İZÜ Araştırma ve Akademik Performans Sistemi
DSpace@İZÜ, İstanbul Sabahattin Zaim Üniversitesi’nin bilimsel araştırma ve akademik performansını izleme, analiz etme ve raporlama süreçlerini tek çatı altında buluşturan bütünleşik bilgi sistemidir.
Güncel Gönderiler
Öğe Türü: Yayın , SVR-Based Cryptocurrency Price Prediction Using a Hybrid FISA-Rao and Firefly Algorithm for Feature and Hyperparameter Selection(MDPI, 2025) Er, Merve; Bayaz, Kenan; Fırat, Seniye ÜmitFinancial forecasting is a challenging task due to the complexity and nonlinear volatility that characterize modern financial markets. Machine learning algorithms are very effective at increasing prediction accuracy, thereby supporting data-driven decision making, optimizing pricing strategies, and improving financial risk management. In particular, combining machine learning techniques with metaheuristic algorithms often leads to significant performance improvements across various domains. This study proposes a hybrid framework for cryptocurrency price prediction, where Support Vector Regression (SVR) with radial basis function kernel is used to perform the prediction, while a Firefly algorithm is employed for correlation-based feature selection and hyperparameter tuning. To improve search performance, the parameters of the Firefly algorithm are optimized using the Fully Informed Search Algorithm (FISA) which is an improved version of the parameterless Rao algorithm. The model is applied to hourly data of Bitcoin, Ethereum, Binance, Solana and Ripple, separately. The model’s performance is evaluated by comparison with Gated Recurrent Unit (GRU), Multilayer Perceptron (MLP), and SVR methods using MSE, MAE, and MAPE metrics, along with statistical validation by Wilcoxon’s signed-rank test. The results show that the proposed model achieves a superior accuracy and demonstrate the critical importance of feature selection and hyperparameter tuning for achieving accurate predictions in volatile markets. Moreover, customizing both feature sets and model configurations for each cryptocurrency allows the model to capture distinct market characteristics and provides deeper insights into intra-day market dynamics.Öğe Türü: Yayın , Diversity, Equity, Inclusion and Belonging in Higher Education: The Case of Indiana University(Ali Khorsandi Taskoh, 2025) Töre, Esra; Töre, EsraThis study aims to analyze the theme of the IndianaUniversity Office of the Vice President for Diversity, Equity, and Inclusion's (OVPDEI) Annual Reports (2021-2022, 2022-2023). This research employs a qualitative research methodologywiththematic and social network analysis as its methodological frameworks. The 2021-2022 OVPDEI Annual Report identified four main themes—Diversity, Equity, Inclusion, and Belonging (DEIB)—encompassing 16 sub-themes. The 2022-2023 OVPDEI Annual Report retained the same four primary themes —encompassing 16 sub-themes. However, it evolved its approach, reflecting a shift toward systemic and data-driven strategies. Both reports share recurring themes such as community engagement, cultural competency, and support mechanisms, which remain critical to fostering inclusion and belonging. However, the 2022-2023 report introduced unique elements such as policy development, feedback, and adaptation. The evolution from broad foundational efforts in 2021-2022 to actionable, systemic strategies in 2022-2023 mirrors best practices in higher education that prioritize representation and structural change. This study highlights Indiana University's progression in addressing DEIB through increasingly targeted and systemic initiatives. The shift from foundational approaches in 2021-2022 to more robust, data-driven strategies in 2022-2023 demonstrates the institution's responsiveness to evolving challenges and priorities.Esra Tore*Keywords: Diversity; Equity; Inclusion; Belonging; U.S. Higher Education; Indiana University*Corresponding author’s email: esra.tore@izu.edu.tr; esratore@iu.eduÖğe Türü: Araştırmacı , Bölüktaş, Rukiye PınarProf. Dr.Öğe Türü: Araştırmacı , Erduran, Mustafa NizamettinProf. Dr.Öğe Türü: Yayın , Advanced Glycation End Products: A Promising Prognostic Indicator in Breast Cancer Patients(Karger, 2025) Erdal, Gülçin Şahingöz; Işıksaçan, Nilgün; Cikot, Murat; Yaman, Mustafa; Yıldırım Servi, Esra; Ede Çintesun, Elif; Kalkanlı Taş, Sevgi; Tasci, Tamay Seda; Kocamaz, Nursel; Karabulut, Dilay; Yaman, Mustafa; Yıldırım Servi, Esra; Çintesun, Elif EdeIntroduction: Advanced glycation end products (AGEs) form through long-term reactions between proteins/lipids and sugars, accumulating in tissues and contributing to disease. AGEs are linked to cancer progression, with studies showing associations with colon and pancreatic cancer. Methods: This study investigates the relationship between AGEs and breast cancer. Stage 2–3 breast cancer patients and age-matched healthy controls were included. Exclusion criteria were diabetes, renal/liver disease, chronic inflammation, and infection. Blood samples were collected from patients pre-surgery and 48 h post-surgery and once from fasting controls. Glyoxal (GO) and methylglyoxal (MGO) levels were measured via liquid chromatography. A total of 60 breast cancer patients and 21 controls participated. Results: GO and MGO levels were significantly higher in patients than controls (p < 0.001) and decreased post-surgery. No significant differences were found between breast cancer subtypes. AGE levels did not correlate with age, lymph node involvement, or menopause status. Conclusion: The significant drop in AGE levels post-surgery suggests tumor burden influences AGE levels. While their predictive value remains uncertain, AGEs could serve as prognostic biomarkers. Monitoring AGEs may encourage lifestyle changes, and rising levels might indicate cancer recurrence or progression.
