İstanbul Beykent Üniversitesi Kurumsal Akademik Arşivi
DSpace@Beykent, İstanbul Beykent Üniversitesi tarafından doğrudan ve dolaylı olarak yayınlanan; kitap, makale, tez, bildiri, rapor, araştırma verisi gibi tüm akademik kaynakları uluslararası standartlarda dijital ortamda depolar, Üniversitenin akademik performansını izlemeye aracılık eder, kaynakları uzun süreli saklar ve yayınların etkisini artırmak için telif haklarına uygun olarak Açık Erişime sunar.
Güncel Gönderiler
Towards reliable solar power forecasting in Sub-Saharan Africa: An explainable hybrid AI approach for Chad
(ScienceDirect, 25.01.2026) Dagal, İdriss; Demirci, Alpaslan; Terkes, Musa; Cali, Umut
Reliable solar power forecasting is critical for expanding energy access and maintaining grid stability in Sub-Saharan Africa, where electrification rates remain low and climatic variability is substantial. This paper introduces one of the first systematic AI-based forecasting studies for Chad, employing a hybrid architecture that integrates Long Short-Term Memory (LSTM) with attention and Extreme Gradient Boosting (XGBoost). Leveraging hourly PV and meteorological data from three representative cities (Pala, Mao, and Amdjarass) across the Sudanian, Sahelian, and Saharan zones, the framework demonstrates forecasting errors consistently below 3% of average hourly PV output. Model interpretability, provided through SHAP analysis, underscores solar irradiance, temperature, and temporal indicators as dominant features, thereby strengthening transparency and user confidence. The findings extend beyond methodological contributions by revealing region-specific dynamics: rainfall-induced fluctuations in Sudanian areas highlight the need for storage and backup capacity, while the stable Saharan climate favors large-scale PV integration. By translating forecasting accuracy into practical design and policy implications, the study supports mini-grid planning, investment prioritization, and fossil-fuel displacement. These outcomes align with global sustainability objectives and highlight the role of explainable AI in enabling resilient and equitable electrification pathways in data-scarce regions.
Comparative analysis of AI-based regression models for solar power forecasting: Techniques, preprocessing, and evaluation
(ScienceDirect, 01.06.2026) Dagal, İdriss; Terkes, Musa; Demirci, Alpaslan; Gokalp, Erdin; Cali, Umut
Accurate prediction of photovoltaic (PV) power output is crucial for improving the efficiency, planning, and stability of solar energy systems. While numerous machine learning (ML) and deep learning (DL) methods have been proposed for this task, practical, implementation-focused resources that guide researchers in model selection, tuning, and evaluation remain limited. This study presents an implementation-oriented comparative analysis of widely used AI-based regression techniques for solar power forecasting. The analysis encompasses key stages including data preprocessing, model selection, performance assessment, and hyperparameter optimization using a 20-year real-world solar dataset with hourly resolution. A set of widely used supervised regression models, including k-Nearest Neighbors, Linear Regression, Ridge and Lasso Regression, Decision Tree, Random Forest, Support Vector Regression (SVR), Gradient Boosting Regressor (GBR), Bagging, Voting Regressor, Multi-Layer Perceptron (MLP)-based Artificial Neural Network, and basic Deep Learning architectures are evaluated in this study. These models are assessed using Python-based tools such as scikit-learn and TensorFlow, with a focus on reproducibility and ease of adaptation for energy system applications. Rather than proposing novel model architectures, the study aims to serve as a practical guide for researchers and engineers, offering insight into the comparative performance and usability of existing regression techniques. The findings emphasize the importance of data quality, preprocessing, and tuning strategies in determining model performance. By combining theoretical clarity, implementation guidance, and empirical evaluation using open-source Python tools, this work provides a reproducible and practical benchmark for AI-driven solar power forecasting, addressing a critical gap in implementation-focused comparative studies.
One-pot Synthesis of Functionalized Benzimidazole-quinazolinone Derivatives
(Bentham Scıence, 28.04.2026) Beker, Hüseyin Kerim; Kaban, Seniz
Introduction/Objective: Quinazolinone and aldehyde derivatives have emerged as important molecules in recent studies because of their wide spectrum of pharmacological and biological effects. They have recently attracted attention in synthesis and research. Combinatorial synthesis for this type of heterocycle has emerged in the literature over the last decade. In one-pot processes, atypical intermediates often play key roles in the overall transformation. An unusual coupling sequence occurs through nucleophilic addition to an in situ-formed Michael intermediate. This is followed by an electrocyclic cyclization step. Motivated by these findings, we focused on designing a convenient synthetic method for the preparation of benzimidazole-quinazolinone and heteroaryl aldehyde derivatives. This study aimed to create efficient MCR pathways using common starting materials to build benzimidazole and quinazolinone scaffolds.
Methods: In this study, we performed a one-pot, three-component reaction. We reacted 2- aminobenzimidazole, various substituted heteroaryl aldehydes, and dimedone in absolute ethanol. Analytical and spectroscopic data (NMR, GC-MS, IR, and UV) were used to characterize and verify the structures of the synthesized complexes.
Results: The lead was compound 4a (88% yield). This route enables efficient heterocycle assembly. GC-MS analysis confirmed that compounds 4e and 4f share the same base peak (m/z 266), suggesting a common fragmentation pathway due to structural similarities.
Discussion: An efficient one-pot method for the synthesis of benzimidazole[2,1-b]quinazolinone derivatives was developed, avoiding multi-step procedures, and spectroscopic analyses confirmed the successful formation of the target compounds, demonstrating the practicality of the method.
Conclusion: The compounds obtained represent promising starting points for structural modification, which could lead to the development of more active quinazoline-based derivatives.
Thermoluminescence properties and trap kinetics of SmCa4(BO3)3 phosphor
(ScienceDirect, 01.03.2026) Şağban, Hüseyin Muzaffer; Çin, Elif Aymila; Bulcar, Kenan; Altowyan, Abeer S.; Çoban, Mustafa Burak; Kaynar, Ümit Hüseyin; Hakami, Jabir; Topaksu, Mustafa; Can, Nurdoğan
Undoped SmCa4O(BO3)3 (SCOB) phosphor was synthesized by a microwave-assisted sol–gel combustion method and confirmed as single-phase monoclinic by X-ray diffraction. Thermoluminescence (TL) was measured after β-irradiation up to 500 Gy at a linear heating rate of 2 °C/s between room temperature and 450 °C. The glow curve at 50 Gy shows two main peaks at about 80 °C and 240 °C; after optimized preheating at 180 °C for 10 s, a single dominant peak near 247 °C remains and is used for all further measurements. The main peak shows good reusability over repeated readouts and a wide dose–response range from ∼1 to about 500 Gy without saturation. Kinetic analysis of this peak using variable heating rate, initial rise, and glow-curve deconvolution yields activation energies around 1.6–1.8 eV and frequency factors of ∼1014–1016 s−1, indicating a thermally stable trapping level suitable for dosimetric applications.
Metformin attenuates fructose-induced pulmonary fibrosis, possibly through the involvement of the TRPC6 channel
(SciELO, 26.01.2026) Akbaş, Esra; Serez, Bilkay; Erçetin, Deniz; Aydın, Muhammet Ali; Sapmaz, Melike; Kaya, Oktay
Pulmonary fibrosis is a chronic, progressive, fatal lung disease characterized by abnormal lung tissue repair and intense collagen accumulation in the lungs. Despite intensive efforts, no specific treatment has been found. The aim of this study was to investigate the effects of a high-fructose diet on lung tissue, whether the use of metformin corrects the damage caused by high fructose, and the possible relationship with transient receptor potential (TRP) channels. Lung damage was induced by adding 200 g/L fructose to the drinking water of Sprague-Dawley rats (n=32) for 10 weeks. In the groups in which the effect of metformin was examined, metformin (dissolved in saline) was administered intraperitoneally at a dose of 100 mg/kg in the last two weeks of the study. Inflammation and TRP channel levels were measured by ELISA. Histopathological evaluation was also assessed by Masson's Trichrome staining. A high-fructose diet caused collagen deposition, inflammation, and intra-alveolar hemorrhage in lung tissue. Interleukin-6 and TRPC6 channel protein levels in lung tissue were higher in the high-fructose group than in the control group. These effects were prevented by metformin treatment. Metformin administration and manipulation of TRPC6 channels may be a therapeutic target for the treatment of pulmonary fibrosis.
