Communications, Series A2-A3: Physical Sciences and Engineering
Permanent URI for this community
Browse
Browsing Communications, Series A2-A3: Physical Sciences and Engineering by Title
Now showing 1 - 20 of 171
Results Per Page
Sort Options
Item 3D reconstruction of coronary arteries using deep networks from synthetic X-ray angiogram data(Ankara Üniversitesi Mühendislik Fakültesi, 2022) Atlı, İbrahim; Other; OtherCardiovascular disease (CVD) is one of the most common health problems that are responsible for one-third of all deaths around the globe. Although X-Ray angiography has deficiencies such as two-dimensional (2D) representation of three dimensional (3D) structures, vessel overlapping, noisy background, the existence of other tissues/organs in images, etc., it is used as the gold standard technique for the diagnosis and in some cases treatment of CVDs. To overcome the deficiencies, great efforts have been drawn on retrieval of actual 3D representation of coronary arterial tree from 2D X-ray angiograms. However, the proposed algorithms are based on analytical methods and enforce some constraints. With the evolution of deep neural networks, 3D reconstruction from images can be achieved effectively. In this study, we propose a new data structure for the representation of objects in a tubular shape for 3D reconstruction of arteries using deep learning. Moreover, we propose a method to generate synthetic coronaries from data of real subjects. Then, we validate tubular shape representation using 3 typical deep learning architectures with synthetic X-ray data we produced. The input to deep learning architectures is multi-view segmented X-Ray images and the output is the structured tubular representation. We compare results qualitatively in terms of visual appearance and quantitatively in terms of Chamfer Distance and Mean Squared Error. The results demonstrate that tubular representation has promising performance in 3D reconstruction of coronaries. We observe that convolutional neural network (CNN) based architectures yield better 3D reconstruction performance with 9.9e-3 on Chamfer Distance. On the other hand, LSTM-based network fails to learn the coronary tree structure and we conclude that LSTMs are not appropriate for auto-regression problems as depicted in this study.Item 3D visualization approach to GPR dataOKAY, Merve Özkan; SAMET, RefikItem A brief review of feed-forward neural networksSAZLI, Murat H.Item A Comparatıve Study: Voltage Multıplıers For RF Energy Harvestıng System(Ankara Üniversitesi Mühendislik Fakültesi, 2019-06-30) Sarı, Filiz; Uzun, Yunus; Other; OtherVoltage multipliers are widely used for energy harvesting processes to convert the received AC signal to DC signal, also enhanced the low level received signal. In this study, Villard, Dickson and Greinacher type voltage multipliers are analyzed without impedance matching and substrate materials to decide the effective voltage multiplier type depend on the inputs of the harvester. So, load resistance, input power and input frequencies’ effects are analyzed and compared with each other. Agilent Advanced Design System (ADS) is used for simulations. HSMS 2852 Schottky diode and capacitors are used for these voltage multipliers. Results show that, determining load resistance is important for evaluating high efficiency, e.g. efficiency differences are reached 33% between 2kΩ and 20 kΩ for Dickson voltage multiplier at 100 MHz input frequency. Furthermore, the best efficiency is obtained by Greinacher voltage multiplier for low input frequencies which is lower than 1 GHz but there are no significant differences are observed for high frequencies. This study shows that load resistance, input frequency and input power are important parameters for voltage multiplier selection and Greinacher voltage multiplier is the best choice to obtain high efficiency for low frequency application of RF harvesting.Item A Comparison of deep Learning Based Architecture With a Conventional Approach for Face Recognition Problem(Ankara Üniversitesi Fen Fakültesi, 2019-12-01) Ünal, Fatime Zehra; Bilgisayar Mühendisliği; Fen Bilimleri EnstitüsüThis paper addresses a new approach for face recognition problem based on deep learning strategy. In order to verify the performance of the proposed approach, it is compared with a conventional face recognition method by using various comprehensive datasets. The conventional approach employs Histogram of Gradient (HOG) algorithm to extract features and utilizes a multi-class Support Vector Machine (SVM) classifier to train and learn the classification. On the other hand, the proposed deep learning based approaches employ a Convolutional Neural Network (CNN) based architecture and also offer both a SVM and Softmax classifiers respectively for the classification phase. Results reveal that the proposed deep learning architecture using Softmax classifier outperform conventional method by a substantial margin. As well as, the deep learning architecture using Softmax classifier also outperform SVM in almost all cases.Item A Concatenated Up And Down Tapered Fıber For Sımultaneous Measurement Of Straın And Temperature(Ankara Üniversitesi Fen Fakültesi, 2020-07-01) Bilsel, Mustafa; Navruz, İsa; Elektrik-Elektronik Mühendisliği; Mühendislik FakültesiA novel fiber optical sensor based on in-line fiber Mach-Zehnder interferometer for simultaneous measurement of strain and temperature is proposed and demonstrated experimentally. The interferometer is simple, extremely robust and highly sensitive and consists of two concatenated parts; one is a down-tapered fiber (DTF) and the other is an up-tapered fiber (UTF). UTF and DTF sections of the sensor are fabricated by using a commercial fiber splicer and a non-commercial setup based on heating and stretching a portion of a standard single-mode fiber, respectively. While UTF section behaves as a beam splitter to decompose the injected light into core and cladding modes, DTF section provides evanescent field to access the surrounding environment. Experimental results indicate that the resolutions of 0.83 °C and 45.80 micro-epsilon were achieved in temperature and strain, respectively, for simultaneous measurement with a 10 pm of wavelength resolution.Item A method for analyzing suspect-filler similarity using convolutional neural networks(Ankara Üniversitesi Mühendislik Fakültesi, 2022) Ar, Yılmaz; Bilgisayar Mühendisliği; Mühendislik FakültesiEyewitness misidentifications are one of the leading factors in wrongful convictions. This study focuses on the structure of the lineups, which is one of the factors that cause misidentification, and the use of artificial intelligence (AI) technologies in the selection of fillers to be included in the lineups. In the study, AI-based face recognition systems are used to determine the level of similarity of fillers to the suspect. Using two different face recognition models with a Convolutional Neural Network (CNN) structure, similarity threshold values close to human performance were calculated (VGG Face and Cosine similarity = 0.383, FaceNet and Euclidean l2 = 1.16). In the second part of the study, the problems that are likely to be caused by facial recognition systems used in the selection of fillers are examined. The results of the study reveal that models responsible for facial recognition may not suffice alone in the selection of fillers and, an advanced structure using CNN models trained to recognize other attributes (race, gender, age, etc.) associated with similarity along with face recognition models would produce more accurate results. In the last part of the study, a Line-up application that can analyze attributes such as facial similarity, race, gender, age, and facial expression, is introduced.Item A new astronomical parameter from remote sensing data: Astronomical clearness index (ACI)(Ankara Üniversitesi Fen Fakültesi, 2021-07-01) Kaba, Kazım; Yaprak, Cahit Yeşil; Şatır, Onur; Other; OtherEastern Anatolia Observatory (DAG) project was initiated in Erzurum/Turkey in 2011. DAG will have Turkey’s largest (4 m) and first infrared telescope. The installation process is planned to be by taking its first light in the end of 2021. This study was focused on a new analysis method about the atmospheric properties of DAG site in terms of the cloudiness as known the most vital atmospheric parameter for ground-based astronomical observatories. In this regard, the cloudiness for DAG site is comprehensively examined using the “Cloud Mask” (CMa) and “Cloud Type” (CT) products from Satellite Application Facility on Support to Nowcasting and Very Short-Range Forecasting (NWC SAF). Firstly, the cloudiness and the cloud types over DAG site were determined. Secondly, NWC SAF CMa and CT data have been redefined for astronomical purposes, and the pixel values/meanings in CMa and CT images have been reduced from 6 to 4 and from 21 to 4 pixels, respectively. Thirdly, these new data were used to define a new index named as “Astronomical Clearness Index” (ACI), and finally, the observable days for DAG site were determined using this newly defined index.Item A new distributed denial-of-service detection system in cloud environment by using deep belief networks(Ankara Üniversitesi Fen Fakültesi, 2021-06-30) İbrahim, İbrahim; Kurnaz, Sefer; Other; OtherThis study presents new method to detect DDOS attacks by using Deep Belief Networks (DBN). The input data which represented the DDoS features in cloud environment are first analyzed by using DBN to extracted high level and sensitive features. The output of the DBN wired to the classifier (SoftMax and SVM). The aim of using the DBN is to extracted features that have ability to present the best classification results and to speed up the processing time by reducing the dimension of features. In the last stage, the Classifier trained in supervised method to classify the features into two labels there is attack or not. The obtained results compared with well-known studies presented in this field.Item A new similarity coefficient for a collaborative filtering algorithmSİNCAN, Özge Mercanoğlu; YILDIRIM, ZeynepItem A Numerical Integration of the Lunar OrbitTÜFEKÇİOĞLU, ZekiItem A Puzzling Eclipsing Binary System :Epsilon AurigaeDEMİRCAN, O.;DERMAN, E.; AYDIN, C.;AKALIN, A.Item A review of turbo coding and decodingSAZLI, Murat H.Item A review on system identification in power generation systemsOZKAYA, Derya; KOSALAY, IlhanItem A Statıstıcal Overvıew On Sleep Scorıng(Ankara Üniversitesi Fen Fakültesi, 2020-12-31) Özbek, Levent; Sütçigil, Levent; Aydın, Hamdullah; Yetkin, Sinan; Özgen, Fuat; İstatistik; Fen FakültesiIn this study, sleep electroencephalography (EEG) which is frequently used in statistical modelling has been modelled with the autoregressive (AR) time-series model and what kind of a structure the variance of the term white noise included in the model represented in different sleep stages has been observed. Taking all of the stages scored in accordance with Rechtschaffen and Kales criterion into account separately, epoches in each stage have been modelled with the AR and the variance of the term white noise in this model has been monitored. The study has evaluated the sleep EEG variances of a subject. In accordance with the results, the heterogeneity at Stage 2 was thought to be the reason why the objective differences appeared in scoring. It is thought that this data pointed out a necessity that the period in Rechtschaffen and Kales scoring which is called Stage 2 must be revised.Item A study on modeling growth model of Adana pigeons(Ankara Üniversitesi Mühendislik Fakültesi, 2022) Özbek, Levent; Elektrik-Elektronik Mühendisliği; Mühendislik FakültesiThe study aims to determine a mathematical model that can be used to describe the growth of the Adana pigeon. Since pigeons have only one breeding season, just one or two pairs of baby pigeons are raised per year. Hatchlings sometimes die before reaching adulthood. For this reason, measurements can be taken for 10, 15 and 60 days periods. Related with this issue, only 43-days measurements of 68 pigeons are used over a 6-year period. The study is modelled by taking the day-to-day average of the data (43 days) of 68 pigeons. The study was conducted on 68 Adana pigeons in the interval between the age of 1 and 43 days. The growth of pigeon cub was measured by daily live weight until 1 to 43 days. The estimation is carried out by writing the specific Matlab codes. Classical growth functions used in animals are in nonlinear form. Various numerical methods have been developed to estimate parameters in nonlinear functions. Special program routines have been developed to implement these methods. In these nonlinear models, there are more than one parameter to be estimated. Therefore, the number of mathematical operations in estimating the parameters is large. The most used models in the literature are Brody, Bertalanffy, Logistic, Generalized Logistic, Gompertz, Richards, Negative Exponential, Stevens, and Tanaka. However, as far as is known, there is no published article for Adana pigeons that uses all of these models and compares which one is better. These models are Brody, Bertalanffy, Logistic, Generalized Logistic, Gompertz, Richards, Negative Exponential, Stevens, and Tanaka. The best analysis was done by the Richards model in terms of both the Mean Squared Error (MSE), mean absolute percentage error (MAPE) and (Coefficient of Determination) R2 .Item A study on non-linear discrete-time state-space models and adaptive extended Kalman filter application on oscillatıon of an object tied to the end of spring(Ankara Üniversitesi Fen Fakültesi, 2021-07-01) Öztürk, Fikri; Özbek, Levent; İstatistik; Fen FakültesiIn this work, Adaptive Extended Kalman Filter (AEKF) is introduced and its use for oscillation of an object connected to the end of a spring is shown. As a new approach, an AEKF is used as a nonlinear estimation tool for online estimation of the states and parameters of an oscillating object attached to the end of a spring model. Parameter states that do not change with time were examined. The simulation results revealed that with proper selection of initial values of AEKF, AEKF is a very useful tool for this particular application.Item A Study On The Search Potentıal of Doubly Charged Leptons At The Sppc Based Ep Colliders(Ankara Üniversitesi Fen Fakültesi, 2020-06-30) Ozansoy, Aysuhan; Albayrak, Oğuzhan; Fizik; Fen FakültesiWe consider the single production of doubly charged leptons which take part in the extended weak isospin models and have exotic electric charges such as at the SppC based electron-proton (ep) colliders. We introduce the effective lagrangians describing the doubly charged lepton gauge interactions with SM leptons. We calculate the decay widths and production cross sections as a function of doubly charged lepton mass. We deal with the process and plot the kinematical distributions for the final state electron both for the signal and corresponding background. We perform a cut-based analysis to obtain the mass limits and couplings of doubly charged leptons at the SppC based ep colliders with the center-of-mass energies of TeV and TeV.