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
Empowering Education Through Virtual Reality-Driven Course and Examination System
(IEEE, 2025) YILDIZ, MEHMET SEDAT; MUSTAFAOĞLU, BERKAY; ELMASRY, WİSAM
This paper presents the development of "Virtual Academy", a Virtual Reality (VR)-based application designed to ensure uninterrupted access to education, particularly in scenarios where physical attendance in classrooms is challenging. The platform enables students to log in via personal credentials, granting access to assigned courses within an immersive virtual classroom. Teachers and students interact in real-time, with educators leveraging audiovisual tools to enhance the learning experience. The system also supports lesson recording for future reference, evaluates the performance of the students via designated exams, and facilitates a seamless transition to remote learning. By harnessing modern VR technology, Virtual Academy enhances educational continuity and offers an interactive and engaging alternative to traditional learning environments.
UTA Method for Sustainable Decisions in Ceramic Tile Production
(Springer Science and Business Media Deutschland GmbH, 2025) KAÇAR, YAREN; BİÇER, SENA İREM; FİLİZ, AYBERK; DURMUŞ, EMİNE ŞEYMA; KUŞ, DUYGU; GERGİN, ZEYNEP
Efforts to minimize environmental damage have gained global importance due to critical issues such as climate change and the depletion of natural resources. In this context, manufacturing industries have increasingly prioritized environmental protection goals alongside profitability when planning their operations. With growing customer awareness and regulatory pressures, such as EU directives and governmental regulations, a focus on sustainability has become both a competitive advantage and a necessity. Consequently, companies are adopting sustainability-oriented approaches, including environmentally friendly material selection from raw materials to packaging. This trend toward sustainability-oriented production planning is also evident in the ceramic industry, the focus of this study. The main raw materials for ceramic products—clay, quartz, and feldspar—are extracted from mines, but their supply is becoming increasingly difficult and costly due to dwindling natural resources. As a result, sustainability-driven competition in the sector has prompted companies to seek more sustainable alternatives for these natural materials. This study aims to assist a manufacturing company in the ceramic sector with its sustainability-focused raw material selection process. The study's objective is to identify production recipes that minimize costs while using sustainable raw materials for floor tile production. The Utility Additive (UTA) multi-criteria decision-making (MCDM) method is applied to evaluate alternative recipes. These recipes incorporate environmentally friendly raw materials, such as recycled products and wastewater. Twelve criteria are initially identified and categorized under sustainability, cost, and manufacturability to guide the decision-making process. The UTA method is then used to determine the order of preference for five different recipes, and two scenarios are evaluated based on changes in the weights of the decision criteria.
Music Generation Using RNN-LSTM with Self-Attention Mechanism
(IEEE, 2025) ABDELALIM, MAHMOUD; BASHAR, MOHAMMAD; NEMER, HAZEM; ELMASRY, WİSAM
Music generation using artificial intelligence is a rapidly evolving domain that bridges the gap between creativity and computational intelligence, offering promising applications in entertainment, education, and therapy. In this paper, a Recurrent Neural Network (RNN) model with Long Short-Term Memory (LSTM) networks for music generation was employed, utilizing the Pretty Midi library. Features were extracted from MIDI files in the dataset and fed these notes into a model composed of three LSTM layers. To prevent overfitting, dropout layers were incorporated. The model was trained on a diverse set of MIDI files, allowing it to capture various musical styles and patterns. The trained model demonstrated high accuracy in music generation, producing coherent and stylistically consistent pieces. Experimental results show that the LSTM + Self-Attention model outperformed baseline RNN, LSTM, and BiLSTM models, achieving the lowest validation loss (0.47), confirming its effectiveness for the complex task of music generation.
Graph Based Business Process Anomaly Detection with Edge Feature Reconstruction and Advanced Linear Networks
(IEEE, 2025) Ayaz, Teoman Berkay; Çevik, Rabia; Özcan, Alper; AKBULUT, AKHAN
Business Process Management (BPM) as an inter-disciplinary field between Managerial Sciences and Computer Science is a subject ever-increasing in importance. This holds more and more true as the business landscape becomes faster and more complex each passing day. Given the management of a businesses operational activities is essential to maintain a healthy lifecycle, the early detection of these inefficiencies and potentially malicious activity becomes more and more crucial. As these deviations can significantly impact a businesses lifecycle, anomaly detection solutions in this domain is that much more lucrative. The pursuit of detecting these deviations gave rise to the field of Business Process Anomaly Detection. Building upon previous research, our study focuses on constructing an advanced Graph Autoencoder (GAE) architecture using various graph convolutional operators, and boost the performance further with advanced linear networks. By comprehensively evaluating 3 distinct encoder architectures and 4 distinct decoder selections, our study comprehensively evaluates the possible ways to combine various encoders and decoders on 6 distinct datasets. The empirical results show a wide range of results with varying trends between different encoder-decoder combinations, ranging from 0.674 to 0.219 F1-score in anomaly detection performance.
ASL UNDERPRESSURE: Gamification of American Sign Language Learning Through Human-Computer Interaction
(IEEE, 2025) ATIA, OSAMA; ASSKAR, HUSSAM; EL KHARCHY, OUSSAME; ELMASRY, WİSAM
ASL Underpressure is an innovative web-based game that utilizes video processing and deep learning models to improve the practice of American Sign Language (ASL) and bridge the communication gap between hearing and deaf communities. The game focuses on education and improving communication skills by challenging players to quickly and accurately form words using the ASL alphabet. The system incorporates a timer to maintain player engagement and allows for multiple attempts per word to encourage learning and mastery. This paper demonstrates the potential of technology to improve communication and foster understanding between diverse communities.