FSM Vakıf Üniversitesi Araştırma ve Akademik Performans Sistemi
DSpace@FSM, FSM Vakıf Üniversitesi’nin bilimsel araştırma ve akademik performansını izleme, analiz etme ve raporlama süreçlerini tek çatı altında buluşturan bütünleşik bilgi sistemidir.
Güncel Gönderiler
Öğe Türü: Öğe , Assessing Carbonation Maturity for Restoration Compatibility: A Spectroscopic–Mineralogical Study of Historic and Modern Lime Mortars(MDPI, 2026) Ceran, İrem; Kaygısız, ErsinUnderstanding the carbonation behavior of lime-based mortars is essential for ensuring material compatibility and long-term durability in architectural restoration. This study presents a comparative spectroscopic and mineralogical analysis of eleven mortar samples collected from both the original (11th–12th century) and modern extension walls of a historic structure. X-ray diffraction (XRD) and attenuated total reflectance–Fourier transform infrared spectroscopy (ATR-FTIR) were employed to assess the mineralogical composition and carbonation maturity. The results indicate that the historic mortars have undergone complete carbonation, as evidenced by sharp and well-defined calcite bands, whereas the modern repair mortars display broader carbonate peaks, suggesting ongoing carbonation processes. XRD analysis confirmed the dominance of calcite and gypsum, along with the presence of illite, albite, and microcline, indicating mineralogical signatures of both binder transformations (such as carbonation and sulfate formation) and aggregate contributions. The weak water absorption bands and limited sulfate signals observed in the spectra further suggest advanced aging and mineral stabilization in the historic mortars. These findings highlight the differing carbonation kinetics between historic and modern lime mortars and emphasize the importance of selecting repair materials with compatible chemical and physical aging characteristics. The combined use of XRD and ATR-FTIR proves to be an effective diagnostic approach to guide restoration material selection and support the long-term integrity of masonry structures.Öğe Türü: Öğe , Bridging Engineering and Neuro-Oncology: A Scalable FastAPI-Deployed CNN Framework for Real-Time Explainable Brain Tumor Diagnosis(Frontiers in Neuroscience, 2026) Nematzadeh, Sajjad; Anka, Ferzat; Çiftçi, Fatih; Ayanoğlu, Kadriye Yasemin Usta; Özarslan, Ali Can; Öncü, EmirBackground: Automated and interpretable classification of brain tumors from MRI scans remains a critical challenge in medical imaging and neuro-oncology. This study addresses the need for reliable and deployable AI-driven tools that support timely tumor differentiation while maintaining transparency and practical usability. Methods: A deep learning–based diagnostic framework was developed using convolutional neural networks implemented in TensorFlow. The system was trained and evaluated on a curated dataset of 3,097 axial brain MRI images spanning four classes: glioma, meningioma, pituitary tumor, and normal cases. To ensure robust performance estimation, all models were evaluated using stratified 5-fold cross-validation and benchmarked against multiple state-of-the-art transfer learning architectures. For real-world applicability, the selected models were deployed via a FastAPI-based server, and Gradient-weighted Class Activation Mapping (Grad-CAM) was incorporated to provide qualitative visual explanations. Results: Across cross-validation folds, the proposed framework demonstrated stable and competitive performance in terms of accuracy, macro-averaged F1-score, and macro-averaged AUC, with low inter-fold variance. Comparative evaluation showed that transfer learning models achieved strong classification performance, while the lightweight custom CNN remained suitable for real-time deployment. The FastAPI implementation enabled low-latency inference and ondemand Grad-CAM visualizations, supporting transparent and responsive model usage. Conclusion: This work demonstrates the feasibility of bridging deep learning– based brain tumor classification with scalable, real-time deployment. By combining robust cross-validation, state-of-the-art benchmarking, and explainability- aware inference, the proposed framework provides a practical pathway toward integrating artificial intelligence into radiological workflows, while highlighting the importance of interpretability and deployment constraints in neuro-oncological applications.Öğe Türü: Öğe , A Large-Scale Peripheral Blood Cell Dataset for Automated Hematological Analysis(Nature, 2026) Yarıkan, Atıf Eren; Örer, Can; Akyıldız, Volkan; Kuş, Zeki; Aydın, Musa; Palaoğlu, Kerim Erhan; İncir, Said; Baysal, Kemal; Özçelik, Cemal; Kiraz, Berna; Kiraz, AlperWhite blood cell classification is fundamental to hematological diagnosis, yet existing datasets are limited in scale and class diversity. We present a comprehensive peripheral blood cell dataset comprising 31,489 high-resolution microscopic images across 13 distinct cell classes, representing the largest publicly available collection for automated blood cell analysis. Images are acquired using the Sysmex DI-60 system from May-Grünwald-Giemsa-stained blood smears at 100 × magnification under standardized laboratory conditions. Expert hematologists with over 10 years of experience performed manual annotation with high inter-rater agreement (Cohen’s kappa >0.85 for all classes). The dataset includes common cell types such as segmented neutrophils and lymphocytes, alongside diagnostically critical but rare subtypes, including myelocytes, blasts, and reactive lymphocytes. Images are organized into training, validation, and test splits (70:10:20 ratio) with consistent 368 × 368 pixel resolution. Baseline experiments using 14 deep learning architectures demonstrate the dataset’s utility, with DenseNet-121 achieving 95.23% accuracy. KU-Optofil PBC Dataset addresses critical gaps in medical image analysis datasets and supports the development of robust automated hematology systems for clinical applications.Öğe Türü: Öğe , Kütüphane Bülteni, 13(FSM Vakıf Üniversitesi, 2026)Sahn-ı Seman Medreseleri, Osmanlı İmparatorluğu’nun “Klasik Çağı'nı inşa eden insan kaynağının kalbidir. Bizans kiliselerindeki geçici çözümlerin ardından devletin kendi özgüveniyle ve muazzam bir bütçeyle kurduğu bu akademi, Fatih Sultan Mehmed’in “kılıçla fethedilen coğrafyanın ancak kalemle, kanunla ve bilimle elde tutulabileceği” yönündeki derin felsefesinin tasa oyulmuş halidir. Bu kurumda atılan sağlam temeller, Osmanlı ilmiye sınıfını yüzyıllar boyunca ayakta tutacak olan kurumsal omurgayı oluşturmuştur.Öğe Türü: Öğe , Nişancı Mehmed Paşa Vakfiyesi Üzerinden Osmanlı Külliye Sistemine Dair Mimari ve Toplumsal Bir İnceleme(İstanbul Üniversitesi, 2026) Ceran, İremBu çalışma, Osmanlı Klasik Dönem külliye mimarisinin geç örneklerinden biri olan Nişancı Mehmed Paşa Külliyesi’nin vakfiyesi üzerinden, mimarlık tarihi ve şehir tarihi bağlamında kapsamlı bir değerlendirme sunmaktadır. Bazı araştırmacılar tarafından Mimar Sinan’ın son eseri kabul edilen bu külliyenin birçok yapısı günümüze ulaşamamıştır. Bu sebeple, külliyenin mimari organizasyonu, sosyal ve vakıf sistemiyle bağlantılı işleyişi hakkında en önemli kaynak vakfiye metnidir. Bu çalışmada daha önce arşiv uzmanları tarafından transkripsiyonu yapılmış fakat yayımlanmamış vakfiyenin mimarlık tarihi açısından sistematik biçimde analiz edilerek içerdiği tarihî verilere eklenen değerlendirme ile vakfiyede yer alan bilgilerin birçok saha için yönlendirici nitelikte olması hedeflenmektedir. Çalışma kapsamında, vakfiyenin satır aralarından Mimar Sinan’ın Osmanlı sanatının zirvesinde tasarladığı son yapının inşa gerekçesi, mekânsal organizasyonu, görevlendirmeleri, toplumsal beklentileri ve dönemin mimari üslubuna dair çıkarımlar yapılmıştır. Böylece Mimar Sinan sonrası külliye kavrayışının devamlılığı ve dönemin devlet ricalinin mimariye müdahale biçimleri üzerine yeni bir katkı sunmak amaçlanmaktadır.
