Şengül Doğan

TransLPQPHOG: a new exemplar feature extraction model for intertrochanteric hip fracture detection

Ömer Esmez, Şükrü Demir, Oguz Kaya, Şükrü Şahin et autres

Automated detection of intertrochanteric hip fractures from radiographs is constrained by the limited size of available datasets and the poor interpretability of many learning-based models. Here we develop TransLPQPHOG, a compact feature-engineering framework that integrates fixed local image patches, local phase quantization, …

tr (code pays fourni par la source)

A multi-resolution hybrid deep feature extraction and ensemble learning framework for OCT-based methamphetamine addiction detection

Merve Bayrak, Deniz Dal, Prabal Datta Barua, Şengül Doğan et autres

tr, au (code pays fourni par la source)

Music-Inspired MK545Pat for AF/PAF/Non-AF Classification Using ECG Signals

Irem Ece Gulensoy, Ilknur Tuncer, Tarık Kıvrak, Ömer Faruk Göktaş et autres

Paroxysmal atrial fibrillation (PAF) may be missed on intermittent electrocardiographic (ECG) recordings. We evaluated MK545Pat, a deterministic one-dimensional descriptor derived from the first-appearance order of the notes in Mozart’s Piano Sonata K.545. The CPSC 2021 dataset contains 1436 records from 105 patients, …

tr, au (code pays fourni par la source)

Generative AI in Management Research After ChatGPT: A Bibliometric Map of Themes, Influence, and Governance

İrem Tanyıldızı Baydili, Burak Taşçı, Şengül Doğan, Türker Tuncer

Generative artificial intelligence (GenAI), particularly since the introduction of ChatGPT, has not only led to a quantitative increase in publications in management and business research but also created a qualitative transformation in research themes and collaborative structures. However, the current literature is …

tr (code pays fourni par la source)

N* algorithm: nonlinearity-perfect substitution boxes generation method for robust cryptographic systems

Fatih Uysal, Burak Taşçı, Turker Tuncer, Şengül Doğan et autres

Substitution boxes (S-Boxes) are the nonlinear cores of many symmetric ciphers. They play an important role in improving resistance against linear and differential attacks. In this article, the presented N* algorithm is introduced as a simple and reproducible method for generating 8-bit …

tr, au (code pays fourni par la source)

EPRA U-Net: an efficient pyramid residual attention framework for accurate infarct segmentation in diffusion-weighted MRI

Hasan Ulutaş, Muhammet Emin Şahin, Mustafa Fatih Erkoc, Esra Yüce et autres

Accurate identification of acute ischemic infarcts on diffusion-weighted magnetic resonance imaging (DWI) is a critical prerequisite for reliable lesion quantification and effective clinical decision support in the management of cerebrovascular events. This study presents EPRA U-Net (Efficient Pyramid Residual Attention U-Net), a …

tr, qa (code pays fourni par la source)

EPRA U-Net: An Efficient Pyramid Residual Attention Framework for Accurate Infarct Segmentation in Diffusion-Weighted MRI

Hasan Ulutaş, Muhammet Emin Sahin, Mustafa Fatih Erkoc, Esra Yuce et autres

Objective: Accurate identification of acute ischemic infarcts on diffusion-weighted magnetic resonance imaging (DWI) is a critical prerequisite for reliable lesion quantification and effective clinical decision support in the management of cerebrovascular events. Methods: This study presents EPRA U-Net (Efficient Pyramid Residual Attention …

EPRA U-Net: An Efficient Pyramid Residual Attention Framework for Accurate Infarct Segmentation in Diffusion-Weighted MRI

Hasan Ulutaş, Muhammet Emin Sahin, Mustafa Fatih Erkoc, Esra Yuce et autres

Objective: Accurate identification of acute ischemic infarcts on diffusion-weighted magnetic resonance imaging (DWI) is a critical prerequisite for reliable lesion quantification and effective clinical decision support in the management of cerebrovascular events. Methods: This study presents EPRA U-Net (Efficient Pyramid Residual Attention …

tr, qa (code pays fourni par la source)

MobileConvNeXt: An Application for Aortic Dissection Detection Using Computed Tomography Images

Serdar Derya, Erhan Akbal, Şükrü Gürbüz, Fazil Ahmet Karabulut et autres

tr, kh (code pays fourni par la source)

mHC-SSM: Manifold-Constrained Hyper-Connections for State Space Language Models with Stream-Specialized Adapters

Abdulvahap Mutlu, Şengül Doğan, Türker Tuncer

Manifold-Constrained Hyper-Connections (mHC) introduce a stability-motivated variant of multi stream residual mixing by constraining residual stream mixing matrices to the manifold of doubly stochastic matrices via Sinkhorn-Knopp projection. In his work, we study whether mHC-style constrained multi-stream residual topology transfers effectively to …

mHC-SSM: Manifold-Constrained Hyper-Connections for State Space Language Models with Stream-Specialized Adapters

Abdulvahap Mutlu, Şengül Doğan, Türker Tuncer

Manifold-Constrained Hyper-Connections (mHC) introduce a stability-motivated variant of multi stream residual mixing by constraining residual stream mixing matrices to the manifold of doubly stochastic matrices via Sinkhorn-Knopp projection. In his work, we study whether mHC-style constrained multi-stream residual topology transfers effectively to …

tr (code pays fourni par la source)

An accurate pavement crack classification using deep feature generation and iterative feature selection techniques

Prabal Datta Barua, Sreenivasulu Chadalavada, Subrata Chakraborty, Abdul Hafeez‐Baig et autres

In this work, we aimed to develop an automated asphalt fault detection model to classify pavement cracks caused by road surface deterioration. For this purpose, we used the open-access Pavement Image Dataset and constructed a balanced dataset containing 4500 labelled images from …

au, pk, by, gb, tr (code pays fourni par la source)