Enhancing construction safety: Machine learning-based classification of injury types

Alkaissy, Maryam; Arashpour, Mehrdad; Golafshani, Emadaldin Mohammadi; Hosseini, M. Reza; Khanmohammadi, Sadegh; Bai, Yu; Feng, Haibo

doi:10.1016/j.ssci.2023.106102

Cited by 26 publications

(13 citation statements)

References 86 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Occupational accident field, 16 out of 61 papers dealt with data on accidents and injuries at work from 2014 to 2023. In the class "occupational accidents," the 89 out of 202 submissions covered the following topics: reporting of accidents [3,26,27,29,32,35,43,45,49,[59][60][61][62]75,76] and days away from work. On this topic, Yelda et al analysed textual narratives to predict injury outcome and days off work in a mining operation.…”

Section: Discussion and Future Directionsmentioning

confidence: 99%

“…The risk in non-randomised studies was assessed on the basis of the following biases: (1) due to confounding, (2) in the selection of the types of data in the study, (3) in the classification of the study objective, (4) due to missing data, (5) in the measurement of outcomes, (6) in the evaluation metrics and (7) in the selection of the reported outcome. Each individual study included was assessed as having a low, moderate, severe, and critical risk of bias.…”

Section: Risk Of Bias For Selected Studiesmentioning

confidence: 99%

See 1 more Smart Citation

A Review of Data Mining Strategies by Data Type, with a Focus on Construction Processes and Health and Safety Management

Pireddu,

Bedini,

Lombardi

et al. 2024

Preprint

View full text Add to dashboard Cite

Increasingly, information technology facilitates the storage and management of data useful for risk analysis and event prediction. Studies on data extraction related to occupational health and safety are increasingly available; however, due to its variability, the construction sector warrants special attention. This review is conducted under the research programmes of the National Institute for Occupational Accident Insurance (Inail). Objectives: The research question focuses on identifying which data mining (DM) methods, among supervised, unsupervised, and others, are most appropriate to be applied to certain investigation objectives, types, and sources of data, as defined by the authors. Methods: Scopus and ProQuest were the main sources from which we extracted studies in the field of construction, published between 2014 and 2023. The eligibility criteria applied in the selection of studies, were based on the Preferred Reporting Items for Systematic Review and meta-analysis (PRISMA). For exploratory purposes, we applied hierarchical clustering, while for in-depth analysis, we use principal component analysis (PCA) and meta-analysis. Results: The search strategy based on the PRISMA eligibility criteria, provided us with 61 out of 2,234 potential articles, 202 observation, 91 methodologies, 4 survey purposes, 3 data sources, 7 data types, and 3 resource type. Cluster analysis and PCA organized the information included in the paper dataset into two dimensions and labels: "supervised methods, institutional dataset, and predictive and classificatory purposes" (correlation 0.97÷8.18E-01; p-value 7.67E-55÷1.28E-22) and the second, Dim2 "not-supervised methods; project, simulation, literature, text data; monitoring, decision-making processes; machinery and environment" (corr. 0.84÷0.47; p-value 5.79E-25÷3.59E-06). We answered the research question regarding which method, among supervised, unsupervised, or other, is most suitable for application to data in the construction industry. Conclusions: The meta-analysis provided an overall estimate of the better effectiveness of supervised methods (Odds Ratio = 0.71, Confidence Interval 0.53÷0.96) compared to not-supervised methods.

show abstract

Section: Discussion and Future Directionsmentioning

confidence: 99%

Section: Risk Of Bias For Selected Studiesmentioning

confidence: 99%

A Review of Data Mining Strategies by Data Type, with a Focus on Construction Processes and Health and Safety Management

Pireddu,

Bedini,

Lombardi

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Among them, DNN is commonly applied for the prediction and classification of data with complex non-linear relationships, as multiple layers act to identify diverse specific functions [ 43 ]. Consequently, this study suggests a framework for developing accident prediction models according to the construction scale using DNN, considering the non-linearity of the accident data of the construction site [ 35 , 44 , 45 ]. To determine the optimal DNN model, the prediction error was estimated by comparison with the multiple regression analysis (MRA) models.…”

Section: Methodsmentioning

confidence: 99%

A deep neural network algorithm-based approach for predicting recovery period of accidents according to construction scale

Kim,

Adhikari,

Bae

et al. 2024

Heliyon

View full text Add to dashboard Cite

“…The "others" includes the accident types (e.g., overexertion, occupational diseases, and fire) that cannot be classified in the remaining five accident types and takes small proportions, which can decrease the reliability of the classification results. The selection of the six types of accidents in this study is based on a comprehensive analysis of accident reports, existing literature, industry standards, and common occurrences in construction sites [13,29,43]. These six accident types encompass a broad spectrum of incidents that are frequently reported and have significant implications for construction site safety.…”

Section: Datamentioning

confidence: 99%

Harnessing Generative Pre-Trained Transformers for Construction Accident Prediction with Saliency Visualization

Yoo,

Kim,

Park

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Leveraging natural language processing models using a large volume of text data in the construction safety domain offers a unique opportunity to improve understanding of safety accidents and the ability to learn from them. However, little effort has been made to date in regard to utilizing large language models for the prediction of accident types that can help to prevent and manage potential accidents. This research aims to develop a model for predicting the six types of accidents (caught-in-between, cuts, falls, struck-by, trips, and others) by employing transfer learning with a fine-tuned generative pre-trained transformer (GPT). Additionally, to enhance the interpretability of the fine-tuned GPT model, a method for saliency visualization of input text was developed to identify words that significantly impact prediction results. The models were evaluated using a comprehensive dataset comprising 15,000 actual accident records. The results indicate that the suggested model for detecting the six accident types achieves 82% accuracy. Furthermore, it was observed that the proposed saliency visualization method can identify accident precursors from unstructured free-text data of construction accident reports. These results highlight the advancement of the generalization performance of large language processing-based accident prediction models, thereby proactively preventing construction accidents.

show abstract

Enhancing construction safety: Machine learning-based classification of injury types

Cited by 26 publications

References 86 publications

A Review of Data Mining Strategies by Data Type, with a Focus on Construction Processes and Health and Safety Management

A Review of Data Mining Strategies by Data Type, with a Focus on Construction Processes and Health and Safety Management

A deep neural network algorithm-based approach for predicting recovery period of accidents according to construction scale

Harnessing Generative Pre-Trained Transformers for Construction Accident Prediction with Saliency Visualization

Contact Info

Product

Resources

About