Behçet Uğur Töreyіn
YOU?
Author Swipe
View article: ToyMatch: a temperament-aligned toy recommendation system for circular design in early childhoods
ToyMatch: a temperament-aligned toy recommendation system for circular design in early childhoods Open
Introduction Toy consumption during early childhood presents a critical opportunity to integrate child temperament, sustainable toy design, and value-aligned decision-making into everyday caregiving. Yet most existing recommendation system…
View article: Influence-driven Sample Selection for Functional Brain Network Classification: Application to Autism Diagnosis
Influence-driven Sample Selection for Functional Brain Network Classification: Application to Autism Diagnosis Open
The proliferation of non-invasive neuroimaging datasets acquired from different modalities has driven advancements in machine learning models for diagnosing brain disorders. While prior studies have primarily focused on feature engineering…
View article: A Bayesian Model for Optimizing Thermal Comfort and Indoor Air Quality
A Bayesian Model for Optimizing Thermal Comfort and Indoor Air Quality Open
This study focuses on the usage of a probabilistic approach on determining the best course of action in a specific environment within the domain of architecture. More specifically, Bayesian decision theory is applied on a simplified proble…
View article: RamanFormer: A Transformer-Based Quantification Approach for Raman Mixture Components
RamanFormer: A Transformer-Based Quantification Approach for Raman Mixture Components Open
Raman spectroscopy is a noninvasive technique to identify materials by their unique molecular vibrational fingerprints. However, distinguishing and quantifying components in mixtures present challenges due to overlapping spectra, especiall…
View article: Do deep neural networks utilize the weight space efficiently?
Do deep neural networks utilize the weight space efficiently? Open
Deep learning models like Transformers and Convolutional Neural Networks (CNNs) have revolutionized various domains, but their parameter-intensive nature hampers deployment in resource-constrained settings. In this paper, we introduce a no…
View article: Blank Frame and Intensity Variation Distortion Detection and Restoration Pipeline for Phase-Contrast Microscopy Time-Lapse Images
Blank Frame and Intensity Variation Distortion Detection and Restoration Pipeline for Phase-Contrast Microscopy Time-Lapse Images Open
In this study, we propose a preprocessing pipeline for the detection and correction of distorted frames in time-lapse images obtained from phase-contrast microscopy. The proposed pipeline employs the average intensities of frames as a foun…
View article: Collection: Wound Healing Assay Dataset (WHAD) and Cell Adhesion and Motility Assay Dataset (CAMAD)
Collection: Wound Healing Assay Dataset (WHAD) and Cell Adhesion and Motility Assay Dataset (CAMAD) Open
the Wound Healing Assay Dataset (WHAD) and the Cell Adhesion and Motility Assay Dataset (CAMAD). WHAD comprises time-lapse phase-contrast images of wound healing assays using genetically modified MCF10A and MCF7 cells, while CAMAD includes…
View article: A multi-spectral myelin annotation tool for machine learning based myelin quantification
A multi-spectral myelin annotation tool for machine learning based myelin quantification Open
Myelin is an essential component of the nervous system and myelin damage causes demyelination diseases. Myelin is a sheet of oligodendrocyte membrane wrapped around the neuronal axon. In the fluorescent images, experts manually identify my…
View article: Direct pore-based identification for fingerprint matching process
Direct pore-based identification for fingerprint matching process Open
Fingerprints are one of the most important scientific proof instruments in solving forensic cases. Identification in fingerprints consists of three levels based on the flow direction of the papillary lines at the first level, the minutiae …
View article: Vehicle Detection and Classification without Residual Calculation: Accelerating HEVC Image Decoding with Random Perturbation Injection
Vehicle Detection and Classification without Residual Calculation: Accelerating HEVC Image Decoding with Random Perturbation Injection Open
In the field of video analytics, particularly traffic surveillance, there is a growing need for efficient and effective methods for processing and understanding video data. Traditional full video decoding techniques can be computationally …
View article: "Machine Learning-Based Compressive Strength Estimation in Nano Silica-Modified Concrete"
"Machine Learning-Based Compressive Strength Estimation in Nano Silica-Modified Concrete" Open
View article: Vehicle Detection and Classification Without Residual Calculation: Accelerating Hevc Image Decoding with Random Perturbation Injection
Vehicle Detection and Classification Without Residual Calculation: Accelerating Hevc Image Decoding with Random Perturbation Injection Open
View article: Table of Contents
Table of Contents Open
View article: Detection and Restoration Pipeline for Phase Contrast Microscopy Time Series Images
Detection and Restoration Pipeline for Phase Contrast Microscopy Time Series Images Open
We propose a pre-processing pipeline for the de-tection and restoration of distorted frames in phase-contrast microscopy time-series images. The analysis is based on the average intensity values of the frames within any given time- series …
View article: PURSUhInT: In Search of Informative Hint Points Based on Layer Clustering for Knowledge Distillation
PURSUhInT: In Search of Informative Hint Points Based on Layer Clustering for Knowledge Distillation Open
View article: CNN-based Server State Monitoring and Fault Diagnosis using Infrared Thermal Images
CNN-based Server State Monitoring and Fault Diagnosis using Infrared Thermal Images Open
The recent spike in the demand for high-performance computing (HPC) server systems has created many challenges in data centers (DCs) including thermal management, system reliability sustenance and server failure minimalization. Lately, dee…
View article: A multi-spectral myelin annotation tool for machine learning based myelin quantification
A multi-spectral myelin annotation tool for machine learning based myelin quantification Open
Myelin is an essential component of the nervous system and myelin damage causes demyelination diseases. Myelin is a sheet of oligodendrocyte membrane wrapped around the neuronal axon. In the fluorescent images, experts manually identify my…
View article: A multi-spectral myelin annotation tool for machine learning based myelin quantification
A multi-spectral myelin annotation tool for machine learning based myelin quantification Open
Myelin is an essential component of the nervous system and myelin damage causes demyelination diseases. Myelin is a sheet of oligodendrocyte membrane wrapped around the neuronal axon. In the fluorescent images, experts manually identify my…
View article: Focus-and-Detect: A small object detection framework for aerial images
Focus-and-Detect: A small object detection framework for aerial images Open
View article: Unsupervised Behaviour Analysis of News Consumption in Turkish Media
Unsupervised Behaviour Analysis of News Consumption in Turkish Media Open
Clickstream data, which come with a massive volume generated by human activities on websites, have become a prominent feature for identifying readers' characteristics by newsrooms after the digitization of news outlets. Although the nature…
View article: Improved cell segmentation using deep learning in label-free optical microscopy images
Improved cell segmentation using deep learning in label-free optical microscopy images Open
The recently popular deep neural networks (DNNs) have a significant effect on the improvement of segmentation accuracy from various perspectives, including robustness and completeness in comparison to conventional methods. We determined th…
View article: A whole-slide image grading benchmark and tissue classification for cervical cancer precursor lesions with inter-observer variability
A whole-slide image grading benchmark and tissue classification for cervical cancer precursor lesions with inter-observer variability Open
View article: An Image Segmentation Method for Wound Healing Assay Images
An Image Segmentation Method for Wound Healing Assay Images Open
Wound healing assays are important for molecular biologists to understand the mechanisms of cell migration. For the analysis of wound healing assays, accurate segmentation of the wound front is a necessity. Manual annotation of the wound f…
View article: Representation Learning using Graph Autoencoders with Residual Connections.
Representation Learning using Graph Autoencoders with Residual Connections. Open
Graph autoencoders are very efficient at embedding graph-based complex data sets. However, most of the autoencoders have shallow depths and their efficiency tends to decrease with the increase of layer depth. In this paper, we study the ef…
View article: ResVGAE: Going Deeper with Residual Modules for Link Prediction
ResVGAE: Going Deeper with Residual Modules for Link Prediction Open
Graph autoencoders are efficient at embedding graph-based data sets. Most graph autoencoder architectures have shallow depths which limits their ability to capture meaningful relations between nodes separated by multi-hops. In this paper, …
View article: PURSUhInT: In Search of Informative Hint Points Based on Layer Clustering for Knowledge Distillation
PURSUhInT: In Search of Informative Hint Points Based on Layer Clustering for Knowledge Distillation Open
One of the most efficient methods for model compression is hint distillation, where the student model is injected with information (hints) from several different layers of the teacher model. Although the selection of hint points can drasti…
View article: Vehicle License Plate Detector in Compressed Domain
Vehicle License Plate Detector in Compressed Domain Open
Data compression techniques allow data size to be reduced prior to data transmission and involve decompression upon transfer. This study shows for the first time that license plate (LP) detection can be accomplished without full decompress…
View article: Phase Contrast Microscopy of cells with annotation
Phase Contrast Microscopy of cells with annotation Open
Three breast cell lines with different morphology and mobility were used in this workspace, invasive breast cancer cell line MDA-MB-231 in mesenchymal morphology; non-invasive breast cancer cell line MCF7 in epithelial morphology, and norm…
View article: Phase Contrast Microscopy of cells with annotation
Phase Contrast Microscopy of cells with annotation Open
Phase contrast Microscopy
View article: A multi-spectral myelin annotation tool for machine learning based myelin quantification
A multi-spectral myelin annotation tool for machine learning based myelin quantification Open
Myelin is an essential component of the nervous system and myelin damage causes demyelination diseases. Myelin is a sheet of oligodendrocyte membrane wrapped around the neuronal axon. In the fluorescent images, experts manually identify my…