ARCENG (INTERNATIONAL JOURNAL OF ARCHITECTURE AND ENGINEERING) ISSN: 2822-6895

Development of a Machine Learning-Based Conversion Model for Uniaxial Compressive Strength Prediction Between Different Specimen Geometries

Murat IŞIK — 2025-12-20

Uniaxial compressive strength (UCS) is one of the most critical design parameters in rock engineering applications, including the design and construction of engineering structures, underground excavations, and slope stability. Specimens required for UCS testing must be prepared in accordance with various national and international standards. However, when the rock structure is weak or brittle, obtaining the required number and size of specimens may not be feasible. In such cases, alternative specimen geometries and sizes recommended by different standards are often adopted. Although the influence of specimen shape and size on UCS has been extensively studied in the literature and is relatively well understood, the relationship between UCS values obtained from different geometries remains largely unexplored. Notably, there is a lack of comparative studies focusing specifically on rock samples. Furthermore, some transformation equations proposed in the literature have proven inadequate in accurately estimating the strength conversion between cylindrical and cubic specimens. In this study, various machine learning (ML)-based regression algorithms were applied to predict UCS values for cylindrical specimens using UCS values obtained from cubic specimens. A comparative evaluation was conducted using linear regression, tree-based models, ensemble learning methods, kernel-based algorithms, and robust regression techniques. Model performances were assessed through 5-fold cross-validation using R², MAE, MAPE, and RMSE as evaluation metrics. The findings reveal that models such as the Huber Regressor and Support Vector Regression (SVR) provided highly accurate predictions, with narrower error margins and stronger generalization capacity compared to classical transformation coefficients. These results suggest that ML-based models offer an effective and reliable approach offering a robust alternative to conventional transformation equations, especially in engineering contexts where direct experimental testing is limited or impractical.

Rendering Revolution: GPU Acceleration and AI Integration in Blue Sky Studios’ Ice Age Films

Ayyappan P — 2025-12-20

This comprehensive study analyzes the technological evolution of Blue Sky Studios' proprietary CGI Studio renderer and production pipeline through a detailed examination of the Ice Age franchise spanning from 2002 to 2016. Through quantitative shot-by-shot analysis and technical specification comparisons between Ice Age (2002) and Ice Age: Collision Course (2016), this research documents the revolutionary transformation from CPU-based ray tracing to GPU-accelerated rendering with emerging AI augmentation techniques. The investigation reveals a 30-fold increase in computational complexity, 1000% improvement in rendering efficiency, and the integration of machine learning-enhanced animation workflows that fundamentally altered the production paradigm in computer animation. Our findings demonstrate how Blue Sky Studios' pioneering adoption of physically-based ray tracing in 2002 established the foundation for subsequent AI-driven innovations that would define modern animation production methodologies.

Architectural Palimpsest of Peshawar: Engineering, Identity, and Conservation Peshawar

Muhammad Tayyab NAQASH — 2025-12-20

Peshawar, one of South Asia’s oldest continuously inhabited cities, presents a living architectural palimpsest shaped by centuries of cultural, political, and religious transformations. This study explores the evolution of Peshawar’s architectural heritage through photographic documentation and case studies of key sites, including Mughal mosques, colonial institutions, and contemporary structures. It integrates architectural analysis with civil engineering approaches to assess preservation challenges and propose sustainable conservation strategies.

The research employs a mixed-methods approach, including photographic documentation, structural analysis, and review of urban development policies. It highlights the role of civil engineering in structural retrofitting, digital documentation (e.g., HBIM), and seismic resilience. Findings reveal that modern urbanization, lack of awareness, and insufficient policy frameworks erode the city’s rich built environment.

The paper advocates for an interdisciplinary conservation model, aligning architectural heritage with engineering innovation, urban planning, and community participation. By understanding Peshawar’s layered built history, stakeholders can ensure that modernization complements rather than erases the city’s historic identity.

Effects of First Story Stiffness on Earthquake Responses of 2-Story Wooden Houses

Koichi KIMURA — 2025-12-20

In this study, a seismic response analysis of 2-story wooden houses has been carried out, and guidelines for proper seismic rehabilitation have been considered. In the analysis, the bilinear + slip model is adopted as the restoring-force characteristics because in previous studies it has been confirmed that the model reproduces characteristics of wooden houses relatively well. First, it was investigated how much the first story stiffness affects the inertia force of the roof during an earthquake. Next, the effects of roof mass were examined. Finally, in the case where an anti-seismic shelter was placed on the ground
floor, a suitable connection method to the house was considered.

Determination of the Most Important Defect Type for an Operating Room Materials Sewing Factory Using AHP

Mehmet MİMAN — 2025-12-20

In this study, prioritizing defect types for a sewing factory that produces operating room materials were accomplished through Analytic Hierarchy Process (AHP). Defects types evaluated in this study are; measurement errors, false and inefficient material usage, folding defects, not producing according to orders. Criteria for faults are time, cost, quality, customer satisfaction and quality. Aggregated priority weights are computed based on geometric average of two experts’ opinions for pairwise comparisons. As a result, producing inappropriately to orders was found to be the most significant fault type having the greatest priority weight. Findings are matching the recent findings obtained through AHP and Fuzzy AHP applications for prioritizing risks for production defects. This study, different than the traditional approach of fault types and their effects analysis, deals with defects types hierarchically as a multi criteria decision making approach. Among the criteria of time, cost, quality, customer satisfaction and quantity considered in this study, customer satisfaction was determined to be the most important criterion. This study contains potentials to be extended through the application of other multi-criteria decision making techniques.

A Different Solution to Forest Fires, Supported by Artificial Intelligence

Murat CANPOLAT — 2025-12-20

Forests are not only a source of oxygen but also a home for many living creatures. Fires are a leading cause of forest destruction. Delayed detection of forest fires, and the resulting inability to intervene early, makes fire control difficult and ultimately leads to disaster.

As technology advances, we evolve our lives, our lives—in short, everything—in this direction. We also seek solutions to our problems in technology. Fighting forest fires, essential to our world and to life itself, is crucial, and efforts to provide relief to forest firefighters are essential.

Exploration of Contemporary Space Dynamics: Spatial Design

Ayça ARSLAN — 2025-12-20

The primary objective of this study is to focus on contemporary spatial dynamics and, unlike traditional spatial structures, to develop contemporary, flexible, user-friendly, and evolving spatial structures. Spatial design focuses on the design of contemporary, permeable, flexible, lightweight spatial boundaries, incorporating parameters such as flexibility, temporal scalability, and convexity, which are inherent to spatial dynamics. In spatial design, boundaries between spaces are established not through walls and doors, but through flexible design elements, significantly different from traditional methods. Spatial design is a design based on perception, and therefore, it can be quite lightweight, flexible, permeable, and incorporate a wide variety of dynamics. The principles of Gestalt theory of perception form the fundamental foundation of spatial design, bringing order and aesthetics to any composition. Therefore, based on perception theory, spatial design categorizes spatial boundaries as point elements, planar elements, elevation differences, color and texture variations, furniture, three-dimensional spatial structures, lighting, and overhead suspended ceilings. Therefore, after defining different spaces with these boundaries, spatial design associates these spaces with a spatial organization different from the traditional room-corridor relationship: depth, density, and interconnectedness In addition to new space boundaries and spatial relationships, it presents contemporary space types in spatial design, including group space characteristics such as day and night compartments, individual space characteristics such as service compartments, and new space types such as; liminal, dual, repetitive, intermediate, niche, and open spaces. This study aims to introduce spatial design in all its dynamics and reveal them through examples. It presents contemporary, flexible, user-friendly, changeable and transformable, and highly adaptable to different scenarios.

Artificial Intelligence-Based Performance Optimization of Oracle PL/SQL Queries

Gökhan TOPSAKAL — 2025-12-20

This study aims to develop an artificial intelligence–based optimization system to analyze and improve the performance of slow-running queries in Oracle PL/SQL and Forms-based applications. Performance data from Oracle queries were collected using SQL_TRACE and EXPLAIN PLAN and analyzed in a Python environment. A dataset was constructed through feature selection based on metrics such as execution time, logical reads, and I/O operations. Random Forest and XGBoost algorithms were applied to identify factors contributing to query slowness, with historical performance records used for model training and evaluation through standard performance metrics. The system was further refined and validated using real-world queries to enhance its recommendation capability. Results indicate substantial improvements: execution time reduced by 82.4%, consistent read rate by 84.8%, physical read rate by 90.9%, and total Oracle cost by 97%. In model comparison, XGBoost achieved superior classification accuracy with 96.1% accuracy and F1-score, while Random Forest provided faster prediction times. This research introduces a novel AI-driven system for diagnosing and optimizing Oracle PL/SQL performance issues, offering decision support for database administrators and contributing to improved query efficiency.