WoS İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/394
Browse
13 results
Search Results
Conference Object Shooting a Water Slug Into an Air Column with and without Vent(Amer Soc Mechanical Engineers, 2025-07-20) Bozkus, Zafer; Dincer, Ali Ersin; Tijsseling, Arris S.; van de Ven, FonsCompressed air is used to shoot a single water slug into an upward sloping pipe with elbow and orifice at its upper end. The experiment concerns a 12 m long pipe of 0.1 m diameter connected to a 0.5 m3 air vessel. The 10 to 50 kg heavy slugs are initially at rest in the lower part of the system. Because the upper end is closed by a flange with orifice, the water slug is expected not to hit the upstream elbow. It causes - like a piston - a fast compression of the air column ahead of it. Sometimes the slug bounces back and forth, which results in a pressure oscillation of serious amplitude. Numerical simulations based on an elementary mathematical model are normally used to interpret the pressure measurements, not all of which are fully understood. Lessons learned are summarised, and suggestions for improved experiments and enhanced simulations are given. The research is of importance, for example, for steam lines where liquid condensates may collect in lower parts after power failure. Start-up of the system will then lead to rapid slug acceleration and potentially damaging impact on elbows, orifices, and machinery.Conference Object Clean Energy Production and Decarbonization of Energy Sector With Floating Photovoltaic Systems(Institute of Physics, 2025-11-01) Bajc, T.; Ozgun, F.; Koca, K.; Karipoğlu, F.Floating photovoltaic systems (FPVS) offer several advantages over traditional land-based PV systems, which has contributed to a growing global interest in their deployment. Since the energy yields are strongly dependent on location and tilt angle of FPVS, this research focuses on the clean energy production and decarbonization potential of FPVS in Serbia and Türkiye for different water bodies, such are natural and artificial lakes and dams. The research is performed for the most appropriate lakes and dams, having in mind importance of the location, energy yields potential, distance from the electricity grid and main roads, environmental impact, water depth and land type quality. Tilt angles are analyzed in a range from 5 to 40°, and the optimal angle is depicted for selected locations. The highest energy yields for Türkiye were obtained for 30° tilt angle, while for Serbia it was 36°. The results showed that possible clean energy production in both countries reaches 15345 kWh of energy in total, while the yearly carbon emissions reduction for all selected locations goes up to 10.76 tCO<inf>2</inf>/year in total. Since the legal framework for the application of FPVS is not established yet in observed countries, these results contribute to the future development of legislation in the field of FPVS and encourage the stakeholders to invest in clean energy production. © Published under licence by IOP Publishing Ltd.Conference Object Modular Floating Energy Islands With Green Hydrogen Integration: Design of a Small-Scale P2x Scheme(Institute of Physics, 2025-11-01) Akpolat, A.N.; Cundeva, S.; Todorovic, J.; Rexhepi, V.; Okhay, O.; Bakon, T.; Borg, R.P.The climate crisis and rising carbon emissions make the integration of renewable energy systems into electricity grids worldwide inevitable. In this context, modular floating energy islands (MFEI) provide innovative solutions for hybrid systems with high renewable energy penetration. This study explores the simultaneous use of various renewable resources, such as solar, wind, tidal, and wave energy, through small-scale MFEI structures that can be situated in seas and lakes. Thanks to their modular design, these systems offer benefits like scalability, portability, and ease of maintenance, allowing for flexible and adaptive developments in the energy infrastructure. As highlighted in recent literature (e.g., the North Sea Wind Power Hub and EU H2Ocean projects), offshore structures for green hydrogen production support energy storage and carbon-free fuel conversion within the Power-to-X (P2X) framework. This study evaluates the potential of photovoltaic (PV)-supported hydrogen production in MFEI structures through numerical analyses. The results emphasize the strategic role of these structures in enhancing energy security, coastal protection, and reducing carbon emissions by producing significant amounts of hydrogen. This hydrogen can be used for various purposes, including re-electrification, industrial applications, heating, and agriculture. Future research should focus on real-time data optimization, AI-supported system management, and integrated hydrogen consumption scenarios. © Published under licence by IOP Publishing Ltd.Conference Object Security Through Digital Twin-Based Intrusion Detection: A Swat Dataset Analysis(IEEE, 2023-10-18) Bozdal, MehmetDigital twin, as a virtual replica of physical entity, offer valuable insights into Industrial Control System (ICS) behavior and characteristics. Leveraging the convergence of digital twins and cybersecurity, this research explores its role in securing critical infrastructure, using the Secure Water Treatment (SWaT) system as a case study. Existing intrusion detection systems (IDS) for SWaT encounter challenges related to requiring huge amounts of a dataset for training, being unable to adopt high data dimensionality, and adaptability to emerging threats. To address these issues, a hybrid digital twin model is proposed, combining physics-based models and data-driven approaches. This model facilitates precise attack localization and explainable IDS outcomes. The method exhibits promising capabilities for enhancing critical infrastructure security and adapting to evolving cyber threats. Experimental results demonstrate the ability to detect eight out of nine attack types.Article Citation - WoS: 2High-Accuracy Identification of Durian Leaf Diseases: A Convolutional Neural Network Approach Validated with K-Fold Cross-Validation and Bayesian Optimization(Springer, 2025-11-18) Soylemez, Ismet; Nalici, Mehmet Eren; Unlu, RamazanTo address the economic losses caused by plant diseases in durian farming, this study presents an optimized deep learning model that diagnoses diseases from leaf images with high accuracy. The model's performance is maximized through Bayesian optimization and hyperparameter tuning, while its reliability is maximized through layered five-fold cross-validation. Training the convolutional neural network model on 2595 leaf images displaying six different states (five diseased and one healthy) resulted in an average test accuracy of 91.98%. This high, consistent success rate demonstrates the model's generalizability to different datasets without overfitting. While the 'Healthy' and 'Algal' classes were successfully detected with high F1-scores, there are difficulties distinguishing between the 'Blight' and 'Colletotrichum' classes due to visual similarities. This study establishes a new reference point for durian disease classification and makes a significant contribution to the development of reliable artificial intelligence-based diagnostic tools for precision agriculture.Conference Object Enhancing Complex Disease Group Scoring with Mirgedinet: A Multi-Algorithm Machine Learning Framework Based on the GSM Approach(IEEE, 2025-06-25) Qumsiyeh, Emma; Bakir-Gungor, Burcu; Yousef, MalikIntegrating biological prior knowledge for disease gene associations has shown significant promise in discovering new biomarkers with potential translational applications. This work investigates the application of a multi-algorithm machine learning framework based on the Grouping-Scoring-Modeling (G-S-M) approach for improving the prediction of complex diseases. The study identifies the primary gene and miRNA interactions in various complex diseases with the help of miRGediNET, which is a machine-learning based tool that integrates data from three biological databases. Traditional methods have only focused on independence between features; the G-S-M method focuses on aggregating genes based on biological interactions, pinpointing the scoring of gene groups for a disease, and modeling its predictive capability using advanced machine learning algorithms. In this research paper, seven algorithms, including Support Vector Machine, Decision Tree, and CatBoost, were applied to eight datasets extracted from the GEO database. This framework proved very robust in ranking gene clusters, thus predicting critical biomarkers while doing 100-fold randomized cross-validation within the evaluation. The results indicate this approach's high potential for refining disease and supporting research for choosing the best algorithm that can provide biological insights and computational advances.Conference Object High Performance and Resource Efficient Low Density Parity Check Decoder Design(IEEE, 2025-06-25) Unal, BurakLow Density Parity Check (LDPC) codes have gained popularity in communication systems due to their capacity-approaching error correction performance. In this study, a highperformance LDPC decoding algorithm with extremely low resource usage is proposed. Among the hard decision class of LDPC decoders, Gallager B (GaB) provides high-performance hardware due to its computational simplicity. However, GaB suffers from poor error-correction performance. In this study, a new intrinsic computation technique for GaB called Intrinsic Gallager B (IGaB) is introduced to improve error correction performance. Our simulation results show that the IGaB algorithm provides better error correction performance compared with GaB. GaB and IGaB algorithms are implemented on Field Programmable Gate Array (FPGA) to compare hardware performance.Conference Object Exploring Microbiome Signatures in Autism Spectrum Disorder via Grouping-Scoring Based Machine Learning(IEEE, 2025-06-25) Temiz, Mustafa; Ersoz, Nur Sebnem; Yousef, Malik; Bakir-Gungor, BurcuThe rapid increase in omic data production increased the importance of machine learning (ML) methods to analze these data. In particular, the use of metagenomic data in the diagnosis, prognosis and treatment of diseases is becoming widespread. Autism Spectrum Disorder (ASD) is a neurodevelopmental disease that occurs in early childhood and continues lifelong. The aim of this study is to increase ML performance, reduce computational costs and achieve successful classification performance using a small number of metagenomic features. In addition, disease prediction is performed; ASD associated biomarkers are determined using the microBiomeGSM on metagenomic data. Classification is performed at three different taxonomic levels (genus, family and order) using the relative abundance values of species. The best performance metric (0.95 AUC) was obtained at the order taxonomic level using an average of 416 features with microBiomeGSM. The identified ASD-related taxonomic species are presented.Conference Object Citation - WoS: 3Citation - Scopus: 4Fine Tuning DeepSeek and Llama Large Language Models with LoRA(IEEE, 2025-06-25) Uluirmak, Bugra Alperen; Kurban, RifatIn this paper, Low-Rank Adaptation (LoRA) finetuning of two different large language models (DeepSeek R1 Distill 8B and Llama3.1 8B) was performed using the Turkish dataset. Training was performed on Google Colab using A100 40 GB GPU, while the testing phase was carried out on Runpod using L4 24 GB GPU. The 64.6 thousand row dataset was transformed into question-answer pairs from the fields of agriculture, education, law and sustainability. In the testing phase, 40 test questions were asked for each model via Ollama web UI and the results were supported with graphs and detailed tables. It was observed that the performance of the existing language models improved with the fine-tuning method.Conference Object TextNetTopics+: Enhancing Text Classification Through Classifier Diversity and Model Ensembling(Springer International Publishing AG, 2025) Voskergian, Daniel; Bakir-Gungor, Burcu; Yousef, MalikTextNetTopics is an innovative text classification framework that integrates topic modeling with feature selection to improve model accuracy and interpretability. Unlike traditional methods that rely on individual words, TextNetTopics selects cohesive topics extracted via Latent Dirichlet Allocation as features for document representation, effectively reducing dimensionality while preserving the semantic structure of the text. This study evaluates the performance of TextNetTopics utilizing multiple machine learning algorithms in the M (Modeling) component, including Random Forest, Support Vector Machine, Gradient Boosting, eXtreme Gradient Boosting, and Logistic Regression. To further enhance classification performance, we introduce TextNetTopics+, an ensemblebased extension that leverages both hard voting and soft voting mechanisms to combine the strengths of multiple classifiers. Comprehensive experiments on the LitCovid and WOS datasets demonstrate that ensemble learning in TextNetTopics + significantly outperforms individual classifiers in TextNetTopics, confirming its effectiveness in improving model robustness and generalization.