Construction site accident analysis using text mining and natural language processing techniques

Zhang, Fan; Fleyeh, Hasan; Wang, Xinru; Lu, Minghui

doi:10.1016/j.autcon.2018.12.016

Cited by 261 publications

(123 citation statements)

References 28 publications

Supporting

Mentioning

120

Contrasting

Unclassified

Order By: Relevance

“…Moreover, the use of working equipment as proximal cause of the accidents confirms the results of similar studies in the construction sector [80,81,82], stressing the need for more rigorous interventions also at the normative level as in the case of scaffolding [83]. The results obtained showed that multiple factors always influenced the accidents′ occurrence, confirming the need to take into account the interactions between the different aspects that characterize working operations.…”

Section: Discussionsupporting

confidence: 79%

Risk Profiling from the European Statistics on Accidents at Work (ESAW) Accidents′ Databases: A Case Study in Construction Sites

Lombardi

Fargnoli

Parise

2019

IJERPH

View full text Add to dashboard Cite

The number of accidents and victims in the construction sector has not decreased significantly despite the increasingly stricter laws and regulations. The analysis of accidents, as well as their root causes and determinants can certainly contribute to the development of more effective preventive interventions. The present study proposes a methodology for the analysis and synthesis of data provided by accidents statistics with the goal of defining specific risk profiles based on the accidents determinants, their variables, and how they interact with one another in influencing the occurrence of an accident. For this purpose, a procedure capable of extracting this type of information from the European Statistics on Accidents at Work (ESAW) database was developed. In particular, data processing and aggregation are performed by means of the synergic use of the Matrix of Descriptors (MoD) and cluster analysis. To validate such a procedure, the analysis of fatalities due to electrical shocks was carried out. The results achieved allowed us to elicit valuable information for both safety managers and decision makers. The proposed methodology can facilitate a systemic analysis of accidents databases reducing the difficulties in managing reports and accident statistics.

show abstract

Section: Discussionsupporting

confidence: 79%

Risk Profiling from the European Statistics on Accidents at Work (ESAW) Accidents′ Databases: A Case Study in Construction Sites

Lombardi

Fargnoli

Parise

2019

IJERPH

View full text Add to dashboard Cite

show abstract

“…The results showed that the SVM-based classifier generated a better F1 value than other classifiers. Zhang et al [16] further proposed sequential quadratic programming (SQP)-based integrated algorithm based on Goh et al's work. This combined method achieved a weighted result of 0.68, which is better than the result of a single machine learning algorithm.…”

Section: Existing Studies On Accident Narrative Classificationmentioning

confidence: 99%

“…Therefore, it is significantly important to investigate the method of automatic classification of texts written in natural language [15]. However, studies of text mining, natural language processing (NLP) and deep learning (DL) techniques for the analysis of construction accident narratives are very limited [16]. To fill this gap, using accident narratives data obtained from the official website of OSHA, this paper presents a novel and unified architecture that contains a bidirectional long short-term memory (BiLSTM) model and a convolutional layer for the classification of construction accident causes.…”

Section: Introductionmentioning

confidence: 99%

A C-BiLSTM Approach to Classify Construction Accident Reports

Hou

Deng

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

The construction sector is widely recognized as having the most hazardous working environment among the various business sectors, and many research studies have focused on injury prevention strategies for use on construction sites. The risk-based theory emphasizes the analysis of accident causes extracted from accident reports to understand, predict, and prevent the occurrence of construction accidents. The first step in the analysis is to classify the incidents from a massive number of reports into different cause categories, a task which is usually performed on a manual basis by domain experts. The research described in this paper proposes a convolutional bidirectional long short-term memory (C-BiLSTM)-based method to automatically classify construction accident reports. The proposed approach was applied on a dataset of construction accident narratives obtained from the Occupational Safety and Health Administration website, and the results indicate that this model performs better than some of the classic machine learning models commonly used in classification tasks, including support vector machine (SVM), naïve Bayes (NB), and logistic regression (LR). The results of this study can help safety managers to develop risk management strategies.

show abstract

“…Collapse accidents at construction sites are continuously occurring [ 1 , 2 , 3 ]. According to Heinrich’s law, a small local displacement occurs in a structure before a large-scale collapse accident occurs [ 4 , 5 , 6 ].…”

Section: Introductionmentioning

confidence: 99%

Marker-Based Structural Displacement Measurement Models with Camera Movement Error Correction Using Image Matching and Anomaly Detection

Kim

Jeong

Lee³

et al. 2020

Sensors

View full text Add to dashboard Cite

To prevent collapse accidents at construction sites, the marker-based displacement measurement method was developed. However, it has difficulty in obtaining accurate measurements at long distances (>50 m) in an outdoor environment because of camera movements. To overcome this problem, marker-based structural displacement measurement models using image matching and anomaly detection were designed in this study. Then, the performance of each model in terms of camera movement error correction was verified through comparison with that of a conventional model. The results show that the systematic errors due to camera movements (<1.7°) were corrected. The detection rate of markers with displacement reached 95%, and the probability that the error size would be less than 10 mm was ≥ 95% with a 95% confidence interval at a distance of more than 100 m. Moreover, the normalized mean square error was less than 0.1. The models developed in this study can measure the pure displacement of an object without the systematic errors caused by camera movements. Furthermore, these models can be used to measure the displacements of distant structures using closed-circuit television cameras and markers in an outdoor environment with high accuracy.

show abstract

Construction site accident analysis using text mining and natural language processing techniques

Cited by 261 publications

References 28 publications

Risk Profiling from the European Statistics on Accidents at Work (ESAW) Accidents′ Databases: A Case Study in Construction Sites

Risk Profiling from the European Statistics on Accidents at Work (ESAW) Accidents′ Databases: A Case Study in Construction Sites

A C-BiLSTM Approach to Classify Construction Accident Reports

Marker-Based Structural Displacement Measurement Models with Camera Movement Error Correction Using Image Matching and Anomaly Detection

Contact Info

Product

Resources

About