Mühendislik Fakültesi / Faculty of Engineering

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

Browse

Now showing 1 - 20 of 53

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, Emre
Early 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.
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, Gokay
Deep 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.
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, Abdullah
We 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.
Design and Implementation of Drive and Control System for Ultrasonic Motor over Power Line Communication
(ELECTRIC POWER COMPONENTS AND SYSTEMS, 2024-04-20) Daldal, Nihat; Aytar, Oktay; Bekiroglu, Erdal; Bal, Gungor
In this study, remote control application of an ultrasonic motor (USM) has been achieved over the power line communication (PLC) system. Fast, practical, affordable and effective operating mode is essential for the USM. This study aimed to develop an original, efficient, effective and economical method. Drive and control of USM control has been succeeded with the developed PLC control system. A two-phase high-frequency inverter, a power line transmitter, and a power line receiver circuits have been designed to drive and control of the ultrasonic motor. Required measurements are acquired from the power line to select the most suitable communication frequency and coupling circuit impedance for the PLC system. For the communication frequency and impedance value measurements the receiver and the transmitter circuits have been designed. The PLC-controlled system has been tested for different operating conditions of the ultrasonic motor. USM control has been accomplished over the existing power line without using extra cables and interfaces for communication. The obtained results show that the PLC-controlled system is practical, reliable, cost-effective, and feasible for the remote control of the USM. This research contributes a new and essential perspective for the PLC-based remote control studies in addition to the USM drive and control strategies.
Determination of Circuit Parameters in Domestic Induction Heaters by Analytical Solution Method
(Başkent Üniversitesi Mühendislik Fakültesi, 2024-04-04) Unal, Kenan; Oncu, Selim; Tuncer, Ugur; Bal, Gungor
Domestic induction heaters provide efficient, fast, and safe heating. Variable circuit parameters in domestic induction heaters show different characteristics depending on the type of parts used for heating and the area they cover on the heating coil. For this reason, resonant frequency, maximum inverter current, and quality factor parameters of the induction heaters also change. In this study, the tests of the domestic induction heater circuit with series resonant inverter were carried out with various of workpieces diameters. The resonant frequency and maximum inverter current parameters obtained from the experimental studies, curve fitting process was performed in the MATLAB and a function on related with heater parameters was derived. By using the obtained functions, the resonant frequency and maximum inverter current of the materials in the workpieces with intermediate diameters were calculated with high accuracy and compared experimentally. Analytical calculations and experimental results confirmed each other with an accuracy and it was shown that induction heater circuit parameters could also be calculated by analytical solution method.
Effect of Microwave-Vacuum Drying on the Physicochemical Properties of a Functional Tomato Snack Bar
(JOURNAL OF THE SCIENCE OF FOOD AND AGRICULTURE, 2024) Gul, Muhammed Rasim; Ince, Alev Emine; Ozel, Baris; Uslu, Aymelek Kubra; Cetin, Melis; Mentes, Duygu; Sumnu, Servet Gulum; Oztop, Mecit Halil
BACKGROUND: Tomato is an indispensable ingredient of the Mediterranean diet. Reformulation of traditional Mediterranean products to increase the adherence of consumers is becoming popular. In this study, a tomato snack bar enriched with olive powder and pea protein was developed by using microwave-vacuum drying. Formulations also included tomato powder (TP) and low-methoxylated pectin (LMP) as a structuring agent. RESULTS:The moisture content of microwave-vacuum-dried samples varied in the range 13.6-19.8% and water activity (a(w)) values were similar to 0.6. LMP and TP concentrations affected the color of microwave-vacuum-dried samples. However, the color mainly changed in conventionally dried samples due to browning. In microwave-vacuum-dried samples, lycopene content decreased with increasing LMP, but increased with increasing TP. Textural properties of microwave-vacuum-dried snack bars increased with increasing LMP and TP. CONCLUSION: Both texture and Fourier transform infrared spectroscopy results indicated that there was a network formation due to the contribution of protein and pectin; however, the type of interaction was highly dependent on the drying mechanism. Nuclear magnetic resonance relaxometry data showed that microwave-vacuum-dried samples had a more uniform water distribution. Besides its time and energy efficiency, microwave-vacuum drying improved the color and textural properties of tomato snack bars compared to conventionally dried ones. (c) 2023 The Authors. Journal of The Science of Food and Agriculture published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.
Enhancing Carbon Fiber Reinforced Aluminum Laminates With Cellulose Paper Interlayers: Experimental Characterization Of Tensile, Flexural, And Interlaminar Fracture Toughness
(Başkent Üniversitesi Mühendislik Fakültesi, 2024-03-30) Ustun, Tugay; Guler, Ebru Saraloglu
The mechanical properties of fiber metal laminates (FML) are influenced by several various factors. Interface adhesion plays a particularly crucial role in interlaminar strength. Enhancing the interlaminar strength of carbon fiber reinforced aluminum laminate (CARALL) composites present a persistent challenge due to inherent weaknesses between metal and composite elements. Therefore, this study focuses on improving the interlaminar performance of CARALL composites by introducing cellulose paper interlayer at the metal/composite interface. The cellulose paper interlayer offers the advantage of being cost-effective and sustainable. Cellulose paper-interleaved CARALL composites were fabricated by vacuum bagging method and exhibited noteworthy improvements in mechanical properties. Comparative analysis with pristine samples revealed substantial enhancements, including a 15% increase in tensile strength, a remarkable 42% improvement in flexural strength, and a significant enhancement in mode-I fracture toughness by 65%. Furthermore, the cellulose paper interleaving played a crucial role in stabilizing fracture formation at the fiber-matrix interface, with mode II fracture toughness witnessing a 3% increase. Visual examination revealed the underlying toughening processes occurring in the interfacial area. This innovative approach of interleaving laminated composites with cellulose paper emerges as a sustainable and effective strategy, demonstrating the potential to fortify and toughen the interlaminar zones of CARALL composites. [GRAPHICS]
Ergodic Type Theorems Via Statistical Convergence
(FILOMAT, 2024) Oguz, Gencay
In the present paper we obtain some mean ergodic and uniform ergodic type theorems via statistical convergence in a Banach space. We prove, in this case that, the mean ergodic decomposition remains true. We also characterize statistical uniform ergodicity for an operator T is an element of B(X) under the condition st - lim(n )parallel to T-n parallel to/n = 0.
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.
Exploring the Critical Risk Factors of Public-Private Partnership City Hospital Projects in Turkey
(BUILDINGS, 2024-03-14) Dogan Erdem, Tugba; Birgonul, Zeynep; Bilgin, Gozde; Akcay, Emre Caner
Governments face challenges in delivering essential public services due to their limited funds. This has led to an increasing reliance on the Public-Private Partnership (PPP) model, an alternative financing model involving a long-term collaboration between the private and public sectors to provide public services. Turkey, as a developing country facing financial limitations, has embraced the PPP model to address urgent public needs. Over the past decade, the Turkish Government has extensively utilized the PPP model, particularly in executing city hospital projects. However, investors have faced challenges in project execution due to various risk factors. Therefore, the main objective of this study is to explore the critical risk factors associated with PPP city hospital projects in Turkey. In this context, a comprehensive literature review was conducted to identify potential risks related to PPP city hospital projects. A questionnaire survey was implemented to assess the probability of occurrence and the severity of the impact of these risk factors. The collected data underwent analysis to determine the priority of these risk factors. The findings revealed that the top five most critical risk factors in PPP city hospital projects in Turkey are "foreign exchange rate fluctuations", "inflation rate volatility", "high finance costs", "fiscal issues", and "economic crises". Conversely, "unavailability of equipment" was identified as the least significant risk factor. The insights gained from this research can offer valuable guidance for prospective investors interested in participating in PPP city hospital projects in Turkey and other developing countries with similar conditions.
Exploring The Viability Of Alternative Cooling-Lubrication Strategies İn Machining Processes: A Comprehensive Review On The Performance And Sustainability Assessment
(Başkent Üniversitesi Mühendislik Fakültesi, 2024-02-19) Roy, Soumikh; Das, Anshuman; Kumar, Ramanuj; Das, Sudhansu Ranjan; Rafighi, Mohammad; Sharma, Priyaranjan
This paper explores the challenges of machining difficult-to-cut metals using tools like coated carbide, ceramics, and CBN under dry conditions, addressing issues such as heat generation, tool wear and friction, chip evacuation, surface integrity, vibration, and chatter. Though cutting fluids have historically improved machinability, environmental concerns, such as toxicity and non-biodegradability, are significant. Researchers aim to enhance the economic and ecological aspects of machining by reducing cutting fluid usage. This paper provides an overview of the performance assessment and sustainability evaluation of various cooling and lubrication methods during the machining of hard-to-machine as well as difficult-to-cut metals. Additionally, the literature review highlights various environmentally friendly cooling strategies, such as minimum quantity lubrication (MQL) and cryogenic arrangements. According to the results of this review, the utilization of various cooling and lubrication technologies has the potential to enhance both sustainability and machinability properties while prolonging the lifespan of cutting tools. The findings also show that there is a lot of room for improvement in terms of optimizing and making these cooling-lubrication solutions more practical and effective.
Fault Detection System For Paper Cup Machine Based On Real-Time Image Processing
(Başkent Üniversitesi Mühendislik Fakültesi, 2024-03-31) Aydin, Alaaddin; Guney, Selda
In the production of paper cups in industrial factories, it is tried to print high quality cups with less waste loss with the help of sensors and heating resistances mounted on the paper cup machine. In this study, a system that detects faulty products based on image processing and removes it by controlling the machine with servo motors, asynchronous motors and programmable logic controller (PLC) is designed. For fault product detection, classification has been performed using real-time Haarcascade algorithm and You Only Look Once (YOLO) algorithm which is a deep learning methods, and real-time object detection has been carried out using the OpenCv library. With this study, an effective faulty product detection and removing hardware system was realized by adapting artificial intelligence algorithms to a machine used in industry. Based on the results, a whole system can be applied to systems that involve removing a faulty product from a band in any production, packaging etc. facility is proposed. A hardware consisting of servo motors, asynchronous motors and PLC was designed to separate faulty cups from the existing paper cup production machine in this study. Then, a data set composed of 1068 images was created with images taken from the camera for faulty and faultless paper cups. Using this dataset, the effect of different deep learning methods on performance in the real-time system has been examined and successful results have been obtained. The optimal outcome was achieved, yielding a real-time application accuracy rate of 90.8% through the utilization of the Yolov5x architecture.
Fine-Tuning Sno2 Films: Unleashing Their Potential Through Deposition Temperature Optimization By Ultrasonic Spray Pyrolysis
(Başkent Üniversitesi Mühendislik Fakültesi, 2024-03-31) Sarica, Emrah; Ozcan, Hakan Bilal; Gunes, Ibrahim; Terlemezoglu, Makbule; Akyuz, Idris
In this study, the optimization of the deposition temperature, which directly affects the crystallinity, morphology, and electrical conductivity of SnO2 films deposited onto Corning Eagle XG glass substrates using the ultrasonic spray pyrolysis technique, was investigated to tailor their physical properties for various applications. Structural analyses revealed that the films had a tetragonal rutile structure, and while films deposited at lower temperatures exhibited a higher prevalence of (200) oriented planes, yet this decreased with an increase in deposition temperature. Morphological analyses showed that the films consisted of grains with octahedral shapes, and films deposited at lower temperatures were found to be more compact. The films had bandgap energy ranges between 3.96 eV and 4.02 eV. Hall effect measurements revealed that not only the carrier concentration decreased from 4.52 x 10(19) cm(-3) to 0.80 x 10(19) cm(-3), but the mobility also decreased from 23.32 cm(2)/Vs to 12.85 cm(2)/Vs. Among all the films, it was noted that the films deposited at 350 degrees C had the highest figure of merit which is 12.3 x 10(-4) Omega(-1). It can be concluded that the changes underlying these variations are associated with structural and morphological changes depending on the substrate temperature. Also, significant results have been attained in applications where precise control over crystal structure and surface morphology is crucial.
Flow Rate-Dependent Properties Of Sno2 Thin Films Deposited By Ultrasonic Spray Pyrolysis
(Başkent Üniversitesi Mühendislik Fakültesi, 2024-05-02) Gunes, Ibrahim; Sarica, Emrah; Ozcan, Hakan Bilal; Terlemezoglu, Makbule; Akyuz, Idris
This study unveils the outcomes of fabricating and characterizing SnO2 thin films through ultrasonic spray pyrolysis. Also, it focuses on the effect of manipulating flow rates on their structural, optical, and electrical characteristics. Structural analysis revealed that the films exhibited a tetragonal rutile structure and (200) crystallographic planes become preferential as the flow rate increases. Crystallite size and lattice strain were calculated using the Debye-Scherrer and Williamson-Hall methods, demonstrating that higher the flow rate resulted in larger crystallite sizes and reduced lattice strain. SEM images showed that all films have uniform and consistent film thickness and grain size enlarged with the solution flow rate as well. The films exhibited high optical transparency (>80%) in the visible spectrum, making them suitable for transparent conductive applications. The band gap of the films decreased gradually with flow rates, and the Urbach energy slightly increased. Hall effect measurements revealed higher flow rates resulted in lower sheet resistance (lowest is 1.32 x 10(2) Omega/sq) and higher carrier mobility (highest is 22.12 cm(2)/V.s), indicating improved electrical properties. These findings offer valuable perspectives for forthcoming researches.
Fluorine-Doped Tin Oxide Films Via Ultrasonic Spray Pyrolysis: Investigation Of Physical Properties Post-Annealing And Their Potential For Tco Applications
(MATERIALS TODAY COMMUNICATIONS, 2024-12) Gunes, Ibrahim; Sarica, Emrah; Bilgin, Vildan; Kucukarslan, Ayse; Ozder, Serhat
In this study, undoped tin oxide (SnO2) and fluorine (F)-doped SnO2 (FTO) films at various doping levels were deposited on glass substrates using the ultrasonic spray pyrolysis technique, followed by an annealing process applied to the films after deposition. In line with this, the study reveals the significant impact of the fluorine doping level optimization on certain physical properties such as the structural, optical, and electrical characteristics of the obtained films, and presents the consequences of the variation in these physical properties for adaptability in various optoelectronic applications. No diffraction peaks were observed in the X-ray diffraction patterns of the deposited films. After the annealing process, however, films with a polycrystalline form and a rutile tetragonal crystal structure were obtained. It was observed that the crystallization levels were better in films doped with 5 % and 10 % F. The optical band gap values of the films were determined to vary between 3.35 eV and 3.68 eV. Furthermore, it was found that with the increase in F doping level, the resistivity (ranging from 2.1 Omega cm to 43.5 Omega cm) and sheet resistance (ranging from 1.62x10(5) Omega/sq to 35.9x10(5) Omega/sq) values of the films decreased, while the figure of merit values (ranging from 0.12x10(-8) Omega(-1) to 67.1x10(-8) Omega(-1)) increased. Among all FTO films, it was revealed that films doped with 10 % F exhibited the highest optical transmittance, the lowest electrical resistivity, and the highest figure of merit values.
Generating The Level 2 Subgroup By Involutions
(Başkent Üniversitesi Mühendislik Fakültesi, 2024-05-19) Altunoz, Tuelin; Monden, Naoyuki; Pamuk, Mehmetcik; Yildiz, Oguz
We obtain a minimal generating set of involutions for the level 2 subgroup of the mapping class group of a closed nonorientable surface. (c) 2024 Elsevier B.V. All rights reserved.
Hamiltonian Formulation Of Relativistic Magnetohydrodynamic Accretion On A General Spherically Symmetric And Static Black Hole: Quantum Effects On Shock States
(EUROPEAN PHYSICAL JOURNAL C, 2024-11-19) Azreg-Ainou, Mustapha; Jamil, Mubasher; Noda, Sousuke
In this paper, our aim is to extend our earlier work [Ahmed et al. in Eur. Phys. J. C 76:280, 2016], investigating an axisymmetric plasma flow with angular momentum onto a spherical black hole. To accomplish that goal, we focus on the case in which the ideal magnetohydrodynamic approximation is valid, utilizing certain conservation laws which arise from particular symmetries of the system. After formulating a Hamiltonian of the physical system, we solve the Hamilton equations and look for critical solutions of (both in and out) flows. Reflecting the difference from the Schwarzschild spacetime, the positions of sonic points (fast magnetosonic point, slow magnetosonic point, Alfv & eacute;n point) are altered. We explore several kinds of flows including critical, non-critical, global, magnetically arrested and shock induced. Lastly, we analyze the shock states near a specific quantum corrected Schwarzschild black hole and determine that quantum effects do not favor shock states by pushing the shock location outward.
Hand and Pose-Based Feature Selection for Zero-Shot Sign Language Recognition
(IEEE ACCESS, 2024-08-22) Ozcan, Giray Sercan; Bilge, Yunus Can; Sumer, Emre
Sign language functions as an indispensable interaction method for a certain portion of people in society, offering a unique way of communication. A significant challenge in advancing towards this objective is the difficulty in obtaining suitable training data for each sign in supervised learning. This challenge comes from the complex process of labeling signs and the limited number of skilled people available to do this job. This work introduces a new approach to the problem of Zero-Shot Sign Language Recognition (ZSSLR). We basically utilize and model hand and landmark data streams extracted from the body of the signer. Based on these extracted and modeled features, we employ a data grading approach to facilitate visual embedding with the self-attention mechanism. We utilize textual sign description features along with visual embedding in the Zero-Shot Learning (ZSL) settings. We assess the efficacy of our methodology in two of the suggested ZSL benchmarks.
Identification of Torsionally Stiff and Flexible Asymmetric Systems, and Their Comparative Seismic Response Evaluation for Low-Rise Frames
(JOURNAL OF EARTHQUAKE ENGINEERING, 2024) Kaatsiz, Kaan; Sucuoglu, Haluk
Torsional status indicators of asymmetrical plan systems are evaluated. The ratio of two modal participation factors in a translational direction (lower to higher mode) is proved as a more accurate indicator than the ratio of translation and rotation dominant modal periods. Seismic responses of low-rise asymmetric-plan frames are then assessed through linear elastic and nonlinear response analysis of representative systems under bi-axial ground motion pairs. The results revealed that those systems that are initially identified as torsionally stiff exhibit a torsionally stiff nonlinear response, whereas those initially categorized as torsionally balanced or flexible evolve to a stiffer torsional performance.
Implementation of Smooth Transitions for Grid Connected PV System between the Operating Modes
(18TH INTERNATIONAL CONFERENCE ON COMPATIBILITY, POWER ELECTRONICS AND POWER ENGINEERING, CPE-POWERENG 2024, 2024-10-02) Onar, Burak; Fesli, Ugur; Demirbas, Sevki
The grid-connected PV microgrid needs coordination among the components, compromising the whole system to supply the power required by the loads. Well-designed energy management and control structures should be ensured to operate grid-connected PV microgrids with smooth and uninterruptible power. Much of the power system instability arises from transitions between grid-connected mode and island mode. This study introduces a control method to ensure a smooth transition between operating modes for PV microgrids operating in both grid-connected and island modes. The proposed control method has been verified with simulation performed with Matlab & Simulink simulation programs.