Browsing by Author "Mersin, G."

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Thumbnail Image
    Conference Object
    Insights From AI-Driven Architectural Design Competition: Challenging Conventional Paradigms
    (Education and Research in Computer Aided Architectural Design in Europe, 2025) Mersin, G.; Çiçek, S.; Basarir, L.
    The rapid advancements in artificial intelligence (AI) are fundamentally transforming the design landscape, prompting a critical reflection: how might architectural design competitions adapt to leverage AI's potential as a collaborative design assistant, challenging conventional paradigms and fostering broader awareness of technological advancements within the architectural profession? Addressing this inquiry, a pioneering competition was organized by a Non-Governmental Organization (NGO) to explore new trajectories in integrating AI into architectural design practices. The competition engaged participants in proposing innovative architectural interventions for a historically and industrially significant urban site. Its central aim was to encourage the development of AI-assisted workflows tailored to each participant’s unique design methodologies, reframing architectural design as an iterative process of thinking, seeing, and making, rather than a static outcome. This paper examines the competition’s methodology, detailing stages such as the preparation of specifications that emphasized AI workflow customization, and the evaluation framework of the jury, which prioritized originality, contextual relevance, and the depth of AI integration. Particular attention is given to how participants utilized AI to document and enhance their creative processes, fostering dynamic and personalized approaches to design. The findings underscore the potential of AI to redefine architectural workflows, offering insights into how computational tools can augment design thinking and practice. By reframing the role of AI in architectural design competitions, this study proposes a transformative model for integrating emerging technologies into the profession, emphasizing the importance of process-driven innovation to inspire broader engagement and understanding within the architectural community. © 2025, Education and research in Computer Aided Architectural Design in Europe. All rights reserved.
  • Thumbnail Image
    Conference Object
    Synthetic Interpretations: AI-Driven Scoring Framework for Architectural Design Evaluation
    (Education and Research in Computer Aided Architectural Design in Europe, 2025) Bingöl, K.; Koç, M.; Çiçek, S.; Aksu, M.S.; Öztürk, E.; Mersin, G.; Basarir, L.
    While artificial intelligence (AI) has significantly influenced architectural design through generative tasks like conceptual exploration and visualization, its capacity for nuanced qualitative evaluation remains underexplored. Effective evaluation requires a convergence of subjective interpretation and objective rigor, addressing contextual relationships, formal qualities, adherence to design principles, programmatic functions, construction strategies, structural systems, and sustainable practices. This research addresses these challenges by developing an AI-driven scoring framework, ArchiJury, based on synthetic architectural reviews aligned with established evaluation criteria. Two distinct AI models form the methodological basis of the study: The first employs visual transformer models and a synergy simulation algorithm for precise, context-based criterion-specific evaluation. The second uses a ResNet-18 deep-learning architecture for multi-criteria holistic scoring, trained end-to-end with an annotated dataset and optimized through mean squared error (MSE) loss, and utilizes Grad-CAM heatmaps for interpretability by visually representing the influential image regions guiding AI scoring decisions. The outputs of both models are comparatively discussed with human expert evaluations to critically assess AI’s potential and limitations, and implications of AI driven evaluation, clarifying how these computational methods align or diverge from expert judgment and exploring their significance for scalable, consistent, and nuanced architectural evaluation. © 2025, Education and research in Computer Aided Architectural Design in Europe. All rights reserved.