Search

Your search keyword '"Güngör, Alper"' showing total 127 results
Start Over Author "Güngör, Alper"
127 results on '"Güngör, Alper"'

1. Bayesian Conditioned Diffusion Models for Inverse Problems

Author

Güngör, Alper, Bilecen, Bahri Batuhan, and Çukur, Tolga

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Computer Science - Machine Learning
Abstract

Diffusion models have recently been shown to excel in many image reconstruction tasks that involve inverse problems based on a forward measurement operator. A common framework uses task-agnostic unconditional models that are later post-conditioned for reconstruction, an approach that typically suffers from suboptimal task performance. While task-specific conditional models have also been proposed, current methods heuristically inject measured data as a naive input channel that elicits sampling inaccuracies. Here, we address the optimal conditioning of diffusion models for solving challenging inverse problems that arise during image reconstruction. Specifically, we propose a novel Bayesian conditioning technique for diffusion models, BCDM, based on score-functions associated with the conditional distribution of desired images given measured data. We rigorously derive the theory to express and train the conditional score-function. Finally, we show state-of-the-art performance in image dealiasing, deblurring, super-resolution, and inpainting with the proposed technique., Comment: 17 pages

Published
2024

2. CalibFPA: A Focal Plane Array Imaging System based on Online Deep-Learning Calibration

Author

Güngör, Alper, Bahceci, M. Umut, Ergen, Yasin, Sözak, Ahmet, Ekiz, O. Oner, Yelboga, Tolga, and Çukur, Tolga

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition
Abstract

Compressive focal plane arrays (FPA) enable cost-effective high-resolution (HR) imaging by acquisition of several multiplexed measurements on a low-resolution (LR) sensor. Multiplexed encoding of the visual scene is typically performed via electronically controllable spatial light modulators (SLM). An HR image is then reconstructed from the encoded measurements by solving an inverse problem that involves the forward model of the imaging system. To capture system non-idealities such as optical aberrations, a mainstream approach is to conduct an offline calibration scan to measure the system response for a point source at each spatial location on the imaging grid. However, it is challenging to run calibration scans when using structured SLMs as they cannot encode individual grid locations. In this study, we propose a novel compressive FPA system based on online deep-learning calibration of multiplexed LR measurements (CalibFPA). We introduce a piezo-stage that locomotes a pre-printed fixed coded aperture. A deep neural network is then leveraged to correct for the influences of system non-idealities in multiplexed measurements without the need for offline calibration scans. Finally, a deep plug-and-play algorithm is used to reconstruct images from corrected measurements. On simulated and experimental datasets, we demonstrate that CalibFPA outperforms state-of-the-art compressive FPA methods. We also report analyses to validate the design elements in CalibFPA and assess computational complexity.

Published
2023

3. DEQ-MPI: A Deep Equilibrium Reconstruction with Learned Consistency for Magnetic Particle Imaging

Author

Güngör, Alper, Askin, Baris, Soydan, Damla Alptekin, Top, Can Barış, Saritas, Emine Ulku, and Çukur, Tolga

Subjects
Electrical Engineering and Systems Science - Image and Video Processing
Abstract

Magnetic particle imaging (MPI) offers unparalleled contrast and resolution for tracing magnetic nanoparticles. A common imaging procedure calibrates a system matrix (SM) that is used to reconstruct data from subsequent scans. The ill-posed reconstruction problem can be solved by simultaneously enforcing data consistency based on the SM and regularizing the solution based on an image prior. Traditional hand-crafted priors cannot capture the complex attributes of MPI images, whereas recent MPI methods based on learned priors can suffer from extensive inference times or limited generalization performance. Here, we introduce a novel physics-driven method for MPI reconstruction based on a deep equilibrium model with learned data consistency (DEQ-MPI). DEQ-MPI reconstructs images by augmenting neural networks into an iterative optimization, as inspired by unrolling methods in deep learning. Yet, conventional unrolling methods are computationally restricted to few iterations resulting in non-convergent solutions, and they use hand-crafted consistency measures that can yield suboptimal capture of the data distribution. DEQ-MPI instead trains an implicit mapping to maximize the quality of a convergent solution, and it incorporates a learned consistency measure to better account for the data distribution. Demonstrations on simulated and experimental data indicate that DEQ-MPI achieves superior image quality and competitive inference time to state-of-the-art MPI reconstruction methods.

Published
2022
Full Text
View/download PDF

4. Unsupervised Medical Image Translation with Adversarial Diffusion Models

Author

Özbey, Muzaffer, Dalmaz, Onat, Dar, Salman UH, Bedel, Hasan A, Özturk, Şaban, Güngör, Alper, and Çukur, Tolga

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition
Abstract

Imputation of missing images via source-to-target modality translation can improve diversity in medical imaging protocols. A pervasive approach for synthesizing target images involves one-shot mapping through generative adversarial networks (GAN). Yet, GAN models that implicitly characterize the image distribution can suffer from limited sample fidelity. Here, we propose a novel method based on adversarial diffusion modeling, SynDiff, for improved performance in medical image translation. To capture a direct correlate of the image distribution, SynDiff leverages a conditional diffusion process that progressively maps noise and source images onto the target image. For fast and accurate image sampling during inference, large diffusion steps are taken with adversarial projections in the reverse diffusion direction. To enable training on unpaired datasets, a cycle-consistent architecture is devised with coupled diffusive and non-diffusive modules that bilaterally translate between two modalities. Extensive assessments are reported on the utility of SynDiff against competing GAN and diffusion models in multi-contrast MRI and MRI-CT translation. Our demonstrations indicate that SynDiff offers quantitatively and qualitatively superior performance against competing baselines., Comment: M. Ozbey and O. Dalmaz contributed equally to this study

Published
2022

5. Adaptive Diffusion Priors for Accelerated MRI Reconstruction

Author

Güngör, Alper, Dar, Salman UH, Öztürk, Şaban, Korkmaz, Yilmaz, Elmas, Gokberk, Özbey, Muzaffer, and Çukur, Tolga

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition
Abstract

Deep MRI reconstruction is commonly performed with conditional models that de-alias undersampled acquisitions to recover images consistent with fully-sampled data. Since conditional models are trained with knowledge of the imaging operator, they can show poor generalization across variable operators. Unconditional models instead learn generative image priors decoupled from the operator to improve reliability against domain shifts related to the imaging operator. Recent diffusion models are particularly promising given their high sample fidelity. Nevertheless, inference with a static image prior can perform suboptimally. Here we propose the first adaptive diffusion prior for MRI reconstruction, AdaDiff, to improve performance and reliability against domain shifts. AdaDiff leverages an efficient diffusion prior trained via adversarial mapping over large reverse diffusion steps. A two-phase reconstruction is executed following training: a rapid-diffusion phase that produces an initial reconstruction with the trained prior, and an adaptation phase that further refines the result by updating the prior to minimize data-consistency loss. Demonstrations on multi-contrast brain MRI clearly indicate that AdaDiff outperforms competing conditional and unconditional methods under domain shifts, and achieves superior or on par within-domain performance.

Published
2022
Full Text
View/download PDF

6. The Relationship between the Emotion Management Proficiencies of School Administrators and the Motivation Level of the Teachers

Author

Güngör, Alper and Helvaci, Mehmet Akif

Abstract

The aim of this research is to put forth the relationship between the emotion management proficiencies of the managers and the motivation level of the teachers. In this study, the opinions of school administrators on the emotion management behavior and the motivation level of the teachers have been examined. It was determined whether or not the opinions of the teachers differentiate according to the changes of genre, marital status, school type, the number of the teachers and the working time at the school they work. In this Ascanning model was used in this study. 374 teachers chosen by random sampling from 650 teachers working in primary, secondary and high schools in the district of Simav in Kütahya created the research phase. Two scales, Mottaz's (1985) "Job Motivation Scale" and "Emotion Management Behaviors of Managers in Terms of Management Process gelistiril developed by Çoruk and Akçay (2012) were used. According to the findings obtained from the research, the motivation perceptions of the teachers and the proficiency levels of the emotion management of the school principals were found. While the proficiency level of the emotion management of the school administrators differentiates significantly depending on the numbers of the teachers in the whole dimensions of the emotion management, it differentiates depending on the school type in the communication and evaluation dimension. The intrinsic and extrinsic motivation opinions of the teachers differentiate significantly depending on the number of the teachers at school. As a result, it has been reached that there is a positive directional strong relationship between the emotional management and and the teacher motivation.

Published
2020

7. TranSMS: Transformers for Super-Resolution Calibration in Magnetic Particle Imaging

Author

Güngör, Alper, Askin, Baris, Soydan, Damla Alptekin, Saritas, Emine Ulku, Top, Can Barış, and Çukur, Tolga

Subjects
Electrical Engineering and Systems Science - Image and Video Processing
Abstract

Magnetic particle imaging (MPI) offers exceptional contrast for magnetic nanoparticles (MNP) at high spatio-temporal resolution. A common procedure in MPI starts with a calibration scan to measure the system matrix (SM), which is then used to set up an inverse problem to reconstruct images of the MNP distribution during subsequent scans. This calibration enables the reconstruction to sensitively account for various system imperfections. Yet time-consuming SM measurements have to be repeated under notable changes in system properties. Here, we introduce a novel deep learning approach for accelerated MPI calibration based on Transformers for SM super-resolution (TranSMS). Low-resolution SM measurements are performed using large MNP samples for improved signal-to-noise ratio efficiency, and the high-resolution SM is super-resolved via model-based deep learning. TranSMS leverages a vision transformer module to capture contextual relationships in low-resolution input images, a dense convolutional module for localizing high-resolution image features, and a data-consistency module to ensure measurement fidelity. Demonstrations on simulated and experimental data indicate that TranSMS significantly improves SM recovery and MPI reconstruction for up to 64-fold acceleration in two-dimensional imaging.

Published
2021
Full Text
View/download PDF

10. Simultaneous use of Individual and Joint Regularization Terms in Compressive Sensing: Joint Reconstruction of Multi-Channel Multi-Contrast MRI Acquisitions

Author

Kopanoglu, Emre, Güngör, Alper, Kilic, Toygan, Saritas, Emine Ulku, Oguz, Kader K., Çukur, Tolga, and Güven, H. Emre

Subjects
Physics - Medical Physics, Electrical Engineering and Systems Science - Image and Video Processing
Abstract

Multi-contrast images are commonly acquired together to maximize complementary diagnostic information, albeit at the expense of longer scan times. A time-efficient strategy to acquire high-quality multi-contrast images is to accelerate individual sequences and then reconstruct undersampled data with joint regularization terms that leverage common information across contrasts. However, these terms can cause features that are unique to a subset of contrasts to leak into the other contrasts. Such leakage-of-features may appear as artificial tissues, thereby misleading diagnosis. The goal of this study is to develop a compressive sensing method for multi-channel multi-contrast magnetic resonance imaging (MRI) that optimally utilizes shared information while preventing feature leakage. Joint regularization terms group sparsity and colour total variation are used to exploit common features across images while individual sparsity and total variation are also used to prevent leakage of distinct features across contrasts. The multi-channel multi-contrast reconstruction problem is solved via a fast algorithm based on Alternating Direction Method of Multipliers. The proposed method is compared against using only individual and only joint regularization terms in reconstruction. Comparisons were performed on single-channel simulated and multi-channel in-vivo datasets in terms of reconstruction quality and neuroradiologist reader scores. The proposed method demonstrates rapid convergence and improved image quality for both simulated and in-vivo datasets. Furthermore, while reconstructions that solely use joint regularization terms are prone to leakage-of-features, the proposed method reliably avoids leakage via simultaneous use of joint and individual terms, thereby holding great promise for clinical use., Comment: Published in NMR in Biomedicine in 2020. 39 pages including Supporting Information, 12 figures

Published
2019
Full Text
View/download PDF

11. PP-MPI: A Deep Plug-and-Play Prior for Magnetic Particle Imaging Reconstruction

Author

Askin, Baris, Güngör, Alper, Alptekin Soydan, Damla, Saritas, Emine Ulku, Top, Can Barış, Cukur, Tolga, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Haq, Nandinee, editor, Johnson, Patricia, editor, Maier, Andreas, editor, Qin, Chen, editor, Würfl, Tobias, editor, and Yoo, Jaejun, editor

Published
2022
Full Text
View/download PDF

13. İZNİK (NICAEA) TİYATROSU’NDA BULUNAN DSC SERAMİKLERİNİN YEREL TAKLİTLERİ

Author

Eda GÜNGÖR ALPER, Aygün EKİN MERİÇ, and Ferhat SOMUNCU

Subjects
i̇znik, roma dönemi, seramik, sigillata, dsc, roman period, ceramic, esc, Social sciences (General), H1-99
Abstract

ÖZ: Anadolu’nun kuzeybatısında, antik Bithynia Bölgesi’nde yer alan İznik, önemli bir geçiş noktasındadır ve binlerce yıldır sürekli yerleşim görmektedir. Antik kent, MS 8. yüzyıldaki Arap akınları ve modern yerleşim nedeniyle çok tahrip olmuştur. İznik Roma Tiyatrosu’nun oturma basamakları dahil olmak üzere, mimari bloklarının büyük bölümü şehir sur yapımında yapı malzemesi olarak kullanılmıştır. Bugün cavea’nın doğu bölümüne MS 12. yüzyılda inşa edilmiş kilisenin altındaki dolgu toprağı içinde beş adet orijinal oturma basamağı dışında sadece blokaj dolguları ve sahne binasının podium kısmı görünmektedir. İznik Tiyatrosu’nda yapılan bilimsel arkeolojik kazılar sırasında bulunan eserlerin önemli bir grubunu seramikler oluşturmaktadır. Roma Dönemi’ne ait çok sayıda seramik arasında Terra Sigillata ve Kırmızı Astarlı Seramikler oldukça fazla sayıdadır. Astar ve form özelliklerine göre farklı gruplara ayrılan malzemeler incelendiğinde, Doğu Sigillata C grubuna (DSC) ait olduğu tespit edilen çok sayıda seramik parçası bulunmuştur. DSC seramiklerinin ilk üretim yeri Pitane’dir (Çandarlı). Bu grup içinde özellikle, Atlante Form L19 / Hayes Form 3 olarak sınıflandırılan kaselerin yoğunluğu dikkat çekmektedir ve İznik Tiyatro alanında DSC grubu seramiklerin üretildiği saptanmıştır. ABSTRACT: Located in the northwest of Anatolia, in the ancient Bithynia Region, Iznik is an important transit point and has been inhabited continuously for thousands of years. The ancient city was destroyed by Arab raids in the 8th century AD and modern settlement. Most of the architectural blocks of the Iznik Roman Theater, including the seating steps, were used as building materials in the construction of the city walls. Today, in the eastern part of the cavea, only the blocking fillings and the podium part of the stage building are visible, apart from the five original sitting steps in the fill soil under the church built in the 12th century AD. Ceramics constitute an important group of the artifacts found during the scientific excavations in the Iznik Theater. Terra sigillata and red slipped ceramics are quite numerous among the many ceramics belonging to the Roman Period. When the materials, which are divided into different groups according to their lining and form characteristics, are examined, there is a group of ceramics determined to belong to the Eastern Sigillata C group (DSC). The first production place of DSC ceramics is Pitane (Çandarlı). In this group, the density of bowls classified as Atlante Form L19 / Hayes Form 3 draws attention. Local productions of these ceramics were produced in Iznik Theatre, as in many centers.

Published
2022
Full Text
View/download PDF

17. 3D Trajectory Analysis for Tomographic Field Free Line Magnetic Particle Imaging

Author

ALPTEKİN SOYDAN, Damla, Karaca, Sefa, Güngör, Alper, and Top, Can Barış

Abstract

In magnetic particle imaging (MPI), spatial mapping of the magnetic nanoparticles is achieved by scanning the field-free region (FFR) throughout the field of view (FOV). The scanning trajectory of the FFR has an impact on image quality and scan time, and also is subject to limitations such as hardware requirements and patient safety. Here, we analyzed 3D imaging performance of an open-sided MPI system using simulations for various trajectories and SNR values. A selection field of 0.35 T m−1 gradient with an FFL was created and scanned tomographically. For low SNR scenarios, the best imaging results were achieved at the expense of a longer scan time when 3D FOV was densely scanned layer by layer. For more sparse trajectories, the effect of the coherence between the scan angles became prominent with the increasing noise level. Image quality can be improved by assigning non-coherent FFL angles to the consequent layers while taking hardware limitations into account., International Journal on Magnetic Particle Imaging IJMPI, Vol 9 No 1 Suppl 1 (2023)

Published
2023
Full Text
View/download PDF

19. Manyetik parçacık görüntüleme için öğrenme tabanlı geriçatım teknikleri

Author

Güngör, Alper and Çukur, Tolga

Subjects
System matrix, Deep equilibrium, Calibration, Deep learning, Medical imaging, Reconstruction, Magnetic particle imaging, Implicit
Abstract

Cataloged from PDF version of article. Thesis (Ph.D.): Bilkent University, Department of Electrical and Electronics Engineering, İhsan Doğramacı Bilkent University, 2023. Includes bibliographical references (leaves 83-97). Magnetic particle imaging (MPI) is a novel modality for imaging of magnetic nanoparticles (MNP) with high resolution, contrast and frame rate. An inverse problem is usually cased for reconstruction, which requires a time-consuming calibration scan for measuring a system matrix (SM). Previous calibration procedures involve scanning an MNP filled sample with a size that matches desired resolution through field of view. This time-consuming calibration scan which accounts for both system and MNP response imperfections is a critical factor prohibiting its practical use. Moreover, the quality of the reconstructed images heavily depend on the prior information about the MNP distribution as well as the specific re-construction algorithm, since the inverse problem is highly ill-posed. Previous approaches commonly solve an optimization problem based on the measurement model that iteratively estimates the image while enforcing data consistency in an interleaved fashion. However, while conventional hand-crated priors do not fully capture the underlying complex features of MPI images, recently proposed learned priors suffer from limited generalization performance. To tackle these issues, we first propose a deep learning based technique for accelerated MPI calibration. The technique utilizes transformers for SM super-resolution (TranSMS) for accelerated calibration of SMs with high signal-to-noise-ratio. For signal-to-noise-ratio efficiency, we propose scanning a low resolution SM with larger MNP sample size. For improved SM estimation, TranSMS leverages the vision trans-former to capture global contextual information while utilizing the convolutional module for local high-resolution features. Finally, a novel data-consistency module enforces measurement fidelity. TranSMS is shown to outperform competing methods significantly in terms of both SM recovery and image reconstruction performance. Next, to improve image reconstruction quality, we propose a novel physics-driven deep equilibrium based technique with learned consistency block for MPI (DEQ-MPI). DEQ-MPI embeds deep network operators into iterative optimization procedures for improved modeling of image statistics. Moreover, DEQ-MPI utilizes learned consistency to better capture the data statistics which helps improve the overall image reconstruction performance. Finally, compared to previous unrolling-based techniques, DEQ-MPI leverages implicit layers which enables training on the converged output. Demonstrations on both simulated and experimental data show that DEQ-MPI significantly improves image quality and reconstruction time over state-of-the-art reconstructions based on hand-crafted or learned priors. by Alper Güngör Ph.D.

Published
2023

24. A comparison of direction of arrival estimation performance for phased-MIMO systems

Author

Bahçeci, M. Umut, Güngör, Alper, Çetintepe, Çağrı, Tuncer, T. Engin, and Güngör, Alper

Subjects
Geliş açısı kestirimi, MIMO, Sıkıştırılmış algılama, Faz- MIMO, Phased- MIMO, Beamforming, Phased array, Direction of arrival, Compressed sensing, Huzme şekillendirme, Fazlı dizi
Abstract

Conference Name: 2021 29th Signal Processing and Communications Applications Conference (SIU) Date of Conference: 9-11 June 2021 Bu çalışmada, literatürde yer alan Fazlı Çoklu Giriş-Çoklu Çıkış (Fazlı-MIMO) dizi konsepti ile Sıkıştırılmış Algılama (SA) teknikleri ilk defa birlikte ele alınarak bir radar sisteminde çoklu hedefler için geliş açısı kestirim (GAK) problemi özgün olarak ele alınmıştır. Göndermeç tarafında ortalama güç kıstasları gözetilerek farklı altdizi sayıları için geleneksel huzme şekillendirme ve rasgele fazlı ağırlıklı tasarım yöntemleri incelenmi ş; almaç tarafında ise huzme şekillendirme, ayrık SA ve grup SA olmak üzere üç farklı geri çatım yöntemi ile çoklu hedefler için GAK başarımı araştırılmıştır. Anılan her senaryo için farklı Sinyal-Gürültü-Oranları (SGO) altında gerçekleştirilen parametrik Monte Carlo benzetimleri ile hedef başına hata sonuçları elde edilmiştir. Düşük SGO durumunda, Fazlı-MIMO ve SA teknikleri birlikte kullanılarak GAK başarımının artırılabileceği gösterilmiştir. Ayrıca grup seyreklik çözümü ile ayrık çözüme kıyasla kestirim hatasında 3 kata kadar bir azalma sağlanmıştır. This work combines the Phased-Multiple-Input-Multiple-Output (PH-MIMO) array and Compressive Sensing (CS) concepts from the literature, for the first time, and investigates direction of arrival (DoA) estimation problem of multiple targets in a such radar system. Transmitter model incorporates a phased-MIMO array with the number of subarrays taken as a parameter, and considers classical beamforming and random phase weight design approaches while placing an average power restriction on each antenna element. Receiver model evaluates three different reconstruction methods, namely beamforming, individual CS and group CS, for DoA performance assessment of multiple targets. Parametric Monte Carlo simulations are conducted to quantify angle error variance per target for each system configuration at different signal-to-noise (SNR) ratios. Simulation results demonstrate that a joint use of PH-MIMO and CS techniques can boost DoA performance at low SNRs, and that group sparsity solution can outperform individual solutions in terms of angle estimation error by a factor of three.

Published
2021

25. İZNİK ROMA TİYATROSU KAZILARI BİR GRUP PLASTİK KANDİL KULPU

Author

Eda Güngör Alper

Subjects
Social, General Engineering, Nikaia,Antik Çağ,Seramik,Kandil,Plastik Kulplar, Sosyal
Abstract

Günümüzdeki ismi İznik olan Nikaia antik kentinin korunan en önemli yapılarından biri Roma Dönemi’ne tarihlenen Tiyatro yapısıdır. Bu yapıda yapılan kazılar sırasında uzun bir tarih aralığına ait olan seramik buluntular ele geçmiştir. Bu seramik buluntular arasında kandiller önemli bir gruptur. Roma ve erken Bizans Dönemine tarihlendirilen bir grup kandilin plastik kulplara sahip olduğu görülmüştür. Bu makalenin konusunu bu plastik kulplar oluşturur. Temelde üç farklı grup altında incelenen plastik kulplar, bitkisel, haç motifli ve figürlü olarak ayrılmış, tipolojik ve kronolojik olarak incelenerek hangi bölgelerle ilişkilerinin olduğu tespit edilmeye çalışılmıştır.

Published
2020

26. Terracotta lamps from Metropolıs in Ionia (Turkey): typological assessment

Author

Eda Güngör Alper

Subjects
010506 paleontology, 060102 archaeology, media_common.quotation_subject, visual_art, visual_art.visual_art_medium, 0601 history and archaeology, 06 humanities and the arts, Art, Ancient history, Terracotta, 01 natural sciences, 0105 earth and related environmental sciences, media_common
Abstract

The lamps studied in this article come from Metropolıs, a strategically located site between Pergamon and Ephesos, functioning in the Hellenistic and Roman periods. Two different techniques of decorating the surfaces of the lamps were distinguished: Red-on-White and Red Slip. The lamps were dated contextually by terracotta oil lamps of the same morphological type found in the same assemblages. The material spanned a chronological range from the 1st to the 6th century AD.

Published
2019

27. Adaptive measurement matrix design in compressed sensing based direction of arrival estimation

Author

Kılıç, Berkan, Güngör, Alper, Kalfa, Mert, Arıkan, Orhan, Kılıç, Berkan, Güngör, Alper, Kalfa, Mert, and Arıkan, Orhan

Subjects
Sıkıştırılmış algılama, Geliş yönü kestirimi, Parçacık süzgeci, Compressed sensing, Direction-of-arrival estimation, Particle filters
Abstract

Conference Name: 2020 28th European Signal Processing Conference (EUSIPCO) Date of Conference: 18-21 January 2021 Geliş yönü kestirimi (GYK) problemlerinde sinyaller arkaplan uzayında, nispeten az boyutlu bir manifoldda yatar. Bu nedenle, sıkıştırılmış algılama teknikleri güvenilir geliş yönü kestirimine olanak verir. Ayrıca, ardışık Monte Carlo yöntemlerini kullanmak, tek bir noktasal kestirim yerine GYK için bir olasılık dağılımı elde etmeye olanak tanır. Sonuç olarak, bu olasılık dağılımı ölçüm matrisi tasarımında kullanıldığında, yüksek kestirim başarımı ile birlikte anten dizisi sinyal işlemede boyut indirgeme sağlanır. Bu çalışmada, olasılık dağılımı elde etmek için parçacık süzgeci kullanan, uyarlamalı sıkıştırılmış algılama tabanlı bir ızgarasız GYK yöntemi önerilmiştir. Ölçüm matrisinin rasgele seçilmesinin ve tasarlanmasının başarımları karşılaştırılmıştır. Ölçüm matrisi tasarımının, antenler üzerindeki ölçüm gürültüsüne bağlı olarak kestirim başarım artırımı, bir dizi benzetim ile gösterilmiştir. The signals in the direction-of-arrival (DOA) estimation problems lie in a relatively few dimensional manifold in their ambient space. Therefore, compressed sensing techniques enable reliable estimations. Furthermore, using sequential Monte Carlo methods enable to obtain a probability distribution for DOA estimation instead of a single point estimate. As a consequence, the probability distributions, when used in measurement matrix design, enable dimension reduction for sensor array signal processing together with high estimation performance. In this study, we use the Particle Filters to obtain the estimation distribution, and we proposed a gridless DOA estimation method within an adaptive compressive sensing framework using this distribution. We compared the performances of random and designed measurement matrices. We demonstrated an estimation performance increase via a set of simulations depending on the measurement noise.

Published
2020

30. A CNN based super-resolution technique for magnetic particle imaging system matrix

Author

Aşkın, Barış, Güngör, Alper, Soydan, Damla Alptekin, Top, Can Barış, Çukur, Tolga, Aşkın, Barış, and Çukur, Tolga

Subjects
Manyetik parçacık görüntüleme, Super-resolution, Kalibrasyon, Calibration, Evrişimsel sinir ağları, Süperçözünürlük, Convolutional neural networks, Magnetic particle imaging
Abstract

Conference Name: 2021 29th Signal Processing and Communications Applications Conference (SIU) Date of Conference: 9-11 June 2021 Manyetik Parçacık Görüntüleme (MPG), süperparamanyetik demir-oksit (SPDO) parçacıklarının yüksek çözünürlük ve kare hızında görüntülenmesini sağlayan bir görüntüleme yöntemidir. Görüntüleme işlemi doğrusal olarak modellenebilmektedir. Ancak deneysel sistemlerin ideal dışı davranışı ve teorik sistemlere kıyasla değişimlerinden dolayı, MPG sistemlerinde çoğu durumda öncelikli olarak ileri model matrisi ölçülür (sistem kalibre edilir) ve ardından bu matrisler kullanılarak görüntülerin geriçatımı yapılır. Görüntü çözünürlüğü ve boyutu doğrudan sistem matrisinin boyutundan etkilenmektedir. Ancak, kalibrasyon işlemi görüntüleme alanına bağlı olarak çok zaman almaktadır. Bu çalışmada, düşük çözünürlükte ölçülen sistem matrisleri üzerinde süper-çözünürlük teknikleri kullanılarak yüksek çözünürlüklü sistem matrisi elde edilmesi önerilmektedir. Bu amaç doğrultusunda evrişimsel sinir ağı (ESA) tabanlı bir süperçözünürlük tekniği MPG için uyarlanmış ve doğrusal aradeğerlemeye (interpolasyon) karşı etkinliği gösterilmiştir. Yöntemler gürültüsüz bir benzetim ortamında kıyaslanmış ve 4 4 kat süper-çözünürlük için, önerilen yöntem %2.92 normalize edilmiş ortalama kare hatasına yol açarken, bikübik aradeğerlemenin %12.47 hataya yol açtığı gösterilmiştir. Magnetic Particle Imaging (MPI) is a new imaging technique that allows high resolution & high frame-rate imaging of super-paramagnetic iron-oxide (SPIOs) particles. The imaging process can be modeled linearly. However, due to non-idealities and variations of the experimental system in time, many MPI systems first measure the forward model matrix (i.e. calibrate the system), then reconstruct frames from the measurements using these matrices. The image resolution and size is directly affected by the size of the system matrix. However, the calibration process may consume a lot of time depending on the field of view and resolution. In this study, we propose applying superresolution techniques on measured low-resolution system matrices to get to high resolution system matrices. Here, we propose a convolutional neural network (CNN) based super-resolution technique tailored for MPI, and show its effectiveness against linear interpolation. The methods are compared in a noiseless simulation environment, and for a super-resolution factor of 4 4, our proposed technique resulted in %2.92 normalized Root Mean Squared Error (nRMSE), while bicubic interpolation techniques resulted in %12.47 nRMSE.

Published
2021

31. Çattepe Höyüğü’nde Bulunan Pişmiş Toprak Kandiller

Author

GÜNGÖR ALPER, Eda and DOKUZ EYLÜL ÜNİVERSİTESİ

Subjects
Siirt,Çattepe Höyük,Geç Roma Dönemi,Seramik,Kandil
Abstract

Çattepe Höyüğü, Siirt İli, Kurtalan İlçesi’ne bağlı, Çattepe Köyü (Tilli/Tili/Til) yakınlarındadır. Höyük, Botan ve Dicle nehirlerinin birleştiği noktada, doğal bir yarımada üzerindedir. Çattepe, stratejik konumu nedeniyle de yaklaşık MS 11. yüzyıla kadar çok önemli bir yerleşim yeri olmuştur; Prehistorik dönemden Orta Çağ’a kadar yerleşim görmüş, MS 11. yüzyıldan sonra ise önemini yitirmiştir. Çattepe Höyüğü üzerinde yapılan yüzey araştırmaları ve kazılarda farklı dönemlere ait çok sayıda buluntu ele geçmiştir. Ancak, az sayıda geç Antik Çağ ve Orta Çağa ait pişmiş toprak kandil buluntusu vardır. Çattepe Höyük Kandil buluntuları sırlı ve sırsız olarak iki gruba ayrılmıştır; çoğunluğu sırlı kandiller oluşturur. Bunun yanı sıra, kandillerin burun kenarında, kandilin aydınlatma amacıyla kullanıldığına işaret eden, yanık izleri olduğu görülmüştür. Ayrıca, MS 10. yüzyıla tarihlenen yangından etkilenmiş olan ve aynı tarihlere verebileceğimiz kandil buluntuları da ele geçmiştir. Bu ayrıntılar da kent ve buluntuları arasında bağlantı kurulması açısından önemlidir.

Published
2021

36. Efficient heterogeneous parallel programming for compressed sensing based direction of arrival estimation.

Author

Fisne, Alparslan, Kilic, Berkan, Güngör, Alper, and Ozsoy, Adnan

Subjects
DIRECTION of arrival estimation, PARALLEL programming, COMPRESSED sensing, SENSOR arrays, REAL-time programming, REAL-time computing
Abstract

Summary: In the direction of arrival (DoA) estimation, typically sensor arrays are used where the number of required sensors can be large depending on the application. With the help of compressed sensing (CS), hardware complexity of the sensor array system can be reduced since reliable estimations are possible by using the compressed measurements where the compression is done by measurement matrices. After the compression, DoAs are reconstructed by using sparsity promoting algorithms such as alternating direction method of multipliers (ADMM). For the given procedure, both the measurement matrix design and the reconstruction algorithm may include computationally intensive operations, which are addressed in this study. The presented simulation results imply the feasibility of the system in real‐time processing with energy efficient implementations. We propose employing parallel programming to satisfy the real‐time processing requirements. While the measurement matrix design has been accelerated 16× with CPU based parallel version with respect to the fastest serial implementation, ADMM based DoA estimation has been improved 1.1× with GPU based parallel version compared to the fastest CPU parallel implementation. In addition, we achieved, to the best of our knowledge, the first energy‐efficient real‐time DoA estimation on embedded Jetson GPGPUs in 15 W power consumption without affecting the DoA accuracy performance. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

40. İnönü Üniversitesi Tıp ve Spor Bilimleri Fakültelerindeki Öğrencilerin İçme Suyu Tercihleri.

Author

YİĞİT, Esra, ÖZDEMİR, Adem Taha, GÜNGÖR, Alper, GÖKÇE, Ayşe, and ÖZER, Ali

Subjects
DRINKING water, SPORTS medicine, WATER consumption, SCIENCE students, SPORTS sciences
Abstract

Copyright of Firat Tip Dergisi is the property of Firat University, Faculty of Medicine and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Published
2021

41. Okul yöneticilerinin duygu yönetimi yeterlilikleri ile öğretmenlerin motivasyon düzeyleri arasındaki ilişki

Author

Güngör, Alper, Helvacı, Mehmet Akif, and Eğitim Bilimleri Ana Bilim Dalı

Subjects
Motivation, Emotion management, Educational administration, Eğitim ve Öğretim, Managerial competence, Education and Training, Teachers, Managers, School administrators, Sufficiency, Measurement and evaluation
Abstract

Bu araştırmanın amacı, okul yöneticilerinin duygu yönetimi yeterlilikleri ile öğretmenlerin motivasyon düzeyleri arasındaki ilişkiyi ortaya koymaktır. Bu bağlamda okul yöneticilerinin her yönetim süreci için duyguları yönetebilme yeterlilik düzeyleri ve öğretmenlerin motivasyon seviyeleri belirlenmiştir. Her yönetim süreci ve motivasyon (içsel/dışsal) düzeyi için öğretmen görüşlerinin cinsiyet, medeni durum, kıdem, okul türü, çalıştığı okuldaki öğretmen sayısı ve bulunduğu okuldaki çalışma süresi değişkenlerine göre farklılık gösterip göstermediği tespit edilmiştir. Araştırmada tarama modeli kullanılmıştır. Araştırma evrenini Kütahya ili Simav ilçesinde kamu ilkokul, ortaokul ve lise de görev yapan toplam 650 öğretmenden oluşturmakta olup bunlar arasından tesadüfi örneklem yolu ile seçilen 374 öğretmen örneklemi oluşturmuştur. Araştırmada Mottaz'ın (1985) `İş Motivasyon Ölçeği` ve Çoruk ve Akçay (2012) tarafından geliştirilen, `Yönetim Süreçleri Açısından Yöneticilerin Duygu Yönetimi Davranışları Ölçeği` olmak üzere iki ölçek kullanılmıştır. Araştırmada okul yöneticilerinin duyguları yönetme yeterliliklerinin ve öğretmenlerim motivasyon düzeylerinin oldukça yüksek olduğu tespit edilmiştir. Okul yöneticilerinin duygu yönetimi yeterlilik düzeyleri; yönetim süreçlerinin tüm boyutlarında okuldaki öğretmen sayısı değişkenine, iletişim ve değerlendirme boyutunda ise okul türü değişkenine bağlı olarak anlamlı bir şekilde farklılaşmaktadır. Öğretmenlerin içsel ve dışsal motivasyon görüşleri ise okuldaki öğretmen sayısı değişkenine bağlı olarak anlamlı bir şekilde farklılaşmaktadır. Okul yöneticilerinin duygu yönetimi yeterlilikleri ile öğretmenlerin motivasyon düzeyleri arasında pozitif yönlü güçlü doğrusal bir ilişki olduğu sonucuna ulaşılmıştır. The aim of this research is to put forth the relationship between the emotion management proficiencies of the managers and the motivation level of the teachers. In this study, the opinions of school administrators on the emotion management behavior and the motivation level of the teachers have been examined.It was determined whether or not the opinions of the teachers differentiate according to the changes of genre, marital status, school type, the number of the teachers and the working time at the school they work.In thisA scanning model was used in this study. 374 teachers chosen by random sampling from 650 teachers working in primary, secondary and high schools in the district of Simav in Kütahya created the research phase. Two scales, Mottaz's (1985) `Job Motivation Scale` and `Emotion Management Behaviors of Managers in Terms of Management Process geliştiril developed by Çoruk and Akçay (2012) were used. According to the findings obtained from the research, the motivation perceptions of the teachers and the proficiency levels of the emotion management of the school principals were found. While the proficiency level of the emotion management of the school administrators differentiates significantly depending on the numbers of the teachers in the whole dimensions of the emotion management, it differentiates depending on the school type in the communication and evaluation dimension. The intrinsic and extrinsic motivation opinions of the teachers differentiate significantly depending on the number of the teachers at school. As a result, it has been reached that there is a positive directional strong relationship between the emotional management and and the teacher motivation. 141

Published
2019

43. Hellenistic and Roman Period Ceramic Finds from the Balatlar Church Excavations in Sinop between 2010-2012

Author

Güngör Alper, Eda

Abstract

The ancient city of Sinop which was located in Paphlagonia during the Roman and Byzantine periods, is situated in the middle of the Anatolian Black Sea coast. The peninsula sheltering the city is the most northerly point of Anatolia and extends North-eastward (Fig. 1). Thanks to its localization, this area has always been an important port. History of Sinop and its environment goes back to Bronze Age. Ancient sources mention that Sinop was re-founded as a Greek colony of the city of Miletus i...

Published
2018

48. Comparison of system-matrix-based and projection-based reconstructions for field free line magnetic particle imaging

Author

Ilbey, Serhat, Top, Can Baris, Güngör, Alper, Cukur, Tolga, Saritas, Emine Ulku, Güven, Hüseyin Emre, Çukur, Tolga, and Sarıtaş, Emine Ülkü

Abstract

In magnetic particle imaging (MPI), system sensitivity can be enhanced by scanning the sample along a field free line (FFL) instead of a field free point (FFP). FFL MPI data can then be processed via system-matrix or projection-based reconstructions. Here, we compare the relative performance of these two approaches. We assume an ideal FFL (straight and homogeneous), which is translated and rotated in a two-dimensional field-of-view. We simulate the acquired data from a numerical vessel phantom for a broad range of noise levels. For the system-matrix reconstruction, we propose Alternating Direction Method of Multipliers (ADMM) to solve a constrained convex optimization problem. We also analyze the results of the nonnegative fused lasso (NFL) model to compare the performance of ADMM with one of the state-of-the-art system-matrix-based methods. For the projection-based reconstruction, we use the inverse Radon transform formulation with x-space reconstruction. System-matrix-based methods resulted in a higher structural similarity index and contrast compared to the x-space reconstruction method at the expense of longer reconstruction time. Artifacts occurred due to gridding errors for the x-space reconstruction. As expected, ADMM and NFL reconstructions yielded similar image quality., International Journal on Magnetic Particle Imaging, Vol.3, No.1, Article ID 1703022

Published
2017

50. Compressive sensing methods for multi-contrast magnetic resonance imaging

Author

Güngör, Alper, Yarman Vural, Fatoş Tunay, Çukur, Tolga, and Bilgisayar Mühendisliği Anabilim Dalı

Subjects
Elektrik ve Elektronik Mühendisliği, Digital signal processing, Digital image processing, Computer Engineering and Computer Science and Control, Electrical and Electronics Engineering, Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontrol
Abstract

Sıkıştırılmış Algılama (SA) daha az ölçüm kullanılarak seyrek bir sinyalin isabetli bir şekilde gerikazanmak için kullanılan bir sinyal işleme tekniğidir. Bu çalışma SA'nın MRGye uygulanışını incelemektedir. Bu çalışmada, öncelikle, SA MRG için bir optimizasyon çatısı sunulmaktadır. Metot, genişletilmiş Lagrange tabanlı bir metot olan yön değiştiren çarpanlar yöntemine (YDÇY) dayanmaktadır. Bu çatı, hedef fonksiyonları olarak görüntünün büyüklüğü üzerinde toplam değişinti ve l1-norm fonksiyonlarının lineer kombinasyonunu içeren bir kısıtlı bir optimizasyon problemini çözmek için kullanılmıştır. Ardından, bu çatının MRG için her yinelemede iki FFT işlemi ile çözülmesine olanak sağlayan hızlı uygulaması geliştirilmiştir. İkinci olarak, seyreklikten daha çok yararlanmak için, çoklu-kontrast MRG için bir ortak geri-kazanım metodu sunulmaktadır. Bu metot hedef fonksiyonu olarak konveks olmayan grup-lp-seyrekliği fonksiyonunun yanı-sıra ortak toplam değişinti fonksiyonunu kullanmaktadır. Son olarak, seyreklik dönüşümü ile birlikte görüntünün bulunmasına olanak sağlayan bir ortak sözlük öğrenimi tabanlı metot sunulmuştur.Yöntem tarafından bulunan seyreklik dönüşümü, bütün kontrast görüntüler üzerinde grup seyrek temsili sağlamaktadır. Bütün önerilen yöntemler literatürdeki önceki yöntemlerle hem deneysel hem de benzetim veri kümeleri kullanılarak nicelik ve kalite açılarından kıyaslanmıştır. Tekli kontrast için YDÇY'nin etkililiği diğer tekli kontrast yöntemler üzerinden gösterilmiştir. Daha sonra, ortak geri-kazanımın avantajları tartışılmış ve gösterilmiştir. Sözlük öğrenimi tabanlı yöntem yüksek işlem gücü gerektirse de, bu yöntemin görüntü kalitesi açısından avantajları gösterilmiştir. Compressive sensing (CS) is a signal processing tool that allows reconstruction of sparse signals from highly undersampled data. This study investigates application of CS to magnetic resonance imaging (MRI). In this study, first, an optimization framework for single contrast CS MRI is presented. The method relies on an augmented Lagrangian based method, specifically alternating direction method of multipliers (ADMM). The ADMM framework is used to solve a constrained optimization problem with an objective function consisting of a linear combination of the total variation on the magnitude image and the l1-norm. Then, a fast implementation is derived for MRI, which requires only two FFT operations per iteration. Second, for better exploitation of sparsity, a joint reconstruction method for multi-contrast CS MRI is presented. This method uses non-convex group-lp-sparsity as well as joint total variation as objective functions. Finally, a joint dictionary learning based method for finding the sparsifying transformation along with the image is presented. The sparsifying transformation reconstructed by the method enforces group sparse representation on all contrast images. All the proposed methods are compared quantitatively and qualitatively with previous methods that exist in the literature using both experimental in-vivo and simulated datasets. The effectiveness of the ADMM for single contrast reconstruction is demonstrated over other single contrast methods. Then, the advantages of using joint reconstruction is discussed and demonstrated. Although dictionary learning based method require high computational cost, it presents benefits in terms of image quality is shown. 138

Published
2017

Catalog

Books, media, physical & digital resources
See catalog results