Generative AI design for building structures

Automation in Construction, Год журнала: 2023, Номер 157, С. 105187 - 105187

Опубликована: Ноя. 11, 2023

Язык: Английский

---

Generative urban design: A systematic review on problem formulation, design generation, and decision-making

Progress in Planning, Год журнала: 2023, Номер 180, С. 100795 - 100795

Опубликована: Июль 22, 2023

Язык: Английский

---

Generative adversarial networks in construction applications

Automation in Construction, Год журнала: 2024, Номер 159, С. 105265 - 105265

Опубликована: Янв. 6, 2024

Generative Adversarial Networks (GANs) have emerged as a powerful tool rapidly advancing the state-of-the-art in numerous domains. This paper conducts comprehensive review to analyse applications of GANs construction industry over years, and aims enrich body knowledge on this emerging Deep Learning (DL) algorithm sector. To achieve this, exploration variation is first conducted establish general foundation knowledge. Subsequently, 76 publications from year 2014 2023 are analysed identify growth significance current research landscape field. The results study indicate that predominantly applied four key domains, yet several limitations persist. serves crucial reference point for researchers, practitioners, stakeholders seeking understand harness transformative power construction.

Язык: Английский

---

Residential floor plans: Multi-conditional automatic generation using diffusion models

Automation in Construction, Год журнала: 2024, Номер 162, С. 105374 - 105374

Опубликована: Март 14, 2024

Язык: Английский

---

Automated building layout generation using deep learning and graph algorithms

Automation in Construction, Год журнала: 2023, Номер 154, С. 105036 - 105036

Опубликована: Июль 27, 2023

Язык: Английский

---

Automated site planning using CAIN-GAN model

Automation in Construction, Год журнала: 2024, Номер 159, С. 105286 - 105286

Опубликована: Янв. 13, 2024

Язык: Английский

---

Intelligent floor plan design of modular high-rise residential building based on graph-constrained generative adversarial networks

Automation in Construction, Год журнала: 2024, Номер 159, С. 105264 - 105264

Опубликована: Янв. 16, 2024

Язык: Английский

---

Generative Adversarial Network Based on Self-Attention Mechanism for Automatic Page Layout Generation

Applied Sciences, Год журнала: 2025, Номер 15(5), С. 2852 - 2852

Опубликована: Март 6, 2025

Automatic page layout generation is a challenging and promising research task, which improves the design efficiency quality of various documents, web pages, etc. However, current layouts that are both reasonable aesthetically pleasing still faces many difficulties, such as shortcomings existing methods in terms structural rationality, element alignment, text image relationship processing, insufficient consideration details mutual influence within page. To address these issues, this article proposes Transformer-based Generative Adversarial Network (TGAN). Networks (GANs) innovatively introduce self-attention mechanism into network, enabling model to focus more on key local information affects layout. By introducing conditional variables generator discriminator, accurate sample discrimination can be achieved. The experimental results show TGAN outperforms other subjective objective ratings when generating layouts. generated perform better avoiding overlap, exhibit higher stability, providing effective solution for automatic generation.

Язык: Английский

---

Environmental Justice in the 15-Minute City: Assessing Air Pollution Exposure Inequalities Through Machine Learning and Spatial Network Analysis

Smart Cities, Год журнала: 2025, Номер 8(2), С. 53 - 53

Опубликована: Март 18, 2025

The intersection of environmental justice and urban accessibility presents a critical challenge in sustainable city planning. While the “15-minute city” concept has emerged as prominent framework for promoting walkable neighborhoods, its implications exposure inequalities remain underexplored. This study introduces an innovative methodology assessing air pollution disparities within context 15-minute activity zones New York City. By integrating street-level PM2.5 predictions with spatial network analysis, this research evaluates patterns that more accurately reflect residents’ daily mobility experiences. results reveal significant socioeconomic racial exposure, lower-income areas Black communities experiencing consistently higher levels their walking ranges. A borough-level analysis further underscores influence localized development demographic distributions on outcomes. comparative demonstrates traditional census tract-based approaches may underestimate these by failing to account actual pedestrian patterns. These findings highlight necessity high-resolution assessments into planning initiatives foster equitable development.

Язык: Английский

---

Automated layout of modular high-rise residential buildings based on genetic algorithm

Automation in Construction, Год журнала: 2023, Номер 152, С. 104943 - 104943

Опубликована: Май 25, 2023

Язык: Английский

---