Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
Permanent URI for this collectionhttps://hdl.handle.net/11147/7148
Browse
4 results
Search Results
Conference Object Semantic Guided Autoregressive Diffusion Based Data Augmentation Using Visual Instructions(Institute of Electrical and Electronics Engineers Inc., 2025) Yavuzcan, Ege; Kus, Omer; Gumus, AbdurrahmanRecent breakthroughs in generative image models, especially those based on diffusion techniques, have radically transformed the landscape of text-guided image synthesis by delivering exceptional fidelity and detailed semantic control. In this study, we present an iterative editing framework that harnesses the inherent strengths of these generative models to progressively refine images with precision. Our approach begins by generating diverse textual descriptions from an initial image, from which the most effective prompt is selected to drive further refinement through a fine-tuned Stable Diffusion process. This pipeline, as detailed in our flow diagram, orchestrates a series of controlled image modifications that preserve the original context while accommodating deliberate stylistic and semantic adjustments. By cycling the augmented output back into the system, our method achieves a harmonious balance between innovation and consistency, paving the way for highquality, context-aware visual transformations. This dynamic, auto-regressive strategy underscores the transformative potential of modern image generation models for applications that require detailed, controlled creative expression. The code is available on Github. © 2025 Elsevier B.V., All rights reserved.Conference Object Df-Segdiff: Adiffusion Segmentation Model Using a New Distributed Parallel Computing Algorithm(IEEE, 2024) Mi, Hancang; Gan, Hong-Seng; Wang, Xiaoyi; Shimizu, Akinobu; Ramlee, Muhammad Hanif; Unlu, Mehmet ZubeyirBrain tumours are among the most life-threatening diseases, and automatic segmentation of brain tumours from medical images is crucial for clinicians to identify and quantify tumour regions with high precision. While traditional segmentation models have laid the groundwork, diffusion models have since been developed to better manage complex medical data. However, diffusion models often face challenges related to insufficient parallel computing power and inefficient GPU utilization. To address these issues, we propose the DF-SegDiff model, which includes diffusion segmentation, parallel data processing, a distributed training model, a dynamic balancing parameter and model fusion. This approach significantly reduces training time while achieving an average Dice score of 0.87, with several samples reaching Dice values close to 0.94. By combining BRATS2020 with the Medical Segmentation Decathlon dataset, we also integrated a comprehensive dataset containing 800 training samples and 53 test samples. Evaluation of the model using Dice, IoU, and other relevant metrics demonstrates that our method outperforms current state-of-the-art techniques.Article Citation - WoS: 4Citation - Scopus: 4Adsorption Kinetics of Methane Reformer Off-Gases on Aluminum Based Metal-Organic Framework(Elsevier Ltd., 2020) Angı, Deniz; Çakıcıoğlu Özkan, Seher FehimeSolvothermal synthesis of aluminum based metal-organic frameworks (MIL-53(Al)s) were conducted by considering the effects of crystallization and activation temperatures, and the solvent at purification step. Adsorption kinetics of Steam Methane Reformer off gas components at 34, 70 and 100 °C temperatures was measured by using ZLC method. Henry constant decreases as diffusion coefficient of the gases increases with increasing temperature; It was determined that the CO gas has the highest activation energy. Adsorption kinetics of gases were controlled with electrostatic interaction. © 2020 Hydrogen Energy Publications LLCArticle Citation - WoS: 28Citation - Scopus: 29Oxidation of Nanocrystalline Aluminum by Variable Charge Molecular Dynamics(Elsevier Ltd., 2010) Perron, A.; Garruchet, S.; Politano, O.; Aral, Gürcan; Vignal, V.We investigate the oxidation of nanocrystalline aluminum surfaces using molecular dynamics (MD) simulations with the variable charge model that allows charge dynamically transfer among atoms. The interaction potential between atoms is described by the electrostatic plus (Es+) potential model, which is composed of an embedded atom method potential and an electrostatic term. The simulations were performed from 300 to 750 K on polycrystalline samples with a mean grain size of 5 nanometers. We mainly focused on the effect of the temperature parameter on the oxidation kinetic. The results show that, beyond a first linear regime, the kinetics follows a direct logarithmic law (governed by diffusion process) and tends to a limiting value corresponding to a thickness of similar to 3 nm. We also characterized at 600 K the effects of an external applied strain on the microstructure and the chemical composition of oxide films formed at the surface. In particular, we obtained a partially crystalline oxide films for all temperatures and we noticed a strong correlation between the degree of crystallinity of the oxide film and the oxidation temperature. (C) 2009 Elsevier Ltd. All rights reserved.