Summary of What Makes a Good Bim Design: Quantitative Linking Between Design Behavior and Quality, by Xiang-rui Ni et al.
What makes a good BIM design: quantitative linking between design behavior and quality
by Xiang-Rui Ni, Peng Pan, Jia-Rui Lin
First submitted to arxiv on: 14 Nov 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This study proposes a novel approach to identify and quantify the relationship between design behaviors and design quality in the Architecture Engineering & Construction (AEC) industry based on Building Information Modeling (BIM). By integrating real-time data collection, log mining, feature engineering, and machine learning models, researchers confirmed an existing quantifiable relationship that can be learned by various models. The best-performing model achieved an R2 value of 0.88 on the test set. Findings highlight behavioral features related to designer’s skill level and changes in design intentions as significant factors impacting design quality. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study helps us understand how designers work and how they create better designs. By collecting data on what designers do, researchers found a link between design behaviors and the quality of designs. They used special models that can learn from this data to see which features are most important. The best model was very accurate, with an R2 value of 0.88. This means that if you know how well someone is doing as they design, you can predict how good their final design will be. |
Keywords
» Artificial intelligence » Feature engineering » Machine learning
