Journal of Brilliant Engineering (BEN)

Ayşenur Arzık Bülent ÇAVUŞOĞLU

This study aims to comprehensively examine the open-source platforms used for simulation and testing processes in the field of 5G new radio technology and offer solutions to address diverse needs. In this study, we compare open-source platforms such as Free5GC, OpenAirInterface, Open5GS, IEEE 5G/6G Innovation Testbed, and MATLAB 5G Toolbox based on different factors such as how the network is set up, what versions they support, what hardware they need, how they use databases, if they can emulate in real-time, their simulation capabilities, and other features, as well as the support from the community and documentation. In addition to all these, the platforms have been evaluated for their accuracy, real-world compatibility, accessibility and developability, installation difficulties, and computational load. In addition, the main possible improvements are listed. The analysis has determined that the Free5GC and Open5GS platforms are suitable for simulating 5G New Radio (NR) core network functions. The OpenAirInterface platform, in contrast, offers a more powerful and flexible structure at both the core and radio access network (RAN) levels. The IEEE 5G/6G Innovation Testbed provides a physical test environment and more realistic results thanks to its hardware-based structure. MATLAB 5G Toolbox stands out for academic studies with its channel modeling, simulation capability of various layers, and academic prototyping. These assessments provide findings that contribute to the advancement of next-generation wireless communication systems by assisting researchers and developers in selecting the best simulation environment for their specific needs.

https://doi.org/10.36937/ben.2025.4998

Oğuzhan Akarsu Abdulkadir Cüneyt Aydın

The current study examines the critical aspects of earthquake-resistant design (ERD) for steel structures, with a particular emphasis on connection detailing, semi-rigid configurations, bracing systems, and material behavior. Although the recent advances in seismic engineering, the latest studies highlight the gap between design approaches and actual seismic behavior, especially in terms of rotational stiffness, energy dissipation capacity, and failure mechanisms. The study critically reviews the seismic performance of semi-rigid and bolted connections, efficiency of different types of bracing–systems as well as the impact of material variability on the response during seismic action. The applicability of performance-based design methodologies and international building codes (Eurocode 8 and AISC specifications) to contemporary seismic design is likewise examined. Grounded in a synthesis of experimental data, numerical modeling, and case studies, this paper outlines inadequacies in existing design methodologies and proposes innovations on the horizon, like self-centering bracing systems and advanced cyclic testing of connections. These research contributions add to the discussion on how to best optimize seismic design strategies to improve the life-safety of structures, limit damage, and enhance performance following an earthquake.

https://doi.org/10.36937/ben.2025.41001

mohammadjavad hosseinpoor

COVID-19, first identified in Wuhan, China in 2019, is a highly contagious respiratory disease with symptoms such as fever, dry cough, and shortness of breath. Computed tomography (CT) scans are a key tool for detecting lung abnormalities related to COVID-19. However, existing approaches to COVID-19 diagnosis often struggle to extract clinically relevant features from CT images, particularly when there is inter-slice variability or limited annotated data. In this study, we introduce an Adaptive Convolutional Neural Network (ACNN) model designed to address these challenges by integrating two core mechanisms: (1) a sequential memory component using Long Short-Term Memory (LSTM) units to capture contextual relationships and dependencies across consecutive CT slices, and (2) transfer learning—leveraging pre-trained weights from large-scale medical imaging datasets to improve feature generalization. This adaptive design differs from standard CNN architectures by explicitly modeling both spatial and limited sequential information in CT scan volumes. The ACNN was trained and evaluated on the SARS-CoV-2 CT dataset, and its performance was assessed using standard metrics. Experimental results show that ACNN outperforms classical machine learning algorithms (such as KNN and SVM) and established deep learning models (including VGG16, ResNet, and DenseNet), achieving an accuracy of 97.5%, a precision of 97.30%, a recall of 97.85%, and an F1-score of 97.58%. Statistical tests confirmed the robustness of these improvements. The results demonstrate that the proposed ACNN, through its memory-augmented and transfer learning-driven design, offers a precise and reliable approach for COVID-19 diagnosis and holds promise for real-world clinical applications.

https://doi.org/10.36937/ben.2025.41003

Dilek BARTIK Engin YENER Ahmet Emin Kurtoğlu

Road transport is the most widely used transport network globally and in Turkey. Every year, asphalt mix designs are prepared for the deterioration or reconstruction of road pavements. Since asphalt mixture designs affect the mechanical and physical properties of roads, they also directly affect their performance. For this purpose, Marshall design, one of the experimental methods, is used. The calculation of design parameters used in mixture design is complex, time consuming and costly. To address this, developing models that predict experimental results using machine learning methods offers an economical and practical approach. A data set consisting of 13 variables including specific gravities, aggregate proportions and bitumen content was created for 453 hot mix asphalt specimens subjected to the Marshall test. Marshall Stability (MS) was determined as the target variable in the model. Random Forest, XGBoost, GBoost and Extra Trees algorithms were used to predict MS; models were compared with performance metrics such as MAPE, R² and RMSE. The XGBoost model was the most successful model for MS prediction; it provided high accuracy and low error rate with R² (coefficient of determination) of 0.96, RMSE (root mean square error) of 0.37 and MAPE (mean absolute percentage error) of 0.02% on the test data.SHAP analysis was performed to determine the variables affecting MS prediction, and the most effective variables were found to be Gef (effective specific gravity of aggregate) and Gsb (bulk specific gravity of aggregate). Such explainability analyses facilitate decision making in the early design stages by supporting the optimization of design parameters.

https://doi.org/10.36937/ben.2025.41034

Saad Issa Sarsam

The sensitivity of the overlay thickness to the implementation of geogrid is assessed using two types of biaxial geogrid (AR-G and AR-1). Circular Asphalt concrete specimens of 152.4 mm diameter and 38.1 mm thickness were constructed and denoted as the lower layer. The hot asphalt concrete material required to construct the upper layer (representing overlay) of variable thickness (38.1 and 63.5) mm was compacted over the lower layer specimen after inserting the geogrid in between. The coupled specimens were tested in a model box of 50 x50 x70 cm filled with loose sand layer of 40 cm thickness, and the load – deformation data was recorded. Implementation of geogrids (AR-1 and AR-G) in thin asphalt concrete layer (38.1 mm over 38.1 mm) improved resistance to deformation by (83.3 and 33.3) % and the load sustaining capacity declined by (19.2, and 23) % respectively as compared with the control mixture. For thick asphalt concrete layer, (63.5 mm over 38.1mm), the implementation of geogrids exhibited improved resistance to deformation by 11.2 % regardless of the geogrid type and the load sustaining capacity declined by (40, and 50) % when AR-1 and AR-G geogrids were implemented respectively as compared with the control mixture. The viscoelastic stage of failure for the thin layer of reinforced asphalt concrete was extended to 6 mm of punching deformation as compared with the control sample. However, the thick layer of reinforced asphalt exhibits no significant variation in the stages of failure.

https://doi.org/10.36937/ben.2025.41007