Graduate School of Informatics, Thesis

Item Usage Stats

Browse

Search within this collection:

Filters

Entity Type
Thesis (1035)

Has File(s)
Yes (1010)
No (25)

Author
Akkoyun, Emrah (2)
Akyol, Mehmet Ali (2)
Alaşehir, Oğuzhan (2)
Albayrak, Samet (2)
Alkan, Sarper (2)

Subject
Engineering and Technology (219)
Social Sciences and Humanities (97)
Natural Sciences (51)
Computer software (33)
Computer software. (33)

Date Issued
1998 - 1999 (3)
2000 - 2009 (206)
2010 - 2019 (495)
2020 - 2026 (331)

Item Type
Master Thesis (782)
Ph.D. Thesis (253)

Recent Submissions

Regime-aware day-ahead electricity consumption forecasting for Türkiye: A meta-learning-based ensemble approach Savaş, Alp Demir; Koçyiğit, Altan; Department of Information Systems (2026-6) Day-ahead electricity consumption forecasting is very important for power system operation, market planning, and reserve scheduling. This thesis focuses on developing accurate day-ahead electricity consumption profiles for...
Generative Modeling of Strong Ground Motion Records Using Attention-Based Variational Autoencoders Hekimoğlu, Nevin Şehbal; Akagündüz, Erdem; Tileylioğlu, Salih; Department of Modeling and Simulation (2026-4-30) Reliable characterization of strong ground motion variability is fundamental at every stage of modern seismic hazard assessment. However, the empirical record remains sparse for many critical combinations of source, path, ...
GENERATING PARKINSONIAN LFP SIGNALS WITH CONDITIONAL DIFFUSION MODEL Ekiz, Merve; Özkurt, Tolga Esat; Department of Data Informatics (2026-4-17) Local field potentials (LFP) are brief, summed electrical signals that reflect synchronous neuronal activity and are produced in nerves and other tissues, such as neurons. Furthermore, in the detection of Parkinson's disea...
MULTI-VIEW MULTIMODAL BEV PERCEPTION FOR CENTERLINE-CENTRIC ROAD TOPOLOGY UNDERSTANDING WITH TRANSFORMER DECODERS Kalfaoğlu, Muhammet Esat; Temizel, Alptekin; Department of Modeling and Simulation (2026-4-16) This thesis studies transformer-based road topology understanding with centerline-centric representations and their relations to traffic elements. The core problem is to jointly model geometry and topology in complex urban...
ANALYSIS AND COMPARISON OF STATIC APPLICATION SECURITY TESTING TOOLS AND COMMON TOOL MECHANISMS Seren, Ata; Tezcan, Cihangir; Department of Cybersecurity (2026-4-14) Static Application Security Testing (SAST) tools play a critical role in identifying vulnerabilities during software development which enables early-stage security and mitigate security risks in production. However, their ...
MUTATION-CENTRIC GRAPH NETWORKS: INTEGRATING LOCAL AND DISTAL GENOMIC CONTEXT Hüseynov, Ramal; Otlu Sarıtaş, Burçak; Department of Bioinformatics (2026-4-13) Somatic mutations drive the transformation of normal cells into cancer, yet the vast majority occur within non-coding regions, where their functional consequences remain poorly under- stood. A key challenge is that non-cod...
EXPLORING HUMAN FACTORS IN LARGE LANGUAGE MODEL-ASSISTED SOFTWARE REQUIREMENTS SPECIFICATION Kocakaya, Başak Düşün; Özcan Top, Özden; Yürüm, Ozan Raşit; Department of Information Systems (2026-4-3) Large Language Models (LLMs) are being integrated into multiple phases of the software development life cycle, from requirements specification to maintenance. LLMs' technical benefits on software development, such as accel...
ESTIMATING HAPTIC PARAMETERS FROM HUMAN PREFERENCES: A BAYESIAN ACTIVE LEARNING APPROACH, Toraman, Rojda; Yet, Barbaros; Department of Cognitive Sciences (2026-1-22) Reproducing natural haptic sensations through artificial mechanical systems is a fundamental challenge in robotics. While haptic devices are controlled by precise numerical parameters, human perception of natural objects r...
Assessment of AI-generated front-end code quality: a comparative study Güler, Umut; Eren, Pekin Erhan; Department of Information Systems (2026-1-20) The adoption of AI coding tools has significantly transformed software development practices, yet empirical evidence regarding the technical quality of AI-generated code and applications remains limited, particularly for m...
Enhancement of Demand Forecasting for Agrochemical Products Through Advanced Analytics Kaya, Gizem; Eren, Pekin Erhan; Department of Data Informatics (2026-1-20) Demand forecasting is an essential part of supply chain planning. Accurate prediction of sales directly affect the resource efficiency and success of inventory management process. However it is especially challenging for s...
A Hybrid Deep Learning Framework for Advanced Detection of Domain Generation Algorithms Düztaş, Sinan; Tezcan, Cihangir; Department of Cybersecurity (2026-1-16) Cyber threat actors (CTAs) rely on botnets to carry out a wide range of malicious operations. These botnets are controlled by command-and-control (C2) servers. If these servers are exposed, CTAs can be detected and their a...
DATA GOVERNANCE CAPABILITY MATURITY MODEL Gökalp, Selin; Koçyiğit, Altan; Department of Information Systems (2026-1-16) Organizations increasingly witness data as a strategic asset, but quite a few of organizations still confront significant difficulties in the development of coherent and scalable data governance practices that can create v...
ENHANCING SPLICE VARIANT PREDICTION: EVALUATING BIOINFORMATICS TOOLS AND THE IMPACT OF TRAINING DATA IN THE CONTEXT OF GENETIC DISORDERS Güney Tamer, Elif; Aydın Son, Yeşim; Çavdarlı, Büşranur; Department of Medical Informatics (2026-1-15) Accurate identification of splice-altering genetic variants is critical for understanding disease mechanisms and improving clinical variant interpretation. Although deep learning–based splice prediction tools perform well ...
MORTALITY SALIENCE AND RISK-TAKING IN DECISION MAKING: CAUSAL AND COGNITIVE MODELLING OF BEHAVIORAL AND NEURAL MECHANISMS Başerdem, Elif Öykü; Yet, Barbaros; Department of Cognitive Sciences (2026-1-14) The replication crisis poses a significant challenge for Terror Management Theory (TMT), particularly regarding the link between Mortality Salience (MS) and risk-taking. While TMT argues that reminders of mortality directl...
Aligning Reviewer Guidelines and Reviewer Feedback: A Data-Driven Study Tanrısever, Özer; Taşkaya Temizel, Tuğba; Department of Data Informatics (2026-1-14) Academic venues have established reviewer guidelines to enable standardized evaluation. This study proposes a framework designed to categorize reviewer inquiries and systematically measure their alignment with institutiona...
AN INTEGRATED COMPUTATIONAL APPROACH FOR AI-ASSISTED BIM ANALYTICS AND DIGITAL TWIN DEVELOPMENT Şahin, Nilsu; Sürer, Elif; Department of Data Informatics (2026-1-14) Building Information Modeling (BIM) integrates geometric representations with structured spatial and functional data, enabling reuse in interactive and operational digital twin applications beyond design and construction. ...
An LLM-Driven Framework For Automatic Curriculum Learning To Enhance Generalization In Open-Ended Reinforcement Learning Orakcı, Olca; Sürer, Elif; Department of Modeling and Simulation (2026-1-14) Reinforcement Learning research has long sought to achieve generalization. The benchmark environments gradually evolved over the years to achieve this demanding task. As environments became more complex and generalization-...
ID-SDM: EXTENDING INFLUENCE DIAGRAMS FOR SHARED DECISION-MAKING AND CLINICIAN-PATIENT RELATIONSHIP YILDIRIM, ZELIHA; YET, BARBAROS; Department of Cognitive Sciences (2026-1-13) Shared Decision-Making (SDM) is a patient-centered healthcare approach emphasizing patients as equal partners with physicians in a two-way information exchange. This dissertation introduces a novel framework, ID-SDM (Influ...
PREDICTION OF SURGICAL DURATIONS USING MACHINE LEARNING METHODS Yiğit, Esin; Acar, Aybar Can; Department of Bioinformatics (2026-1-13) Accurate prediction of surgical case durations is essential for effective operating room (OR) scheduling and hospital resource management. However, many hospitals still rely on manually entered surgery times, which contain...
AN ADAPTIVE HYBRID EXTREME-VALUE FRAMEWORK FOR DAILY VALUE-AT-RISK ESTIMATION IN THE TURKISH EQUITY MARKET Kulu, Ali Rıfat; Koçyiğit, Altan; Department of Information Systems (2026-1-12) Standard risk management frameworks, particularly those relying on the Value-at-Risk (VaR) metric under normality assumptions, might fail to capture the extreme volatility observed in emerging markets. This thesis evaluate...

Citation Formats