKF filter outperforms KF and EKF in estimating system states, particularly in measurement-related error scenarios. Mean square error analysis further confirmed that LERAFKF exhibited the lowest error values, showcasing superior performance over KF and EKF in linear and nonlinear systems.
  • No Thumbnail Available
    Item
    Detection and Characterization of Cusp Singularities
    (Başkent Üniversitesi Mühendislik Fakültesi, 2024-06-25) Buyuktas, Selin; Karacor, Deniz
    Studies on nonlinear analysis of system dynamics have increased in recent years. Since most systems that exist in nature have complex dynamics and therefore exhibit nonlinear behavior; there are various methods and theories developed in this context. Self-similar functions are mathematical functions exhibiting self-similar and scale-invariant behaviors performing fractal structures. Singularities are the basis for producing the self-similar behavior of these functions. Singularity analysis is mainly carried out by using wavelet transform (WT). The cusp singularities are non-oscillating singularities which are characterized by their singularity strength. However, the representation and behavior of this type of singularity differs depending on the sign of the exponent, known as the singularity strength. The cusp singularity functions with negative exponent show irregular behavior progressively different than positively valued functions since the value of the function is undefined at that particular singular point. It is commonly accepted that the singularity strength is studied as Holder exponent of the cusp function, but by definition, the value of this exponent cannot take negative values. We present a new method to estimate the singularity strength of cusp singularities with negative exponent. The developed method is based on analyzing and redistributing the amplitudes of a cusp function with negative exponent by taking the WT. The redistribution of amplitudes over time is achieved by applying curve fitting process to frequency values of the analyzing function.
  • No Thumbnail Available
    Item
    Q-Learning Guided Algorithms For Bi-Criteria Minimization Of Total Flow Time And Makespan In No-Wait Permutation Flowshops
    (Başkent Üniversitesi Mühendislik Fakültesi, 2024-07-04) Yuksel, Damla; Kandiller, Levent; Tasgetiren, Mehmet Fatih
    Combining Deep Reinforcement Learning and meta-heuristic techniques represents a new research direction for enhancing the search capabilities of meta-heuristic methods in the context of production scheduling. Q-learning is a prominent reinforcement learning in which its utilization aims to direct the selection of actions, thus preventing the necessity for a random exploration in the iterative process of the metaheuristics. In this study, we provide Q-learning guided algorithms for the Bi-Criteria No-Wait Flowshop Scheduling Problem (NWFSP). The problem is treated as a bi-criteria combinatorial optimization problem where total flow time and makespan are optimized simultaneously. Firstly, a deterministic mixed-integer linear programming (MILP) model is provided. Then, Q-learning guided algorithms are developed: Bi-Criteria Iterated Greedy Algorithm with Q-Learning (BCIGQL). Bi-Criteria Block Insertion Heuristic Algorithm with Q-Learning (BC-BIHQL). Moreover, the performance of the proposed Q-learning guided algorithms is compared over a collection of Bi-Criteria Genetic Local Search Algorithms (BC-GLS), Bi-Criteria Iterated Greedy Algorithm (BC-IG), Bi-Criteria Iterated Greedy Algorithm with a Local Search (BC-IGALL) and Bi-Criteria Variable Block Insertion Heuristic Algorithm (BC-VBIH). The complete computational experiment, performed on 480 problem instances of Vallada et al. (2015), which is known as the VRF benchmark set, indicates that the BC-BIHQL and the BC-IGQL algorithms outperform the BC-GLS, BC-IG, BCIGALL, and BC-VBIH algorithms in comparative performance metrics. More specifically, the proposed BC-BIHQL and BC-IGQL algorithms can yield more non-dominated bi-criteria solutions with the most substantial competitiveness than the remaining algorithms. At the same time, both are competitive with each other on the benchmark problems. Moreover, the BC-IGQL algorithm dominates almost 97% and 99% of the solutions reached by the BC-IG, BC-IGALL, and BC-VBIH algorithms in small and large datasets. Similarly, The BC-BIHQL algorithm dominates almost 98% and 99% of the solutions reached by the BC-IG, BC-IGALL, and BC-VBIH algorithms in small and large datasets, respectively. This means that, among all the features that have been compared, the Qlearning-guided algorithms demonstrate the highest level of competitiveness. The outcomes of this study encourage us to discover many more bi-criteria NWFSPs to reveal the trade-off between other conflicting objectives, such as makespan & the number of early jobs, to overcome various industries' problems.
  • No Thumbnail Available
    Item
    Deep Generative Models İn Medical İmaging : A Literature Review
    (Başkent Üniversitesi Mühendislik Fakültesi, 2024-06-16) Sener, Begum
    Deep 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.
  • No Thumbnail Available
    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, Bulent
    This 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.