Civil Engineering and Architecture Vol. 13(3), pp. 2100 - 2113
DOI: 10.13189/cea.2025.130345
Reprint (PDF) (1458Kb)

Integrating Machine Learning Algorithms with Parametric Tools in Architectural Engineering for Material Selection in Residential Interiors

Mansour Safran ^*
Department of Architecture, Faculty of Engineering, Jerash University, Jordan

ABSTRACT

This study explores the integration of advanced machine learning algorithms and parametric design tools within architectural engineering to optimize the selection of interior materials for residential buildings. The research addresses the challenges posed by conflicting criteria such as cost, durability, sustainability, and aesthetic value in material selection. By leveraging machine learning models, including Gradient Boosting Machines, the study achieves high-fidelity predictions of material properties. To identify the most suitable materials, these predictions are refined using metaheuristic optimization techniques, specifically Particle Swarm Optimization (PSO) and Genetic Algorithms (GA). The methodology follows a systematic workflow, encompassing data collection, preprocessing, model training, optimization, and integration into parametric design tools. Results demonstrate the approach's efficacy, with Neural Networks optimized through PSO achieving an accuracy of 0.90 and a minimized objective function value of 0.63. This highlights the effectiveness of combining machine learning and optimization algorithms in enhancing decision-making processes for material selection. The study concludes that this integrated methodology significantly enhances the efficiency and sustainability of material choices in residential interior design. By providing a robust and data-driven framework, this research contributes to the field of architectural engineering by enabling informed decisions that balance functionality, aesthetics, and environmental considerations, ultimately advancing sustainable interior design practices.

KEYWORDS
Architecture, Interior Design, Machine Learning, Parametric Design, Material Selection, Particle Swarm Optimization

Cite This Paper in IEEE or APA Citation Styles
(a). IEEE Format:
[1] Mansour Safran , "Integrating Machine Learning Algorithms with Parametric Tools in Architectural Engineering for Material Selection in Residential Interiors," Civil Engineering and Architecture, Vol. 13, No. 3, pp. 2100 - 2113, 2025. DOI: 10.13189/cea.2025.130345.

(b). APA Format:
Mansour Safran (2025). Integrating Machine Learning Algorithms with Parametric Tools in Architectural Engineering for Material Selection in Residential Interiors. Civil Engineering and Architecture, 13(3), 2100 - 2113. DOI: 10.13189/cea.2025.130345.