BIM log mining framework using deep learning for productivity assessment in construction facilities

Assessing construction productivity objectively and in real-time remains challenging. This study proposes an automated framework leveraging Building Information Modeling (BIM) interaction logs and predictive modeling. The methodology involves systematic log data processing and feature engineering, g...

Full description

Saved in:
Bibliographic Details
Main Authors: Ali Akbar, Younghee Chang, Jinwoo Song, Seojoon Lee, Sanghyeon Park, Jinhyun Bae, Soonwook Kwon
Format: Article
Language:English
Published: Taylor & Francis Group 2025-07-01
Series:Journal of Asian Architecture and Building Engineering
Subjects:
Online Access:http://dx.doi.org/10.1080/13467581.2025.2508442
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849393201100619776
author Ali Akbar
Younghee Chang
Jinwoo Song
Seojoon Lee
Sanghyeon Park
Jinhyun Bae
Soonwook Kwon
author_facet Ali Akbar
Younghee Chang
Jinwoo Song
Seojoon Lee
Sanghyeon Park
Jinhyun Bae
Soonwook Kwon
author_sort Ali Akbar
collection DOAJ
description Assessing construction productivity objectively and in real-time remains challenging. This study proposes an automated framework leveraging Building Information Modeling (BIM) interaction logs and predictive modeling. The methodology involves systematic log data processing and feature engineering, generation of pseudo-label productivity scores derived from an initial expert-informed model, and a rigorous comparative evaluation of predictive architectures. Sixteen diverse models were evaluated using 10-fold cross-validation on a 500-instance dataset derived from construction logs. The cross-validation identified XGBoost as the top-performing architecture (R2 = 0.97 ± 0.01), demonstrating the effectiveness of gradient boosting on the engineered tabular features. The framework incorporates an integrated interface with visualization and natural language processing for enhanced insight generation and accessibility. While acknowledging limitations concerning pseudo-label usage and initial data processing steps, this research presents a robust, validated methodology for data-driven productivity assessment, offering a scalable alternative to traditional methods in construction project management.
format Article
id doaj-art-db43ee25bcf44a55b8732a20c2a2ba75
institution Kabale University
issn 1347-2852
language English
publishDate 2025-07-01
publisher Taylor & Francis Group
record_format Article
series Journal of Asian Architecture and Building Engineering
spelling doaj-art-db43ee25bcf44a55b8732a20c2a2ba752025-08-20T03:40:30ZengTaylor & Francis GroupJournal of Asian Architecture and Building Engineering1347-28522025-07-010011610.1080/13467581.2025.25084422508442BIM log mining framework using deep learning for productivity assessment in construction facilitiesAli Akbar0Younghee Chang1Jinwoo Song2Seojoon Lee3Sanghyeon Park4Jinhyun Bae5Soonwook Kwon6Sungkyunkwan UniversitySungkyunkwan UniversitySungkyunkwan UniversitySungkyunkwan UniversitySungkyunkwan UniversitySungkyunkwan UniversitySungkyunkwan UniversityAssessing construction productivity objectively and in real-time remains challenging. This study proposes an automated framework leveraging Building Information Modeling (BIM) interaction logs and predictive modeling. The methodology involves systematic log data processing and feature engineering, generation of pseudo-label productivity scores derived from an initial expert-informed model, and a rigorous comparative evaluation of predictive architectures. Sixteen diverse models were evaluated using 10-fold cross-validation on a 500-instance dataset derived from construction logs. The cross-validation identified XGBoost as the top-performing architecture (R2 = 0.97 ± 0.01), demonstrating the effectiveness of gradient boosting on the engineered tabular features. The framework incorporates an integrated interface with visualization and natural language processing for enhanced insight generation and accessibility. While acknowledging limitations concerning pseudo-label usage and initial data processing steps, this research presents a robust, validated methodology for data-driven productivity assessment, offering a scalable alternative to traditional methods in construction project management.http://dx.doi.org/10.1080/13467581.2025.2508442building information modeling (bim)deep learning architecturesconstruction productivitybim log mininglstm autoencoder
spellingShingle Ali Akbar
Younghee Chang
Jinwoo Song
Seojoon Lee
Sanghyeon Park
Jinhyun Bae
Soonwook Kwon
BIM log mining framework using deep learning for productivity assessment in construction facilities
Journal of Asian Architecture and Building Engineering
building information modeling (bim)
deep learning architectures
construction productivity
bim log mining
lstm autoencoder
title BIM log mining framework using deep learning for productivity assessment in construction facilities
title_full BIM log mining framework using deep learning for productivity assessment in construction facilities
title_fullStr BIM log mining framework using deep learning for productivity assessment in construction facilities
title_full_unstemmed BIM log mining framework using deep learning for productivity assessment in construction facilities
title_short BIM log mining framework using deep learning for productivity assessment in construction facilities
title_sort bim log mining framework using deep learning for productivity assessment in construction facilities
topic building information modeling (bim)
deep learning architectures
construction productivity
bim log mining
lstm autoencoder
url http://dx.doi.org/10.1080/13467581.2025.2508442
work_keys_str_mv AT aliakbar bimlogminingframeworkusingdeeplearningforproductivityassessmentinconstructionfacilities
AT youngheechang bimlogminingframeworkusingdeeplearningforproductivityassessmentinconstructionfacilities
AT jinwoosong bimlogminingframeworkusingdeeplearningforproductivityassessmentinconstructionfacilities
AT seojoonlee bimlogminingframeworkusingdeeplearningforproductivityassessmentinconstructionfacilities
AT sanghyeonpark bimlogminingframeworkusingdeeplearningforproductivityassessmentinconstructionfacilities
AT jinhyunbae bimlogminingframeworkusingdeeplearningforproductivityassessmentinconstructionfacilities
AT soonwookkwon bimlogminingframeworkusingdeeplearningforproductivityassessmentinconstructionfacilities