Department of Electrical and Electronics Engineering

Permanent URI for this collection


Recent Submissions

Now showing 1 - 20 of 4159
  • ItemEmbargo
    High-precision laser focus positioning of rough surfaces by deep learning
    (Elsevier Ltd, 2023-05-18) Polat, Can; Yapici, Gizem Nuran; Elahi, Sepehr; Elahi, Parviz
    This work presents a precise positioning detection based on a convolutional neural network (CNN) to control the laser focus in laser material processing systems. The images of the diffraction patterns measured at different positions of the laser focus concerning the workpiece are classified in the range of the Rayleigh length of the focusing lens with an increment of about 7% of it. The experiment was carried out on different materials with different levels of surface roughness, such as copper, silicon, and steel, and over 99% accuracy in the positioning detection was achieved. Considering surface roughness and camera noise, a theoretical model is established, and the effects of these parameters on the accuracy of focus detection are also presented. The proposed method exhibits a noise-robust focus detection system and the potential for many precise positioning detection systems in industry and biology. © 2023 Elsevier Ltd.
  • ItemOpen Access
    Employing transformer encoders for enhanced functional connectivity mapping
    (IEEE - Institute of Electrical and Electronics Engineers, 2023-08-28) Bedel, Hasan Atakan; Çukur, Tolga
    Functional magnetic resonance imaging (fMRI) provides a way to spatially and temporally map brain activity, making it a crucial tool in many advanced psychology and neuroscience studies. A variety of techniques are suggested to analyze the four-dimensional data produced by fMRI scans. When it comes to classification tasks, the most prevalent method involves examining functional connectivity. This process involves dividing the brain volume into separate regions and determining the correlation between the series of events occurring over time in these regions. While deep graph models and deep convolutional models are frequently employed to process functional connectivity, these methods can sometimes overcomplicate the procedure. In contrast, we present a straightforward approach that utilizes transformer encoders to map functional connectivity to labels. Our method demonstrates superior performance in gender classification tasks when compared to existing deep graph and convolution models. We've validated this on two publicly accessible datasets.
  • ItemOpen Access
    Autonomous air combat with reinforcement learning under different noise conditions
    (IEEE - Institute of Electrical and Electronics Engineers, 2023-08-28) Taşbaş, A. S.; Serbest, S.; Şahin, Safa Onur; Üre, N. K.
    The autonomous realization of air combat with reinforcement learning-based methods has recently become a prominent field of study. In this paper, we present a classifier architecture to solve the air combat problem in noisy environments, which is a sub-branch of this field. We collect data from environments with different noise levels using air combat simulation. Using these data, we train three different data sets with the number of state stacks 2, 4, and 8. We train neural network-based classifiers using these datasets. These classifiers adaptively estimate the noise level in the environment at each time step and activate the appropriate pre-trained reinforcement learning policy based on this estimate. In addition, we share the performance comparison of these classifiers in different state stacks.
  • ItemOpen Access
    Improving experience replay architecture with K-Means clustering
    (IEEE - Institute of Electrical and Electronics Engineers, 2023-08-28) Serbest, S.; Taşbaş, A. S.; Şahin, Safa Onur
    Replay memory highly affects the performance of deep reinforcement learning algorithms in terms of data efficiency and training time. How the experiences will be stored in the memory and sampling will be realized are subjects of ongoing research in the field. In this paper, a new replay memory module, called K-Means Replay Memory is designed. The module consists of two submodules called Recent Memory and Global Memory. New experiences are inserted only into recent memory and when the number of experiences in recent memory exceeds a certain limit, experience share occurs from recent memory to global memory. After the experience share, similarity sets are constituted via K-Means clustering algorithm within the stored experiences. While sampling, the distribution of experiences sampled from recent memory with respect to similarity sets and average losses obtained from neural networks are taken into account in order to compute set probabilities. Experiences are sampled from global memory by using these probabilities. Experiments are performed by using Prioritized Experience Replay, Uniform Experience Replay and K-Means Replay Memory, and obtained results are given in this paper.
  • ItemOpen Access
    A transformer-based real-time focus detection technique for wide-field interferometric microscopy
    (IEEE - Institute of Electrical and Electronics Engineers, 2023-08-28) Polat, Can; Güngör, A.; Yorulmaz, M.; Kızılelma, B.; Çukur, Tolga
    Wide-field interferometric microscopy (WIM) has been utilized for visualization of individual biological nanoparticles with high sensitivity. However, the image quality is highly affected by the focusing of the image. Hence, focus detection has been an active research field within the scope of imaging and microscopy. To tackle this issue, we propose a novel convolution and transformer based deep learning technique to detect focus in WIM. The method is compared to other focus detecton techniques and is able to obtain higher precision with less number of parameters. Furthermore, the model achieves real-time focus detection thanks to its low inference time.
  • ItemOpen Access
    A transformer-based prior legal case retrieval method
    (IEEE - Institute of Electrical and Electronics Engineers, 2023-08-28) Öztürk, Ceyhun Emre; Özçelik, Şemsi Barış; Koç, Aykut
    In this work, BERTurk-Legal, a transformer-based language model, is introduced to retrieve prior legal cases. BERTurk-Legal is pre-trained on a dataset from the Turkish legal domain. This dataset does not contain any labels related to the prior court case retrieval task. Masked language modeling is used to train BERTurk-Legal in a self-supervised manner. With zero-shot classification, BERTurk-Legal provides state-of-the-art results on the dataset consisting of legal cases of the Court of Cassation of Turkey. The results of the experiments show the necessity of developing language models specific to the Turkish law domain.
  • ItemOpen Access
    Wind power prediction using machine learning and deep learning algorithms
    (IEEE - Institute of Electrical and Electronics Engineers, 2023-08-28) Şimşek, Ecem; Güngör, Ayşemüge; Karavelioğlu, Öykü; Yerli, Mustafa Tolga
    In this study, it has been tried to predict the wind power generation values in a long-term period by using a dataset containing the wind power generation values of 10 zones using machine learning and deep learning methods. In this context, the importance of accurately predicting renewable energy production was emphasized by associating it with machine learning and deep learning methods. The methods to be used in the study were selected based on the literature review and the characteristics of the time series datasets. Since the dataset includes the basic wind components, a detailed feature analysis was performed, and the dataset was enriched with the newly added features. The hyperparameters of the utilized models were optimized for all regions in the dataset separately and the models were run with these hyperparameters. The results of the models were evaluated with different error metrics and compared with each other, and the models with the lowest error scores were determined.
  • ItemOpen Access
    Conditions of well-posedness for planar conewise linear systems
    (Sage Publications, 2023-04-24) Namdar, Daniyal; Özgüler, Arif Bülent
    A planar (2D) conewise linear system (CLS) is considered. This is a piecewise linear system of two states and multiple modes, where each mode is linear with its state-space constrained into a polyhedral, finitely generated, convex cone. It is allowed to have a discontinuous vector field and sliding modes. Alternative conditions for well-posedness of Caratheodory solutions of this system that have intuitive interpretations with respect to eigenvectors and cone-boundary vectors are derived. It is also shown that a well-known condition for well-posedness of bimodal systems also applies to two adjacent modes of this system without any change.
  • ItemOpen Access
    Denoising diffusion adversarial models for unconditional medical image generation
    (IEEE - Institute of Electrical and Electronics Engineers, 2023-08-28) Dalmaz, Onat; Sağlam, Baturay; Elmas, Gökberk; Mirza, Muhammad Usama; Çukur, Tolga
    Unconditional medical image synthesis is the task of generating realistic and diverse medical images from random noise without any prior information or constraints. Synthesizing realistic medical images can enrich the quality and diversity of medical imaging datasets, which in turn, enhance the performance and generalization of deep learning models for medical imaging. Prevalent approach for synthesizing medical images involves generative adversarial networks (GAN) or denoising diffusion probabilistic models (DDPM). However, GAN models that implicitly learn the image distribution are prone to limited sample fidelity and diversity. On the other hand, diffusion models suffer from slow sampling speed due to small diffusion steps. In this paper, we propose a novel diffusion-based method for unconditional medical image synthesis, Diff-Med-Synth, that generates realistic and diverse medical images from random noise. Diff-Med-Synth combines the advantages of denoising diffusion probabilistic models and GANs to achieve fast and efficient image sampling. We evaluate our method on two multi-contrast MRI datasets and show that it outperforms state-of-the-art methods in terms of quality, diversity, and fidelity of the synthesized images.
  • ItemOpen Access
    A diffusion-based reconstruction technique for single pixel camera
    (IEEE - Institute of Electrical and Electronics Engineers, 2023-08-28) Güven, Baturalp; Güngör, A.; Bahçeci, M. U.; Çukur, Tolga
    Single-pixel imaging enables high-resolution imaging through multiple coded measurements based on lowresolution snapshots. To reconstruct a high-resolution image from these coded measurements, an ill-posed inverse problem is solved. Despite the recent popularity of deep learning-based methods for single-pixel imaging reconstruction, they are insufficient in preserving spatial details and achieving a stable reconstruction. Diffusion-based methods, which have gained attention in recent years, provide a solution to this problem. In this study, to the best of our knowledge, the single-pixel image reconstruction is performed for the first time using a denoising diffusion probabilistic model. The proposed method reconstructs the image by conditioning it towards the least squares solution while preserving data consistency after unconditional training of the model. The proposed method is compared against existing singlepixel imaging methods, and ablation studies are conducted to demonstrate the individual model components. The proposed method outperforms competing methods in both quantitative measurements and visual quality.
  • ItemOpen Access
    Focal modulation based end-to-end multi-label classification for chest X-ray image classification
    (IEEE - Institute of Electrical and Electronics Engineers, 2023-08-28) Öztürk, Şaban; Çukur, Tolga
    Chest X-ray imaging is of critical importance in order to effectively diagnose chest diseases, which are increasing today due to various environmental and hereditary factors. Although chest X-ray is the most commonly used device for detecting pathological abnormalities, it can be quite challenging for specialists due to misleading locations and sizes of pathological abnormalities, visual similarities, and complex backgrounds. Traditional deep learning (DL) architectures fall short due to relatively small areas of pathological abnormalities and similarities between diseased and healthy areas. In addition, DL structures with standard classification approaches are not ideal for dealing with problems involving multiple diseases. In order to overcome the aforementioned problems, firstly, background-independent feature maps were created using a conventional convolutional neural network (CNN). Then, the relationships between objects in the feature maps are made suitable for multi-label classification tasks using the focal modulation network (FMA), an innovative attention module that is more effective than the self-attention approach. Experiments using a Chest x-ray dataset containing both single and multiple labels for a total of 14 different diseases show that the proposed approach can provide superior performance for multi-label datasets.
  • ItemOpen Access
    Transformer-based bug/feature classification
    (IEEE - Institute of Electrical and Electronics Engineers, 2023-08-28) Öztürk, Ceyhun Emre; Yılmaz, E. H.; Köksal, Ö.
    Automatic classification of a software bug report as a 'bug' or 'feature' is essential to accelerate closed-source software development. In this work, we focus on automating the bug/feature classification task with artificial intelligence using a newly constructed dataset of Turkish software bug reports collected from a commercial project. We train and test support vector machine (SVM), k-nearest neighbors (KNN), convolutional neural network (CNN), transformer-based models, and similar artificial intelligence models on the collected reports. Results of the experiments show that transformer-based BERTurk is the best-performing model for the bug/feature classification task.
  • ItemOpen Access
    Detection of jammers in range-doppler images generated in DTED based radar simulator using convolutional neural networks
    (IEEE - Institute of Electrical and Electronics Engineers, 2023-08-28) Şahinbay, H. E.; Akyol, Ali Alp; Özdemir, Ö.
    Airborne radars have a variety of air-to-air and air-to-ground missions. In both air-to-air and air-to-ground target detection missions, ground clutter reflections are received from the main beam and side lobes of the radar. The effects of this clutter can be clearly seen in the radar range-Doppler maps. In addition, there may be other sources in the environment that distort the radar's range-Doppler maps. These sources can be categorized as jammer and interference signals. They distord the range-Doppler maps, making target detection more difficult, interfering with target detection and, in some cases, leading to false target detection. The detection of jammer and interference signals, which are the source of this situation, is of critical importance for the operators controlling the platform. It is often not possible for operators to quickly detect and classify these jamming signals. Deep learning methods, which have recently been used in every field, can achieve much faster and robust target detection and classification results compared to humans. In this study, the success of a Convolutional Neural Network based technique, which is one of the deep learning methods, in detecting and classifying jammer and interference signals is investigated.
  • ItemOpen Access
    Super-resolution diffusion model for accelerated MRI reconstruction
    (IEEE - Institute of Electrical and Electronics Engineers, 2023-08-28) Mirza, Muhammad Usama; Çukur, Tolga
    MRI reconstruction is a process to generate high-quality images from the raw data obtained during magnetic resonance imaging. Diffusion models, a class of generative models, have become a popular method for MRI Reconstruction due to their ability to generate high quality images. Diffusion models work by adding Gaussian noise to the original image and training a network to remove the noise. Diffusion models can continue to generate high quality images even with a different type of noise added to the original image. In this study we combine a resolution decreasing operator with noise scheduling used by regular diffusion models, ResDiff to perform MRI Reconstruction. One of the biggest drawbacks of Diffusion models is the amount of time taken to generate images. Down-sampling images to a lower resolution requires fewer steps allowing ResDiff to achieve competitive results in far less time.
  • ItemOpen Access
    Understanding the suitable alloying conditions for highly efficient Cu- and Mn-doped Zn1-xCdxS/ZnS core-shell quantum dots
    (Elsevier B.V., 2023-10-20) Kaur, Manpreet; Sharma, Ashma; Erdem, Onur; Kumar, A.; Demir, Hilmi Volkan; Sharma, M.
    Doping of alloyed colloidal quantum dots (QDs) has garnered significant attention for providing tunable and Stokes-shifted emission. By alloying the host semiconductor nanocrystals (NCs), their band gap can be tuned. With the specific addition of dopant ions, these NCs can emit tunable emissions within the visible spectrum. However, while doped and alloyed quantum dots (QDs) have shown promise for tunable emissions, their emission qualities have not been consistent across the spectrum. Here, we report the synthesis of high-quality Cu- and Mn-doped ZnxCd1-xS (x = 0–1) alloyed QDs by a colloidal non-injection method. In this study, we examined the effect of different dopant ions on the optical properties of similar alloyed nanocrystals. The deposition of a ZnS shell on these doped QDs significantly improves their quantum yield (QY), increasing it from 7.0 % to 50.0 % for Cu-doped QDs and from 30.0 % to 80.0 % for Mn-doped QDs. The Cu-doped QDs exhibit tunable emission from green to red across the visible spectrum by varying the Zn/Cd ratio, whereas the Mn-doped QDs show a fixed orange emission. Interestingly, the Cu-doped alloyed QDs show a contrasting trend in quantum yield (QY) compared to those of Mn-doped QDs when the amount of Cd in ZnCdS alloyed QDs is systematically changed. As the amount of Cd increases in the ZnCdS alloyed QDs, the Cu-doped QDs show both an increase in average lifetime and an increase in QY. In contrast, for the Mn-doped QDs, the decay lifetime values remain fairly constant for different amounts of Cd in the ZnCdS alloyed QDs, but the QY decreases as the amount of Cd increases. The results of this study may facilitate the design of optimal alloying combinations for Cu/Mn-doped QDs in optoelectronic applications. © 2023 The Authors
  • ItemOpen Access
    Modeling age of information in a cooperative slotted Aloha network
    (Springer, 2023-03-28) Vaezi, Kaveh; Akar, Nail; Karaşan, Ezhan
    In this paper, we study a slotted Aloha cooperative network where a source node and a relay node send status updates of two underlying stochastic processes to a common destination. Additionally, the relay node cooperates with the source by accepting its packets for further re-transmissions using probabilistic acceptance and relaying. We obtain the exact steady state distributions of Age of Information (AoI) and Peak AoI sequences of both nodes using Quasi-Birth-Death Markov chains. The analytical model is first validated by simulations and then used to obtain optimal cooperation policies when transmission probabilities are fixed. Subsequently, we study the more general problem of joint optimization of the transmission probabilities and cooperation level between the source and relay, with detailed numerical examples.
  • ItemOpen Access
    Deep-learning-enabled electromagnetic near-field prediction and inverse design of metasurfaces
    (Optica Publishing Group (formerly OSA), 2023-10-16) Kanmaz, Tevfik Bülent; Öztürk, E.; Demir, Hilmi Volkan; Gündüz-Demir, Ç.
    Metasurfaces generate desired electromagnetic wavefronts using sub-wavelength structures that are much thinner than conventional optical tools.However, their typical design method is based on trial and error, which is adversely inefficient in terms of the consumed time and computational power. This paper proposes and demonstrates deep-learning-enabled rapid prediction of the full electromagnetic near-field response and inverse prediction of the metasurfaces from desired wavefronts to obtain direct and rapid designs. The proposed encoder-decoder neural network was tested for different metasurface design configurations. This approach overcomes the common issue of predicting only the transmission spectra, a critical limitation of the previous reports of deep-learning-based solutions. Our deep-learning-empowered near-field model can conveniently be used as a rapid simulation tool for metasurface analyses as well as for their direct rapid design. © 2023 Optica Publishing Group.
  • ItemOpen Access
    A slotted pilot-based unsourced random access scheme with a multiple-antenna receiver
    (Institute of Electrical and Electronics Engineers, 2023-08-30) Özateş, Mert; Kazemi, Mohammad; Duman, Tolga Mete
    We consider unsourced random access over fading channels with a massive number of antennas at the base station, and propose a simple, yet energy-efficient solution by dividing the transmission frame into slots. We utilize non-orthogonal pilot sequences followed by a polar codeword for transmission in each slot. At the receiver side, we first detect the transmitted pilot sequences by employing a generalized orthogonal matching pursuit algorithm and utilize a linear minimum mean square error solution to estimate the channel vectors. We then perform an iterative decoding based on maximal ratio combining, single-user polar decoding, and successive interference cancellation with re-estimation of the channel vectors to recover the data bits. We also analyze the performance of the proposed scheme using normal approximations and provide a detailed complexity analysis. Numerical examples demonstrate that the proposed scheme either outperforms the existing schemes in the literature or has a competitive performance with a lower complexity. Furthermore, it is suitable for fast-fading scenarios due to its excellent performance in the short blocklength regime.
  • ItemOpen Access
    Enhanced generation of higher harmonic from Halide Perovskite Metasurfaces
    (META Conference, 2023) Tonkaev, P.; Koshelev, K.; Masharin, Mikhail A.; Makarov S.; Kruk S.; Kruk S.
    Many outstanding properties of halide perovskites provided their applications in optoelectronics. Perovskite films demonstrate outstanding nonlinear properties with large optical nonlinearities comparable to the nonlinear constants of conventional semiconductor materials. Meanwhile, nonlinear properties can be enhanced by the metaphotonic approach. Here we demonstrate a two-order enhancement of fifth-harmonic generation in halide perovskite nonlocal metasurfaces due to high-quality resonance at the generated harmonic wavelength in the visible frequency range. © 2023, META Conference. All rights reserved.
  • ItemOpen Access
    Foerster-Type nonradiative energy transfer in media with complex permittivity
    (META Conference, 2023) Hernandez-Martinez, Pedro Ludwig; Yucel, Abdulkadir C.; Demir, Hilmi Volkan
    We present the effects of the complex permittivity of a background medium on Foerster-type nonradiative energy transfer (FRET) and the changes in FRET as a function of the relative permittivity of the medium. We discuss examples of enhanced FRET via tuning the complex permittivity of the medium and illustrate that FRET can significantly increase when the denominator of the FRET screening factor approaches zero. © 2023, META Conference. All rights reserved.