Mühendislik Fakültesi / Faculty of Engineering
Permanent URI for this collectionhttps://hdl.handle.net/11727/1401
Browse
17 results
Search Results
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 A Pilot Study on Comparison of Teaching Workloads of Academicians Based on Working Periods During and Before the COVID-19 Pandemic(Başkent Üniversitesi Mühendislik Fakültesi, 2025-01-25) Yorulmaz, Muhammed; Can, Gulin Feryal; Toktas, PelinThe COVID-19 pandemic has had a profound impact on society, greatly changing the structure of social and working lives. Educational institutions, especially in higher education, were forced to suspend face-to-face education and switch to distance education. This change inevitably affected the working styles and workloads of academics. This study aims to explore the effects of the COVID-19 pandemic on academic teaching workloads by examining transaction data for a one-year period before and during the pandemic. The data were obtained from the system logs of a learning management system platform, which was used extensively during the pre-pandemic and pandemic periods, and were analyzed in terms of transaction density, day, and time of transactions. The findings from the pre-pandemic period showed that the academic workload was higher on weekdays than on weekends. However, with the transition to distance education during the pandemic, the difference between weekday and weekend workloads diminished significantly. Additionally, the working hours shifted during the pandemic by approximately one hour to later hours in the day.Item A Robust Aluminum Material Selection Process in the Aviation Industry: A Linear Discrete System Stability Test Perspective for Fuzzy Multicriteria Decision-Making(Başkent Üniversitesi Mühendislik Fakültesi, 2024-04-10) Ic, Yusuf Tansel; Hamzaoglu, Burak Meric; Yurdakul, MustafaAluminum parts are used in the aviation industry because of the need for light. However, in addition to lightness, critical parts that must have high strength properties have also been developed. The corrosion resistance, resistance to high temperatures, and workability were investigated in this case. It becomes difficult to choose among many aluminum materials that can be alternatives to each other when these features are included. The developed approach, which considers many of the features listed above and ultimately recommends to the user the most suitable aluminum material for the relevant critical part, will be used in overcoming the difficulties in this process. A material selection model is proposed in this paper for this purpose, and the decision-making model is demonstrated with examples from the aviation industry. Therefore, the developed model, which will enable the selection of the most suitable materials among alternative materials, especially for critical parts in the aviation industry, will guide professionals working in this field. For this purpose, the fuzzy TOPSIS method is used in the study, and suitable alternatives are determined. Finally, a robustness analysis is proposed to determine the most suitable aluminum material for highly uncertain situations. We apply a stability evaluation study based on process control theory in the robustness analysis.Item A Revisit To The Plane Problem For Low-Frequency Acoustic Scattering By An Elastic Cylindrical Shell(Başkent Üniversitesi Mühendislik Fakültesi, 2024-03-16) Yucel, Hazel; Ege, Nihal; Erbas, Baris; Kaplunov, JuliusThe proposed revisit to a classical problem in fluid-structure interaction is due to an interest in the analysis of the narrow resonances corresponding to a low-frequency fluid-borne wave, inspired by modeling and design of metamaterials. In this case, numerical implementations would greatly benefit from preliminary asymptotic predictions. The normal incidence of an acoustic wave is studied for a circular cylindrical shell governed by plane strain equations in elasticity. A novel high-order asymptotic procedure is established considering for the first time all the peculiarities of the low-frequency behavior of a thin fluid-loaded cylinder. The obtained results are exposed in the form suggested by the Resonance Scattering Theory. It is shown that the pressure scattered by rigid cylinder is the best choice for a background component. Simple explicit formulae for resonant frequencies, amplitudes, and widths are presented. They support various important observations, including comparison between widths and the error of the asymptotic expansion for frequencies.Item Categorization Of Alzheimer's Disease Stages Using Deep Learning Approaches With Mcnemar's Test(Başkent Üniversitesi Mühendislik Fakültesi, 2024-03-13) Sener, Begum; Acici, Koray; Sumer, EmreEarly diagnosis is crucial in Alzheimer's disease both clinically and for preventing the rapid progression of the disease. Early diagnosis with awareness studies of the disease is of great importance in terms of controlling the disease at an early stage. Additionally, early detection can reduce treatment costs associated with the disease. A study has been carried out on this subject to have the great importance of detecting Alzheimer's disease at a mild stage and being able to grade the disease correctly. This study's dataset consisting of MRI images from the Alzheimer's Disease Neuroimaging Initiative (ADNI) was split into training and testing sets, and deep learning -based approaches were used to obtain results. The dataset consists of three classes: Alzheimer's disease (AD), Cognitive Normal (CN), and Mild Cognitive Impairment (MCI). The achieved results showed an accuracy of 98.94% for CN vs AD in the one vs one (1 vs 1) classification with the EfficientNetB0 model and 99.58% for AD vs CNMCI in the one vs All (1 vs All) classification with AlexNet model. In addition, in the study, an accuracy of 98.42% was obtained with the EfficientNet121 model in MCI vs CN classification. These results indicate the significant potential for mild stage Alzheimer's disease detection of Alzheimer's disease. Early detection of the disease in the mild stage is a critical factor in preventing the progression of Alzheimer's disease. In addition, a variant of the non -parametric statistical McNemar's Test was applied to determine the statistical significance of the results obtained in the study. Statistical significance of 1 vs 1 and 1 vs all classifications were obtained for EfficientNetB0, DenseNet, and AlexNet models.Item A Fuzzy Computing Approach To Aggregate Expert Opinions Using Parabolic And Exparabolic Approximation Procedures For Solving Multi-Criteria Group Decision-Making Problems(Başkent Üniversitesi Mühendislik Fakültesi, 2024-03-02) Ic, Yusuf TanselTriangular fuzzy numbers (TFNs) are widely used for selection problems to determine expert opinions using linguistic expressions. Some aggregation procedures are developed to determine expert opinions more accurately. However, there is a need for a simple and more useful procedure to solve the selection problems more suitably. For this purpose, our study offers a triangular, exparabolic, and parabolic area calculation-based approximation approach for TFNs to aggregate the possible hedges (very and more or less) for TFNs. Hence, this aggregation procedure provides a tuning opportunity for classical TFN expressions to capture possible tuning processes to reflect the hesitancies of experts. The technique for order preferences by similarity to ideal solution (TOPSIS) method is applied in the two studies from extant literature, and suitable alternatives are determined as a result of the ranking process. Finally, a comparative analysis is presented to illustrate the efficiency of the proposed procedure. The conventional TOPSIS model's ranking scores are very close for exemplified examples (i.e., 0.5308, 0.4510, 0.4550 and 0.5304, 0.4626, 0.4940), but the proposed model's result has fluctuated for the same examples (i.e., 0.346, 0,669, 0,567 and 0.208, 0.991, 0.148). So, the main advantage of the proposed aggregation procedure is the alternative ranking scores separation capability analyzed with their linguistic diversification.Item Accelerating The Environmental Biodegradation Of Poly-3-Hydroxybutyrate (Phb) Via Plasma Surface Treatment(BIORESOURCE TECHNOLOGY REPORTS, 2024-09-02) Akdogan, Ebru; Sirin, Hasret Tolga; Sahal, Gulcan; Deniz, Zulkuf; Kaya, Ayberk; Serdaroglu, Dilek CokelilerThe surface of poly-3-hydroxybutyrate (PHB) was modified using a low-pressure plasma system with air as the process gas to accelerate its biodegradation rate in soil. The water contact angle of PHB was reduced from 98 degrees to 57 degrees after plasma treatment, rendering the surface hydrophilic and also induced an increase in the surface free energy. Etching on the surface was observed after the plasma treatment without a significant change in the surface crystallinity. AFM imaging showed that the plasma treatment increased the surface roughness by about 10 folds and created diverse surface structures. The soil burial test showed an approximately 1.5-fold increase in the biodegradation rate for the plasma-treated sample. Initial microbial attachment and biofilm formation were higher on the modified surface. This study demonstrated that the surface morphology created by plasma treatment promoted initial colonization and subsequent biofilm formation on the PHB surface, facilitating and accelerating its biodegradation in soil.Item An Effective Optimization Method for Integrated Scheduling of Multiple Automated Guided Vehicle Problems(TSINGHUA SCIENCE AND TECHNOLOGY, 2024-10) Sang, Hongyan; Li, Zhongkai; Tasgetiren, M. FatihAutomated Guided Vehicle (AGV) scheduling problem is an emerging research topic in the recent literature. This paper studies an integrated scheduling problem comprising task assignment and path planning for AGVs. To reduce the transportation cost of AGVs, this work also proposes an optimization method consisting of the total running distance, total delay time, and machine loss cost of AGVs. A mathematical model is formulated for the problem at hand, along with an improved Discrete Invasive Weed Optimization algorithm (DIWO). In the proposed DIWO algorithm, an insertion-based local search operator is developed to improve the local search ability of the algorithm. A staggered time departure heuristic is also proposed to reduce the number of AGV collisions in path planning. Comprehensive experiments are conducted, and 100 instances from actual factories have proven the effectiveness of the optimization method.Item Cu2znsns4 Films Prepared By A Hybrid Pvd Deposition System: A Multi-Layered Graphitic Carbon Intermediate Layer At The Mo/Czts Interface(JOURNAL OF MATERIALS SCIENCE-MATERIALS IN ELECTRONICS, 2024-11) Akcay, Neslihan; Yildirim, Ali Riza; Kesik, Deha; Gremenok, Valery F.; Ozcelik, Suleyman; Ceylan, AbdullahWe report the insertion of a new intermediate layer, a multi-layered graphitic carbon (MLGC), at Mo/CZTS interface and its impact on the structural and morphological characteristics of the back interface and absorber. MLGC was synthesized directly on Mo-coated SLG under a gas mixture flow of H2/CH4 at 550 degrees C via PECVD for 3 and 5 h. CZTS precursors were prepared on SLG/Mo and MLGC-coated SLG/Mo in a hybrid physical vapor deposition system, including evaporation and sputtering techniques, then subjected to sulfurization at 550 degrees C. The sheet resistance of back contact, microstructural parameters of the absorbers, the distributions of C and constituent elements were investigated. The diffraction peaks of the hexagonal Mo2C indicated the reaction between the C and Mo before the MLGC's growth. Raman analysis confirmed the formation of the MLGC during the long deposition time after the Mo2C formation. With the addition of MLGC, the sheet resistance of the back contact decreased from 2 to 0.5 ohm/sq, and the crystallite size of the absorbers improved. Raman spectra from the interface exhibited that MoS2 peaks' intensities significantly reduced with increasing the growth time. This implied that the 5 h-deposited MLGC was more effective in blocking the reaction between Mo and S. The absorbers with the MLGC had more uniform surface morphologies, densely packed grains, and fewer secondary phases. FIB analysis revealed the separation of the absorber with the 5 h-deposited MLGC into two parts due to C impurity. More C diffusion into the absorber for this sample was confirmed by SIMS.Item A Dss Development Study For Document Distribution Networks For Preparing Autonomous Vehicle-Integrated Distribution Systems(DECISION, 2024-12) Derya, Tusan; Ic, Yusuf Tansel; Erbay, Mehmet Dogan; Konuk, Kubra; Fidan, NihalWe propose a decision support system (DSS) to complete the tours of the routes of the traveler in charge of document distribution in the least amount of time for the document distribution task of a university to prepare autonomous vehicle-integrated distribution systems. A mathematical model-based decision support system is developed to determine distribution routes that optimize the total distance to target locations and obtain optimal system conditions for use in the migration of autonomous distribution systems. The purpose is to find the shortest-cost tours to cover all or subsets of edges in a network. Documents are shared and distributed by travelers to other related locations. Soon after, travelers will be replaced by autonomous vehicles. There are many application areas, such as newspapers and mail delivery systems. Therefore, the proposed model can be easily extended to other application areas, such as newspaper, cargo, and mail delivery systems, to construct autonomous vehicle-based systems.