Analysis of Construction Accident Reports Based on C-BiLSTM Model

Deng, Da; Hou, Yuexian; Wang, Mingen

doi:10.1109/icicta51737.2020.00017

Cited by 5 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They used deep-learning models such as CNN, Gated recurrent unit (GRU), and Recurrent Neural Network (RNN) to automatically learn injury precursors from raw construction engineering reports by identifying textural patterns, asserting that such an approach can be used to understand, predict, and prevent injury occurrence in construction. Other applications for text monitoring in construction industry described in articles in this cluster include classifying construction safety accident reports automatically (Deng et al 2020), using fastText-based classification to classify text reports of court compensation cases involving construction accidents , classifying short text containing building quality complaints (Zhong et al 2019), and text classification to automate job hazard analysis (Chi et al 2013), to name a few.…”

Section: Construction Site Text Report Monitoring Using Deep Learningmentioning

confidence: 99%

“…Another area warranting the attention of construction researchers is the use of a deep-learning approach to classify text and speech in construction. There have been a few studies published in this area, including such applications as construction site text report monitoring for accidents and claims (Deng et al 2020), text classification to automate job hazard analysis (Chi et al 2013), speech recognition technology for building quantity estimation (Olanrewaju et al 2020), and on-site conversation analysis (Zhang et al 2018, Scarpiniti et al 2021. Deep-learning models are capable of classifying text and speech with high accuracy in a range of environmental conditions, and the use of deep learning in construction for text classification can enhance understanding of construction reports and support timely analysis of complaints by automating the process.…”

Section: Deep Learning For Text and Speech Classification In Construc...mentioning

confidence: 99%

See 1 more Smart Citation

Scientometric analysis and critical review on the application of deep learning in the construction industry

et al. 2023

View full text Add to dashboard Cite

Deep learning in construction industry has attracted increasing attention among researchers. In this article, scientometric analysis and critical review are performed to analyze the state-of-the-art literature on the application of deep learning in construction. This research used the science mapping method to quantitatively and systematically analyze 423 related bibliographic records retrieved from the Scopus database, and further, a critical review is performed on collected themes. The results of the critical review indicate that deep convolution neural networks, you only look once, residual neural networks and fast region-based convolution neural networks have been the most widely used methods in the construction industry. The most commonly addressed problems in the construction industry using deep learning methods includes classification of construction equipment, worker's safety helmet detection and ergonomics analysis. This paper provides an in-depth understanding of the existing literature along with the challenges and future direction of deep learning in the construction industry.

show abstract

Section: Construction Site Text Report Monitoring Using Deep Learningmentioning

confidence: 99%

Section: Deep Learning For Text and Speech Classification In Construc...mentioning

confidence: 99%

Scientometric analysis and critical review on the application of deep learning in the construction industry

et al. 2023

View full text Add to dashboard Cite

show abstract

Identifying High-Risk Workers’ Actions Contributing to Highway Construction Accidents

Nguyen,

Do,

et al. 2024

Computing in Civil Engineering 2023

View full text Add to dashboard Cite

A Novel Bim-Enabled Software-Based Solution for Mitigating Construction Risk Management

Abosaq,

Batool

2024

Yanbu Journal of Engineering and Science

View full text Add to dashboard Cite

This paper presents a novel Software-based solution to mitigate the most prevalent construction risks with systematic implementation of Building Information Modeling Software at the lifecycle stages of the project and provides practical recommendations for industry practitioners. The construction industry has a complex and uncertain process presenting different opportunities and challenges at various project phases. Incorporating traditional risk management methods with BIM helps identify and manage risks effectively. This research paper presents a systematic approach to implementing BIM throughout the lifecycle of an eight-story building project, from feasibility to construction, to manage major risks in each phase. The paper addresses a gap in the literature by identifying and mitigating prominent risks in the construction industry of Pakistan through BIM modeling, based on a review of 180 common risks and detailed interviews. The research methodology involved surveys and data analysis to identify and prioritize the most significant risks and suitable BIM mitigation measures. The study suggests that BIM’s collaboration software resolves communication issues while Clash Detection mitigates Design-related risks before the start of construction. Simulation of Planned vs. Actual Progress and accurate Quantity Estimates achieved by BIM’s estimation software contribute to the successful completion of the project. BIM and its tools have the potential to revolutionize the construction process if used as a structured risk management tool throughout the project lifecycle. The paper advises designing out most project risks in the Planning and Design phase while reserving monitoring and control for later stages as early identification and management of risks is critical for success.

show abstract

Analysis of Construction Accident Reports Based on C-BiLSTM Model

Cited by 5 publications

References 6 publications

Scientometric analysis and critical review on the application of deep learning in the construction industry

Scientometric analysis and critical review on the application of deep learning in the construction industry

Identifying High-Risk Workers’ Actions Contributing to Highway Construction Accidents

A Novel Bim-Enabled Software-Based Solution for Mitigating Construction Risk Management

Contact Info

Product

Resources

About