Journal of Artificial Intelligence in Architecture

Front Matter of JARINA Vol.4 No.2, 2025

2025-08-16T11:38:00+07:00

Back Matter of JARINA Vol.4 No.2, 2025

2025-08-16T11:39:14+07:00

Utilization of Augmented Reality in Architecture Pedagogy with A Case Study of Lego House Denmark

2024-11-08T16:11:52+07:00

This study explores the utilisation of Augmented Reality (AR) in architectural education through a case study of LEGO House. AR offers an innovative approach by integrating traditional design methods with digital technology to enhance students' understanding of design exploration. The research methodology includes a literature review, bibliometric analysis, and data collection through questionnaires assessing architecture students' experiences with AR. The main findings indicate that integrating AR with physical models such as LEGO enhances design visualisation efficiency and student engagement in the learning process. Specifically, 96.2% of respondents agreed that digital technology improves design accuracy and efficiency, while 88.5% emphasised the importance of physical models in understanding proportions and scale. These findings align with existing literature, highlighting AR's role in bridging traditional and digital design methodologies. The implications of this research contribute to the development of more innovative teaching methods in architectural education and suggest further exploration of AR's long-term impact on design learning.

Text-to-Image Generative Αrtificial Intelligence As Conceptual Mechanism For Architectural Design

2025-02-19T20:37:45+07:00

This study investigates the potential of text-to-image generative AI applications to be used as exploration mechanisms for architectural design rather than mere visualisation tools. We examine whether text-to-image generative AI applications can "understand" architecture's spatial and geometric configuration in meaningful and creative ways. Our experimental method used a series of architectural plans and artistic patterns as image prompts, combined with varied text prompts and parameters to evaluate Midjourney's capacity for geometric and spatial interpretation and creativity. The experiments focused on the application's capacity to (1) generate diagrams from architectural plans, (2) create variations of two-dimensional drawings and patterns, and (3) transform two-dimensional layouts into three-dimensional spaces. Results indicate that Midjourney can generate meaningful abstractions and spatial configurations but struggles with strict spatial fidelity, particularly for asymmetrical or fragmented layouts. The study highlights the significance of short prompts and increased image weight parameters for improving fidelity and structural coherence. While Midjourney exhibits potential as a conceptual tool for highly creative architectural exploration, it lacks the precision required for deterministic spatial manipulation. Dall-E performs significantly better in fidelity and alignment to the original drawing, but further research is needed to determine its potential use as an assistive tool for architectural design. The findings contribute to the discourse on AI-assisted architectural design for creative ideation and suggest further research into the design capacities of other similar models.

A Systematic Review on Visual Sensory of Children Towards City Landmarks

2025-01-14T23:41:46+07:00

Children's visual sensory of city landmarks is interesting because it has a different perspective than adults or teenagers. High curiosity about something made the preferred landmarks and chosen focus different for each child's age. It does not have to be a prominent city landmark like a monument; even landscapes have become interesting for children to visit. The problem is how many papers discuss this and the resulting children's visual sensory issues. The purpose of this study was to review as many papers as possible to explore the objects of preferred city landmarks and the responses obtained. The method used was to collect various documents from Google Scholar with Publish or Perish and Vos Viewer based on keywords about children's visual sensory of city landmarks, a total of 25 papers to be described in table form to see the essence of the research, the country conducting the study and the year of the study. Then, the paper's contents, such as methods, landmark objects, memory responses, and age groups, were reviewed. The result is that the landscape has become a widely studied place, and technology has begun to create landmarks virtually, using EEG tools, eye trackers, and game engines.

Application of Generative Design on Architecture to Optimize Design Decision in Preliminary Design Stage

2024-12-28T16:11:04+07:00

This study investigates the application of generative design through Autodesk Forma, a cloud-based AI platform, to optimise architectural decision-making in the preliminary design stage of a ten-story hotel in Cirebon City, Indonesia—a region characterised by a hot and humid climate. The research employed simulations based on five environmental parameters: sun hours, daylight potential, wind distribution, microclimate conditions, and solar energy. Three optimal models were selected based on orientation, spatial configuration, and environmental responsiveness. Subsequent development simulations were conducted on these three models by refining openings, adding vegetation, and enhancing shading strategies. Model-2 emerged as the best-performing design. It demonstrated an energy efficiency potential of approximately 23%, achieved through improved daylighting (VSC ≥ 27% on most facades), reduced reliance on artificial cooling due to stable microclimatic conditions (temperatures moderated by 2–3°C during peak hours), and the integration of solar panels generating an estimated 165,000 kWh/year from 40% roof coverage at 10% efficiency. The results confirm that AI-driven generative design can significantly accelerate the design process while enhancing environmental performance. This approach supports energy-efficient architecture in tropical regions, although it requires access to advanced technology, skilled practitioners, and robust internet connectivity.

The Influence of Inlet and Outlet Ratios on the Performance of Natural Ventilation in Mosque, Indonesia

2025-04-18T22:22:44+07:00

Natural Ventilation is a sustainable passive strategy for enhancing thermal comfort and reducing energy consumption in buildings with fluctuating occupancy levels, such as mosques. This study investigates the effects of varying inlet-to-outlet opening ratios using different schemes, simulated through Computational Fluid Dynamics (CFD) with the RANS model via OpenFOAM (Butterfly plugin in Grasshopper). Based on urban wind profiles, this research evaluates wind-driven Ventilation under isothermal conditions. The simulation examines five inlet-outlet opening ratios (ranging from 1:1 to 1:5), two inlet configurations (single vs. double), five building lengths (5×10, 10×10, 15×10, 20×10, and 25×10 m), and three building heights (3 m, 4 m, and 5 m). Results indicate that an opening ratio of 1:3 provides the optimal balance between airflow efficiency and thermal stability, particularly concerning solar radiation effects. The single-inlet configuration yields higher air velocity at standing height (1.1 m), whereas the double-inlet setup promotes a more uniform vertical airflow distribution. Increasing building height enhances airflow due to reduced ground-level resistance, while elongated floor plans (over 10 m in length) experience flow stagnation in the central zone. These findings underscore that optimal natural ventilation in mosques depends on opening ratios, spatial proportions, and inlet configurations. Such insights contribute to climate-responsive mosque design, especially in dense urban environments, supporting energy-efficient and comfortable indoor conditions during congregational prayers.