Welcome to IKU Academic Digital Archive System
OpenAccess@IKU is Istanbul Kultur University's Academic Digital Archive System, established in June 2014 to digitally store and provide open access to academic and artistic outputs in line with international standards and intellectual property rights. The system includes various outputs such as articles, presentations, theses, books, book chapters, reports, encyclopedias, and works of art produced by the university's faculty members and students.
IKU University is a leading institution using UniSpace.
Recent Submissions
Deep Learning-Based Classification of Software Bugs Using Code Context and AST Features
(IEEE, 2025) Gökcen, Alpaslan; ARŞIK, ARDA; AKBULUT, AKHAN; Çatal, Çağatay
A software component plagued with bugs is likely to experience both functional and non-functional difficulties, such as usability, performance, and security issues. These bugs can range from improper layouts to system crashes and security vulnerabilities. In this research, we developed a deep learning-based model to classify software bugs based on preceding and corrected code statements. Preprocessing includes extracting features from the Abstract Syntax Tree (AST) by traversing the tree to capture node types and relationships, then encoding the AST into a numerical vector representation for classification. Using AST and padding methods, features are extracted from code statements for use in a Convolutional Neural Network (CNN) model. We proposed a CNN-based model with AST-based feature extraction for large-scale software bug classification and evaluated on 153,652 bug samples from 1,000 GitHub projects. Compared to traditional datasets, this large dataset presents challenges in building accurate prediction models. This model is particularly useful in continuous integration (CI) pipelines, where it can automatically detect problematic code during the build process, helping to identify bugs faster and reduce manual review.
Structural, Optical, and Dielectric Studies on Transition Metals Doping (Cu, Ni) in MgFe2o4 Ferrites
(Elsevier Ltd., 2025) Dhahri, Siwar; Omri, Aref; Dhaou, Mohamed Houcine; Dhahri, Essebti; Graça, Manuel P.F.; Brito, Anna B.; FAUSTO, RUI; Pina, João; Costa, Benilde F.O.
Spinel ferrites are increasingly researched for their tunable optical and electrical properties, with applications in electronic devices and microwave absorption. This study investigates Mg0.5Cu0.3Ni0.2Fe2O4 synthesized via sol-gel auto-combustion, yielding a single-phase cubic spinel structure (Fd-3m) with crystallite sizes of ∼1.1 μm. XRD and Raman spectroscopy confirmed the phase purity and identified five active modes (A1g, Eg, 3T2g). Optical analysis revealed a direct bandgap (Eg = 2.335 eV), low Urbach energy (Eu = 0.2386 eV), and strong UV–Vis absorption, indicating high crystallinity and suitability for optoelectronics. Electrical measurements demonstrated semiconducting behavior with an activation energy (Ea) of 0.34 eV, governed by the Correlated Barrier Hopping (CBH) model. Dielectric studies showed high permittivity (ε' > 103 at low frequencies) and significantly reduced loss (tan δ < 0.1 at 106 Hz), confirming efficacy in high-frequency energy transmission/storage. The synergistic Cu/Ni doping enables tailored structural, optical, and dielectric properties, positioning this material as a promising candidate for high-frequency electronics, energy storage systems, and solar cells.
Development of Agriculture in Turkey and Changing Dynamics: Factor Analysis Approach
(Springer Science and Business Media Deutschland GmbH, 2025) ÇELEBİ, HASAN HÜSEYİN; Paksoy, Ayşe
This study investigates the factors affecting agricultural productivity in Turkey from 1990 to 2023 using factor analysis. As the global population increases, understanding the variables that influence crop yields becomes crucial for sustaining the food supply. The research examines data such as average temperature, rainfall, inflation rates, and fuel prices, sourced primarily from the Turkish Statistical Institute. By applying factor analysis, the study groups these variables into meaningful clusters that reveal the underlying correlations between them and agricultural outputs like wheat, barley, rice, and corn. The results indicate that certain economic and environmental factors, such as consumer inflation and annual average temperature, consistently influence multiple crops. This research contributes a new perspective to the literature by identifying the key factors that drive agricultural productivity in Turkey, providing insights that can inform future agricultural policies. The study concludes with suggestions for further analysis involving a broader range of variables to enhance understanding of the complex dynamics in Turkish agriculture.
Experimental and Finite Element Analysis Evaluation of the Effect of Variable Parameters on Tensıle Capacity in Knife Plate Connections
(Springer Science and Business Media Deutschland GmbH, 2025) AYDIN, ELİF; Alemdar, Fatih
Welded knife plate connections are widely used in steel bridge construction and play a critical role in structural elements subjected to variable and repeated loading, particularly due to traffic-induced dynamic effects. These connections are vulnerable to fatigue-related damage over time, potentially compromising structural integrity. Therefore, understanding the influence of key parameters on the tensile capacity of such connections is essential for ensuring safe design, extending service life and achieving cost-effective structural solutions.This study systematically investigates the effects of weld length, the gap between the knife plate and the hollow structural section (HSS) and various profile geometries on the tensile performance of knife plate welded connections. Unlike most previous studies that focus on a single parameter, this research adopts a comprehensive parametric approach and contributes to a deeper understanding of the interactions between multiple design variables. The methodology integrates experimental testing with numerical simulations conducted using the ABAQUS finite element software. A total of 15 full-scale tensile experimental tests were carried out and the results were compared with numerical predictions. The findings indicate a strong correlation between the experimental and numerical results with the finite element model achieving over 90% accuracy. These results validate the reliability of the numerical approach and demonstrate its potential to reduce dependence on experimental testing in future optimization and design studies offering significant savings in both time and cost.
Data-Driven Machine Learning Approaches to Demand Forecasting in Supply Chain Management
(IEEE, 2025) ALREFAAI, SAFA; ERMİŞ, MURAT
This study explores pharmaceutical demand forecasting by integrating statistical analysis and machine learning within the context of supply chain management. The dataset, from a pharmaceutical manufacturer, includes six drug categories and around 240 products. Initial data exploration was conducted using Power BI to understand the structure and trends. Statistical models, namely Moving Averages, Single Exponential Smoothing, Trend Analysis, and ARIMA, were applied, focusing specifically on Acantaine (Antibiotics class) for detailed analysis. Machine learning models were trained on the full dataset to improve generalization, but testing was focused on Acantaine, with accuracy metrics computed. A comparative analysis showed that machine learning models, especially Random Forest, significantly outperformed traditional statistical methods in forecasting accuracy. The study underscores the value of machine learning in enhancing prediction and supporting strategic decisions in pharmaceutical supply chains.