https://hdl.handle.net/11436/924 Fri, 25 Sep 2026 01:46:46 GMT 2026-09-25T01:46:46Z https://hdl.handle.net/11436/10920 The effectiveness of deep learning in the differential diagnosis of hemorrhagic transformation and contrast accumulation after endovascular thrombectomy in acute ischemic stroke patients Beyazal, Mehmet; Solak, Merve; Tören, Murat; Asan, Berkutay; Kaba, Esat; Çeliker, Fatma Beyazal Objectives: Differentiation of hyperdense areas on non-contrast computed tomography (NCCT) images as hemorrhagic transformation (HT) and contrast accumulation (CA) after endovascular thrombectomy (EVT) in acute ischemic stroke (AIS) patients are critical for early antiplatelet and anticoagulant therapy. This study aimed to predict HT and CA on initial NCCT using deep learning. Material and Methods: This study was conducted between January and December 2024. The study included 556 images of 52 patients (21 female and 31 male) who underwent EVT due to AIS, with hyperdense areas observed in the NCCT examination within the first 24 h post-EVT. The evaluated images were labeled as ‘contrast accumulation’ and ‘hemorrhagic transformation’. These labeled images were trained with nine different models under a convolutional neural network (CNN) architecture using a large dataset, such as ImageNet. These models are DenseNet201, InceptionResNet, InceptionV3, NASNetLarge, ResNet50, ResNet101, VGG16, VGG19 and Xception. After training the CNN models, their performance was evaluated using accuracy, loss, validation accuracy, validation loss, F1 score, Receiver Operating Characteristic (ROC) Curve, confusion matrix, confidence interval, and p-value analysis. Results: The models trained in the study were derived from 556 images in data sets obtained from 52 patients; 186 images in training data for CA and 186 images training data for HT (with an increase to 558 images), 115 images used for validation data, and 69 images were compared using test data. In the test set, the Area Under the Curve (AUC) metrics showing sensitivity and specificity values under different cutoff points for the models were as follows: DenseNet201 model AUC = 0.95, InceptionV3 model AUC = 0.93, NasNetLarge model AUC = 0.89, Xception model AUC = 0.91, Inception_ResNet model AUC = 0.84, Resnet50 and Resnet101 models AUC = 0.74. The InceptionV3 model demonstrates the best performance with an F1 score of 0.85. Recall scores generally ranged between 0.62 and 0.85. Conclusions: In our study, hyperdensity areas in initial NCCT images obtained after EVT in AIS patients were successfully differentiated from HT and CA with high accuracy using CNN architectures. Our findings may enable the early identification of patients who would benefit from anticoagulation or antiplatelet therapy to prevent re-occlusion or progression after EVT. Wed, 01 Jan 2025 00:00:00 GMT https://hdl.handle.net/11436/10920 2025-01-01T00:00:00Z https://hdl.handle.net/11436/10851 Design and initial experimental verification of a high-speed electrodynamic levitation measurement system utilizing modular magnetic field sources and aluminium rails Öztürk, U. Kemal; Mollahasanoğlu, Hakkı; Abdioğlu, Murat; Okumuş, Halil İbrahim; Gedikli, Hasan This work presents design and development of a modular high-speed electrodynamic levitation (EDL) test system that integrates advanced magnetic field configurations and real-time control capabilities at high operational speeds. The system comprises a rotating aluminium rail and interchangeable magnetic field sources, including permanent magnet array (PMA) and high-temperature superconducting (HTS) bulk, allowing for a variety of experimental configurations. The initial experimental results focused on testing the system through PMA–aluminium rail and HTS–aluminium rail configurations. A key innovation of this system is its modular structure, which allows for easy replacement and reconfiguration of magnetic components and rail geometries. The adaptability of the system enables a thorough investigation of how different magnetic field sources influence magnetic force and dynamic stability at high speeds. Furthermore, the system is fully integrated with a programmable logic controller (PLC) and supervisory control and data acquisition (SCADA) interface, enabling precise real-time monitoring, synchronized control and automatic data acquisition. Experimental results demonstrate the system's capability to measure vertical displacement variations and force fluctuations at different speeds, with resonance effects identified around 145 km/h. The levitation forces of 99 N were measured at a gap of 10 mm, with the PMA at a maximum speed of 283 km/h above an aluminium rail, while it was measured as 16 N with HTS at a vertical gap of 9 mm. This flexible test platform provides a critical foundation for determining the force parameters of the real-scale EDL Maglev technologies and advancing their practical application potential in high-speed transportation. Wed, 01 Jan 2025 00:00:00 GMT https://hdl.handle.net/11436/10851 2025-01-01T00:00:00Z https://hdl.handle.net/11436/10836 The investigation of electronic and photocatalytic characteristics of van der Waals WSeTe/GaSe heterostructures: the frist principles study Yelgel, Celal; Yelgel, Övgü Ceyda The development of efficient photocatalysts is essential to addressing global energy demands and mitigating environmental degradation. Two-dimensional (2D) materials have emerged as promising candidates for photocatalytic applications due to their large surface area, tunable band structures, and short charge carrier diffusion lengths. Among them, group-III monochalcogenides and Janus transition metal dichalcogenides (TMDs) have garnered significant interest for solar-driven water splitting, owing to their suitable band edge positions and inherent structural asymmetry. In this work, we propose a novel van der Waals (vdW) heterostructure composed of WSeTe and GaSe monolayers, systematically investigated via first-principles calculations. The heterostructure demonstrates thermodynamic stability, with a low lattice mismatch of 0.47% and a binding energy of -8.6 meV/atom. Electronic structure analysis reveals a type-I band alignment and a direct band gap of 0.849 eV. Notably, the built-in electric field at the interface promotes spatial separation of photoexcited carriers, reducing recombination losses. The conduction and valence band edges of the WSeTe/GaSe heterostructure straddle the water redox potentials, confirming its viability for overall photocatalytic water splitting under neutral conditions. In addition, the strong light absorption in the visible spectrum, coupled with favorable charge transport properties, enhances its potential for integrated optoelectronic and energy conversion systems. This study offers fundamental insights into the interfacial physics of 2D Janus-based heterostructures and presents WSeTe/GaSe as a promising platform for next-generation photocatalysis. Wed, 01 Jan 2025 00:00:00 GMT https://hdl.handle.net/11436/10836 2025-01-01T00:00:00Z https://hdl.handle.net/11436/10827 A review of machine learning approaches for the discovery of thermoelectric materials Yelgel, Övgü Ceyda; Yelgel, Celal Thermoelectric (TE) materials have garnered significant interest due to their capacity to convert heat directly into electrical energy and vice versa, offering a sustainable route for energy harvesting and waste heat recovery. Nevertheless, many of the high-performance TE materials reported to date rely on elements that are scarce, costly, or environmentally hazardous, thereby limiting their large-scale deployment. To overcome these challenges, the development of efficient, earth-abundant, and environmentally benign alternatives is essential. Although first-principles methods provide valuable insights into the transport behavior of potential TE materials, their high computational cost restricts their utility in large-scale material screening. Recent progress in computational infrastructure, along with the advent of data-centric approaches such as machine learning (ML), has transformed the landscape of thermoelectric research. ML algorithms, trained on comprehensive datasets including experimental measurements, crystallographic data, and density functional theory (DFT) results can predict key TE metrics, such as the figure of merit (ZT), with remarkable speed and accuracy. This review explores the integration of ML into TE materials discovery, emphasizing its role in property prediction, descriptor engineering, and structural optimization. A systematic examination of ML-driven strategies promises to accelerate the discovery process and improve the efficiency of next-generation thermoelectric systems. Wed, 01 Jan 2025 00:00:00 GMT https://hdl.handle.net/11436/10827 2025-01-01T00:00:00Z