A5075755166- BIM and Construction Integration
- Construction Project Management and Performance
- 3D Surveying and Cultural Heritage
- Manufacturing Process and Optimization
- Infrastructure Maintenance and Monitoring
- Innovations in Concrete and Construction Materials
- Business Process Modeling and Analysis
- Model-Driven Software Engineering Techniques
- Semantic Web and Ontologies
- 3D Modeling in Geospatial Applications
- Facilities and Workplace Management
- Evacuation and Crowd Dynamics
- Technology and Data Analysis
- Occupational Health and Safety Research
- Product Development and Customization
- Advanced Database Systems and Queries
- Geotechnical Engineering and Analysis
- Natural Language Processing Techniques
- Robotics and Sensor-Based Localization
- Software Engineering Research
- Industrial Vision Systems and Defect Detection
- Urban Design and Spatial Analysis
- Topic Modeling
- Simulation and Modeling Applications
- Design Education and Practice
Yonsei University
2016-2025
China Railway Construction Corporation (China)
2021
Korea Institute of Civil Engineering and Building Technology
2013
Georgia Institute of Technology
2002-2006
Purdue University West Lafayette
2002
Suggestions abound for successful adoption of building information modeling (BIM); however, a company with limited resources cannot adopt them all. The factors that have top management priority accomplishment task are termed critical success (CSFs). This paper aims to derive the CSFs four questions commonly asked by companies in first wave BIM adoption: (1) What adopting company? (2) selecting projects deploy BIM? (3) services? (4) company-appropriate software applications? A list...
Abstract Zero‐shot learning, applied with vision‐language pretrained (VLP) models, is expected to be an alternative existing deep learning models for defect detection, under insufficient dataset. However, VLP including contrastive language‐image pretraining (CLIP), showed fluctuated performance on prompts (inputs), resulting in research prompt engineering—optimization of improving performance. Therefore, this study aims identify the features a that can yield best classifying and detecting...
This paper reports the worldwide status of building information modeling (BIM) adoption from perspectives engagement level, Hype Cycle model, technology diffusion and BIM services. An online survey was distributed, 156 experts six continents responded. Overall, North America most advanced continent, followed by Oceania Europe. Countries in Asia perceived their phase mainly as slope enlightenment (mature) model. In main BIM-users were early majority (third phase), but those Middle East/Africa...
The architecture engineering construction (AEC) industry has been plagued by notoriously low efficiency, high error rates, and large budget time overruns. main cause inadequate and...
This study introduces a framework for transplanting building information modeling (BIM) library. Design detailing constitutes 50%–60% of the total design time, even within BIM context. Previous studies have highlighted potential integrating and artificial intelligence (AI) enhanced productivity. However, challenges arise due to architects' preferences unique project-specific details when applying generalized AI approaches based on big data. To address this, we propose library transplant...
Authorities handle over 2,000 inquiries daily about building code violations. Interpreting these complex, frequently updated codes is challenging, even for legal experts. Prior studies used large language models (LLMs) with retrieval-augmented generation (RAG) but struggled to maintain context due data segmentation. This study evaluates three automated interpreter (ABCI) models—Original, Inferred, and Filtered—leveraging long-context window (LCW) LLMs. ABCI-Filtered achieved 63.2% accuracy...