Doktora Tezleri
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/5800
Browse
8 results
Search Results
Doctoral Thesis MRG Taramalarında Alzheimer Hastalığının Zaman Dağılımlı Sınıflandırılması(Abdullah Gül Üniversitesi, Fen Bilimleri Enstitüsü, 2024) Dündar, Mehmet Sait; Yılmaz, BülentThis thesis presents a comprehensive framework for studying Alzheimer's Disease (AD) progression by focusing on the classification of AD, Mild Cognitive Impairment (MCI), and Cognitively Normal (CN) individuals using advanced machine learning models that analyze changes in brain volumetrics over time through MRI scans. In the first phase of the research, MR images from the Alzheimer's Disease Neuroimaging Initiative database were utilized, which included sequences of 3-4 scans taken annually from 22 CN, 18 AD, and 20 MCI subjects. Key volumetric parameters such as cortical thickness and intracranial volumes were extracted using the CAT12 toolbox in SPM software. A novel classification method based on the rate of volumetric changes over time was employed, effectively capturing the progressive nature of neurological changes. This approach achieved accuracies of 82.5% in distinguishing AD from CN, 71% in differentiating MCI from AD, and 69% in separating MCI from CN, alongside a 55% accuracy in a three-way classification using random forest and support vector machines. Building on these initial insights, the second phase of the study significantly advanced the methodology by integrating a pre-trained 3D ResNet 101 CNN algorithm for initial spatial categorization of MRI scans, followed by the use of Long Short-Term Memory (LSTM) networks. These LSTMs processed the same sequences of 3-4 annual scans for each patient, enhancing the model's ability to analyze and interpret the temporal progression of volumetric changes. This sophisticated approach led to marked improvements in classification accuracy: 96.7% in differentiating AD from CN, 87.5% in distinguishing AD from MCI, and 86.4% in separating MCI from CN. The study effectively demonstrates a significant enhancement in capturing the temporal dynamics of AD progression.Doctoral Thesis El Protezleri için EEG ve EMG Sinyalleriyle Algı Kestirimi ve Tork Kontrolü(Abdullah Gül Üniversitesi, Fen Bilimleri Enstitüsü, 2024) Karakullukcu, Nedime; Yılmaz, BülentUpper extremity prostheses vary based on patients' articulation levels and movement methods. They can be cosmetic, operate mechanically with shoulder movement, or be controlled by myoelectronic and electroencephalography (EEG) signals. However, unnatural prosthesis control burdens users mentally. This thesis seeks to enhance bionic hand prosthesis control using EEG and electromyography (EMG) signals, coupled with users' visual weight perception, aiming to reduce physical and mental discomfort associated with mechanical prostheses. The prototype hand's preconditioning evaluates objects' weight visually, aiming to reduce shoulder force and mental load while holding an object. EEG and EMG signals from subjects were processed for real-time implementation. In the first stage, a study focused on operating the prosthesis using the motor intention waves of prosthesis users, and the machine learning approaches' classification success (detection of the intention to activate the prosthesis) was examined using EEG data from 30 healthy participants. The second stage recorded EEG and EMG signals from 31 participants during reaching, lifting, and placing an object, employing various classifications for object weight. In the real-time classification of multi-channel EEG signals from 20 healthy individuals using Fourier-based synchrosequeezing transform (FSST) and singular value decomposition (SVD) approaches, the system aimed to control the stiffness of the wrist part of the prosthesis. Consequently, the system could detect the weight of the object perceived by the user while using the prosthesis, allowing for the preconditioning of the prosthesis based on this weight when the user wants to hold and move the object.Doctoral Thesis Trafik Yoğunluğu Tahmini için Derin Öğrenme Modelleri(Abdullah Gül Üniversitesi, Fen Bilimleri Enstitüsü, 2024) Çini, Nevin; Aydın, ZaferIn the last 50 years, with the growth of cities and increase in the number of vehicles and mobility, traffic has become troublesome. As a result, traffic flow prediction started to attract attention as an important research area. However, despite the extensive literature, traffic flow prediction still remains as an open research problem, specifically for long- term traffic flow prediction. Compared to the models developed for short-term traffic flow prediction, the number of models developed for long-term traffic flow prediction is very few. Based on this shortcoming, in this study, we focus on long-term traffic flow prediction and propose a novel deep ensemble model (DEM). In order to build this ensemble model, first, we developed a convolutional neural network (CNN), a long short term memory (LSTM) network, and a gated recurrent unit (GRU) network as deep learning models, which formed the base learners. In the next step, we combine the output of these models according to their individual forecasting success. We use another deep learning model to determine the success of the individual models. Our proposed model is a flexible ensemble prediction model that can be updated based on traffic data. To evaluate the performance of the proposed model, we use a publicly available dataset. Numerical results show that our proposed model performs better than individual deep learning models (i.e., LSTM, CNN, GRU), selected traditional machine learning models (i.e., linear regression (LR), decision tree regression (DTR), k-nearest-neighbors regression (KNNR) and other ensemble models such as random-forest-regression(RFR).Doctoral Thesis Biyoçipler için Mikro Biyomalzemelerin ve Hücrelerin Görüntü İşleme Yöntemleri ile Otomatik Olarak Sayılması ve Analizi(Abdullah Gül Üniversitesi, Fen Bilimleri Enstitüsü, 2023) Çelebi, Fatma; İçöz, KutayQuantification of tumor cells is essential for early cancer detection and progression tracking. Multiple techniques have been devised to detect tumor cells. In addition to conventional laboratory instruments, several biochip-based techniques have been devised for this purpose. Our biochip design incorporates micron-sized immunomagnetic beads and micropad arrays, necessitating automated detection and quantification not only of cells but also of the micropads and immunomagnetic beads. The primary function of the biochip is to simultaneously acquire target cells with distinct antigens. As a readout technique for the biochip, this study devised a digital image processing-based method for quantifying leukemia cells, immunomagnetic beads, and micropads. Images were acquired on the chip using bright-field microscopy with image objectives of 20X and 40X. Conventional image processing methods, machine learning methods, and deep learning methods were used to analyze the images. To quantify targets in the images captured by a bright-field microscope, color- and size-based object recognition and machine learning-based methods were first implemented. Secondly, color- and size-based object detection and object segmentation methods were implemented to detect structures in bright-field optical microscope images acquired from the biochip. Third, segmentation of the minimal residual disease (MRD) using deep learning. Implemented biochip images comprised of leukemic cells, immunomagnetic beads, and micropads. Moreover, mesenchymal stem cells (MSCs) are stem cells with the capacity for multilineage differentiation and self-renewal. Estimating the proportion of senescent cells is therefore essential for clinical applications of MSCs. In this study, a self-supervised learning (SSL)-based method for segmenting and quantifying the density of cellular senescence was implemented, which can perform well despite the small size of the labeled dataset.Doctoral Thesis Videodan Gece Yangın Tespiti(Abdullah Gül Üniversitesi, Fen Bilimleri Enstitüsü, 2022) Ağırman, Ahmet Kerim; Taşdemir, KasımWith the recent advancements in the field of Computer Vision, the central tasks such as object detection, segmentation or object tracking methods attain all-time high accuracies in natural image sets such as ImageNet, COCO, etc. However, due to the innate downsides of digital images acquired in insufficiently illuminated environments, the conventional methods suffer severely. This specific problem remains unsolved. Especially if the environment is pitch dark and the object of interest is emitting light, the dynamic range of the current digital cameras falls short in this situation and the generated digital image contains almost no perceptible visual texture. One prominent example of this is nighttime forest fire videos. In this thesis, detection of nighttime forest fires from video is addressed as an application of the challenging task, scene perception in low light conditions. The first contribution of this dissertation is developing a novel object tracking algorithm for glowing object in the dark environments. The algorithm allows to track fire and nonfire objects throughout the video. The second contribution of the thesis is proposal of new handcrafted features which are designed to capture spatio-temporal behavior of the glowing objects since there is little or no visual textures to be processed. The results showed that the features are descriptive enough to distinguish fire from the other deceptive light sources. The third contribution is employing deep learning models to automatically extract spatial features with CNNs, and temporal features from bidirectional Long Short-Term Memory (BLSTM) networks. The empirical test results show that a CNN + BLSTM pipeline can effectively detect fires at night with a high accuracy. Finally, a new comprehensive nighttime fire video dataset comprising 1358 positive videos and 334535 of fire frames is created.Doctoral Thesis Zamansal Bilgiden Faydalanarak Videodan Orman Yangınlarının Erken Tespiti(Abdullah Gül Üniversitesi, Fen Bilimleri Enstitüsü, 2022) Taş, Merve; Taşdemir, Kasım; Aydın, ZaferForest fires are considered as the major threats to lives, properties and to the integrity of the ecosystem around the world. In most cases, the fire damage can be reduced, when the initial signs of the fire are detected in a timely manner. Since smoke is considered as the first visual sign of fire, detection of smoke is vital. Hence, a successfully designed smoke detection system is essentially critical in the early detection of smoke for outdoor environments. The existing smoke detection methods suffer from high false alarm rates and cannot accurately detect smoke in hazy environments. To address these problems, this thesis is focused on smoke detection model at an early stage that utilizes deep learning (DL) based techniques for outdoor locations. This work contributes mainly to four aspects of smoke detection: (1) new datasets preparation for three smoke detection tasks classification, detection-segmentation, and video classification, (2) utilizing transfer learning to detect the smoke on the relatively small dataset, (3) image dehazing process that includes removing the haze from the dataset images to enhance the system performance, (4) designing a novel hybrid video classification model by combining the two DL based video classification structures. This work will be a resourceful reference for researchers working in the fields of forest fire or smoke detection studies at an early stage. The experiments, research findings, and enhanced performance of the smoke detection system provide a source of information about smoke detection. Current studies can be utilized to further improve the design of efficient and reliable fire safety models. Keywords: Deep Learning, Spatio-Temporal Information, Forest Fire Early Detection, Smoke Detection, Image DehazingDoctoral Thesis Bor Esaslı Nano Yapıların Modellenmesi ve İncelenmesi(Abdullah Gül Üniversitesi, Fen Bilimleri Enstitüsü, 2022) Tahaoğlu, Duygu; Durandurdu, Murat; Alkan, FahriPolyhedral boron clusters and their applications have been subject to research in many fields such as medicine, materials science, catalytic applications, energy studies, etc. These molecules owe their popularity to their exceptional 3D stable structures, as well as their various sought-after properties in many applications. This doctoral thesis was prepared within the focus of a computational investigation of different polyhedral borane and carborane clusters by using DFT methods. The results of our studies were reported in two main chapters (Chapters 3 and 4). In the first part (Chapter 3), theoretical evaluation of relative stabilities and electronic structure for [BnXn]2− clusters were provided. The structural and electronic characteristics of [BnXn]2− clusters were examined by comparison with the [B12X12]2− counterparts with a focus on the substituent effects (X = H, F, Cl, Br, CN, BO, OH, NH2). The effects of the substituents were discussed in relation to their mesomeric (±M) and inductive (±I) effects. The results showed that the icosahedral barrier can be reduced through substitution by destabilizing the [B12X12]2−cluster with symmetry-reducing ligands or ligands with +M effects rather than stabilizing the larger clusters. In the second part (Chapter 4), the investigation of the photophysical properties of carborane-containing luminescent systems was presented. The o-CB-Anth system is known to exhibit a dual-emission property by radiating in the visible region from two low energy conformations with local excited (LE) and hybridized local and charge transfer (HLCT) characters, however, it shows a very low emission quantum yield in solution state similar to many other CB-luminescent systems. In this section, the excited-state potential energy surface (PES) of o-CB-Anth and o-CB-Pent were investigated in detail and the effect of a low-lying CT on the low quantum yield was discussed.Doctoral Thesis Optoelektronik Aygıtlar için Yarıiletken Kolloidal Kuantum Noktaları ve Kuantum Kuyularının Sentezi ve Karakterizasyonu(Abdullah Gül Üniversitesi, 2018) ALTINTAS, YEMLİHA; Altıntas, Yemliha; Mutlugün, EvrenYarıiletken kuantum noktalar son derece küçük boyutları (2-20 nm), boyutlarına bağlı değişen eksitonik özellikleri, mükemmel derecede ışık ve ısı stabilite özellikleri sayesinde son birkaç on yılda nanomalzemelerin önemli dallarından biri haline gelmiştir. Kuantum noktaların tüm bu özellikleri onları ışık yayan diyotlar, güneş pilleri ve kolloidal lazer gibi optoelektronik uygulamalar için egzotik nanomalzemeler olarak adlandırmasını sağlamıştır. Bu tez çalışmasının ana odağı yüksek kalitede ve stabil nanokristal malzemeler üretmek ve onların optoelektronik uygulamalarını sunmaktır. Bu amacı gerçekleştirmek için yüksek kalitede ve saf renkte ışık yayan CdSe/ZnS kuantum noktaları sentezlendi ve bu kuantum noktalar kullanılarak hazırlanan esnek polimerik filmler yardımıyla da yüksek kalitede beyaz ışık yayan diyotlar elde edildi. Bu filmlerin kullanılması ile elde edilen sonuçlar 122,5 NTSC renk gamı (CIE-1931), 88,6 CRI, 190 lm/Wopt LER ve 2763 K CCT değerleri sayesinde hem ekran hem de aydınlatma uygulamaları için sunulmuştur. Cd-tabanlı nanomalzemelere yönelik çevresel kaygılar nedeniyle Cd-tabanlı nanomalzemelere ek olarak dikkatimizi Cd-içermeyen kuantum noktacıkları üzerine odakladık. Birçok farklı uygulamada kuantum noktaların performanslarının değerlendirilmesi onların QY, FWHM ve değişebilen ışıma dalga boyu gibi optik özelliklerine bağlıdır. Çevreye duyarlı kuantum noktaların optik özelliklerini iyileştirmek için birçok sentez yöntem ve tarifi, farklı kimyasallar, konsantrasyonlar ve yapılar ile denendi. Dikkatlice hazırlanan sentez tarifi, kimyasalların optimize edilmesi ve önerilen InPZnS/ZnS alaşımlı çekirdek/kabuk yapısının yardımı ile % 78 QY ve 45 nm FWHM değerleri elde edildi. Tüm sentez aşamalarında sentezden numune almak suretiyle kuantum noktaların optik özelliklerin değişimi kararlı hal ve zaman çözünürlüklü fotolüminesans analizi ile karakterize edildi. Alaşımlı çekirdeğin ışıma ömrü, 20,3 ns' den 50,4 ns' ye kabuk kaplama ve ışımasız lifetime bileşenlerinin baskılanmasıyla arttı. Kadmiyum içermeyen kuantum noktaların optik özelliklerinin daha da artması için sentezde kullanılan Zn çeşidi ve konsantrasyonunu sistematik olarak çalıştık. Yeşil ışıyan kuantum noktalar 54 nm FWHM ve % 87 kuantum verimlilik ile sentezlendi. Yeşil ve kırmızı ışıyan kuantum noktaların verici ve alıcı çiftleri arasındaki ışıma kinetiği ve FRET verimliliği kararlı hal ve zaman çözünürlüklü fotolüminesans analizi yardımıyla araştırıldı. Verimli yeşil ışıyan kuantum noktalar ile kırmızı ışıyan kadmiyum içermeyen kuantum noktaların polimerik filmler içerisindeki karışımı ile % 70,3 FRET verimliliğini sağladı. Son yıllarda, ışıyan numunelerin film içerisindeki optik özelliklerinin ve veriminin korunması için nanokristallerin polimerik yapı ile kullanılmasına alternatif olarak tuz kristalleri verimli bir platform olarak ortaya çıktı. FRET verimliliği, ışık stabilitesi ve tuz tablet içerisine konulmuş kadmiyum içermeyen kuantum noktaların beyaz-LED performansı tuz karışımı içerisindeki alıcı ve verici arasındaki konsantrasyon oranının değiştirilmesiyle araştırıldı. % 65 FRET verimliliği 324 lm/Wopt LER ile 84,7 CRI değerleri kadmiyum içermeyen kuantum noktalardan elde edildi. Ayrıca iki boyutlu kuantum kuyuların sentezi ve bu malzemelerin verimli bir şekilde optic kazanç ve lazer uygulamalarında kullanılmasına odaklandık. c-ALD metodu ile üretilen çekirdek/kabuk yapıdaki nanolevhaların (NPL)' lerin düşük verim ve düşük kararlılıkları onların optik kazanç ve lazer uygulamalarında kullanılmalarını kısıtlıyordu. Bu nedenle, ilk olarak numunelerin optik özellik ve kararlılıklarını hem solüsyon içerisinde hem film içerisinde iyileştirmeye çalıştık. Nihayetinde %100 verimli CdSe/ZnS çekirdek/kabuk NPL' leri sıcak ekleme kabuk büyütme yaklaşımı ile başarılı bir şekilde sentezlendi. Yeni sentez protokolümüz ile sentezlenen NPL' ler, sıradışı ısı ve ışık kararlılıkları ve 7 µJ cm-2 kadar düşük eşik değerine sahip optik kazanç performansı sergiledi.