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 , An Efficient Ransomware Attack Detection Framework Using Machine Learning and Feature Reduction Techniques(IEEE, 2026) Mutlu, Gökay; Rihani, Neşe; Bayazıt, Esra Çalık; Şahingöz, Özgür KorayIn recent years, ransomware attacks have emerged as one of the most troublesome cybersecurity threats largely due to their widespread adoption to digital platforms, cloud services, and highly interconnected systems. Although different detection mechanisms are proposed in literature and used different detection systems, modern ransomware variants are increasingly capable of bypassing traditional signaturebased detection mechanisms. Therefore, the use of machine learning techniques for more effective threat detection is preferred in many protection mechanisms. However, many machine learning–based solutions suffer from their high computational overhead and excessive feature dimensionality, which limits their practical deployment for the systems. To overcome this deficiency, the proposed system presents a ransomware detection framework, which integrates machine learning approach with systematic feature reduction model to achieve both high detection performance and effective execution of the detection systems. Mainly, features are extracted from system-level activities, after which feature selection methods are applied to identify the most informative features to significantly reduce the overall feature space and execution time. We conducted experiments on a recent ransomware dataset to show that the proposed framework maintains high detection accuracy and low false-positive rates while considerably reducing execution time and resource consumption. Moreover, the proposed framework performs steadily in underclass imbalance conditions and proves to be resistant to ransomware samples never seen before. In particular, using only 20 selected features, the XGBoost classifier reaches an accuracy of up to 100%, proving its suitability for effective and efficient ransomware detection.Öğe Türü: Öğe , An Enhanced Machine Learning–Based Android Malware Detection Framework with Static Analysis(IEEE, 2026) Özyurt, Halime Sıla; Akkök, Selma; Şahingöz, Özgür KorayThe widespread use of Android devices has made them a prime target for increasingly sophisticated malware attacks, posing serious threats to user privacy and data security. Traditional signature-based detection methods fail to identify novel and polymorphic malware variants, necessitating more adaptive approaches. This paper presents an improved machine learning-based framework for Android malware detection that overcomes the limitations of existing systems through static analysis techniques. Our framework leverages advanced feature engineering methods to extract comprehensive behavioral and structural characteristics from Android applications, such as permissions, API calls, network activities, and code-level static attributes. We implement and evaluate several machine learning algorithms to achieve robust classification performance. The proposed framework uses feature selection optimization to reduce dimensionality while maintaining detection accuracy, balancing computational efficiency with detection effectiveness. Experimental evaluation on benchmark dataset demonstrates that our framework achieves good performance compared to state-of-the-art approaches, ensuring the detection of zero-day malware variants. The results indicate that our enhanced framework offers a practical and scalable solution for real-time Android malware detection in various deployment scenarios.Öğe Türü: Öğe , Phase Evolution, Mechanical Properties and Corrosion Behavior of CoCrFeNi Alloys: Effect of Hf(Elsevier, 2026) Cengiz, Sezgin; Fazi, Andrea; Ceylan, Doğancan; Muhaffel, Faiz; Tarakçı, Gürkan; Özer, Gökhan; Thuvander, MattiasIt is well known that the formation of phases and microstructures, and their interactions, must be understood to develop new alloys with excellent mechanical properties and corrosion resistance. This study aimed to investigate the effect of Hf content on the phase formation and evolution in CoCrFeNi high-entropy alloys (HEAs). The formation of micrometre and nanometre-scale phases (FCC, Laves) was studied by electron microscopy, and phase interfaces were examined using atom probe tomography (APT). With increasing Hf content, the HEAs gradually transformed from FCC single phase to firstly Ni7Hf2+FCC, and finally to lamellar FCC/Laves phases. The FCC phase shows homogeneous Co–Cr–Fe distribution, while the Laves phase is enriched in Co–Ni–Hf, with a distinct Ni–Co depletion zone forming at the FCC/Laves interface due to mixing enthalpy effects. The growing Laves fraction significantly improves hardness—up to a fourfold increase for CoCrFeNiHf0.42 alloy, while the elastic modulus rises only when the eutectic structure becomes dominant. Corrosion studies reveal a dual effect: CoCrFeNiHf0.1 improves passive film stability, whereas higher Hf contents promote second-phase formation, leading to microgalvanic corrosion and reduced corrosion resistance. Overall, Hf addition plays a compositiondependent role in tailoring microstructure, mechanical properties, and corrosion behavior of CoCrFeNi HEAs.Öğe Türü: Öğe , Beyond Participation, Architecting the Unknown Future: a Methodological Framework for Form-Based Adaptability(Emerald, 2026) Akbar, JamelPurpose – This research addresses the “temporal paradox” in architectural design, where even participatory methods produce fixed configurations that constrain future adaptability. It proposes a design methodology focused on creating inherently adaptable built environments capable of meeting the unknown needs of future generations. Design/methodology/approach – The study builds upon John Habraken’s “Support/Infill” theory and Stanford Anderson’s concept of the “Robust Environment.” It employs a design-by-research approach, utilizing evidence from architectural experiments conducted with students over three decades. The study methodologically follows Imre Lakatos’s epistemological framework of scientific research programs, which views urban studies as evolving through a “hard core” and progressive research programs (Akbar, 2025). Findings – The research concludes that the key to long-term adaptability lies in prioritizing a “form-generating process” over a functionalist one. The optimal configuration of a building for future change is determined “not” by its initial function, but by spatial form and the “constraints” of its layout (e.g. positions of openings). Research limitations/implications – The study is conceptual and based on pedagogical experiments. The findings require further validation through a real-world application. Practical implications – This methodology provides architects with a research framework for designing buildings that will undergo significant functional changes with minimal demolition. This promotes sustainability, reduces waste, etc. Originality/value – This paper makes a theoretical contribution by synthesizing and advancing the work of Habraken and Anderson. It moves beyond the participatory design paradigm to introduce a forward-looking, “form-first” epistemology for urban adaptability. The proposed method offers a teachable design process to achieve the theoretical goal of a “robust environment,” presenting a parallel approach to conventional, functionally deterministic architectural practices.Öğe Türü: Öğe , Production of Chitosan-PVA Coated Vitamin E and Ephedrine Nanoparticles Using Electrospraying for the Treatment of Narcolepsy(MDPI, 2026) Yakut, Asude Bilge; Bingöl, Ayşe Betül; Oktay, Büşra; Çiftçi, Fatih; Üstündağ, Cem Bülent; Kızılkurtlu, Ahmet AkifThis study focuses on the production and characterization of polyvinyl alcohol (PVA)- chitosan (CS)-based nanoparticles loaded with vitamin E (VitE) and ephedrine (Ep) via electrospraying for intranasal drug delivery in narcolepsy treatment. The nanoparticles were successfully synthesized using optimized parameters (15.5 kV voltage, 0.3 mL/h flow rate, 25 G needle size, and 14 cm distance). Scanning electron microscopy (SEM) analysis confirmed the formation of spherical particles with an average size of 350–500 nm, while energy-dispersive X-ray spectroscopy (EDS) mapping revealed a homogeneous elemental distribution with oxygen (51.74%), silicon (24.48%), carbon (6.47%), zinc (6.08%), and aluminum (3.82%). Fourier-transform infrared (FTIR) spectra demonstrated the successful encapsulation of VitE and Ep through characteristic peaks at 3285 cm−1 (OH stretching), 1731 cm−1 (C=O stretching), and 1086 cm−1 (C-O-C stretching). In vitro drug release analysis indicated a controlled and sustained release profile, with cumulative VitE and Ep release reaching 78.6% and 84.3%, respectively, over 48 h in phosphate-buffered saline (PBS, pH 7.4). Antioxidant activity assessment using the DPPH assay confirmed an R2 value of 18.84 μg/mL, demonstrating significant free radical scavenging potential. The antibacterial activity, tested via the disk diffusion method, exhibited inhibition zones of 18.31 ± 5.8 mm (E. coli) and 21.51 ± 1.57 mm (S. aureus), confirming strong antimicrobial properties. These findings suggest that the developed electrosprayed PVA/CS nanoparticles loaded with VitE and Ep offer a promising intranasal delivery system with enhanced bioavailability, controlled release, antioxidant capacity, and antibacterial properties, making them a viable candidate for narcolepsy treatment.
