Download PDFOpen PDF in browser

Machine Learning for Improving Construction Productivity: A Systematic Literature Review

8 pagesPublished: May 26, 2024

Abstract

Machine learning, as one of the Artificial Intelligence (AI) approaches, has been widely adopted in various fields and is now becoming one of the emerging technologies revolutionizing the construction industry. One of the machine learning applications in the construction industry is to improve construction productivity. However, the current application in this field primarily focuses on enhancing productivity within specific, isolated construction tasks, often lacking real-world applicability. Therefore, a more holistic framework aimed at enhancing productivity across the entire construction process is desired by industry professionals. To enhance readiness for constructing such a framework, a methodical examination of existing literature has been carried out to explore the status of utilizing machine learning to enhance efficiency in construction practices. This review not only identifies but also categorizes the existing machine-learning applications and practices. Additionally, it highlights limitations and potential enhancements within current machine learning techniques, offering valuable insights for future research endeavors.

Keyphrases: ai, construction productivity, deep learning, machine learning

In: Tom Leathem, Wes Collins and Anthony Perrenoud (editors). Proceedings of 60th Annual Associated Schools of Construction International Conference, vol 5, pages 558-565.

BibTeX entry
@inproceedings{ASC2024:Machine_Learning_Improving_Construction,
  author    = {Asad Sultan and Zhili Gao},
  title     = {Machine Learning for Improving Construction Productivity: A Systematic Literature Review},
  booktitle = {Proceedings of 60th Annual Associated Schools of Construction International Conference},
  editor    = {Tom Leathem and Wes Collins and Anthony Perrenoud},
  series    = {EPiC Series in Built Environment},
  volume    = {5},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2632-881X},
  url       = {/publications/paper/mxWf},
  doi       = {10.29007/bzlk},
  pages     = {558-565},
  year      = {2024}}
Download PDFOpen PDF in browser