Figure - uploaded by Antoine J.-P. Tixier
Content may be subject to copyright.
Source publication
By building on a recently introduced genetic-inspired attribute-based conceptual framework for safety risk analysis, we propose a novel methodology to compute univariate and bivariate construction safety risk at a situational level. Our fully data-driven approach provides construction practitioners and academicians with an easy and automated way of...
Citations
... Scholars have attempted to apply more systemic models and methods to improve construction accidents analysis (Carrillo-Castrillo et al., 2017). Data-driven safety risk analysis is an important method to improve construction safety performance (Tixier et al., 2017;Zhou et al., 2021a). China's metro construction accidents have occurred frequently due to the lack of effective safety risk control in the context of large-scale construction (Li et al., 2018). ...
Purpose
The purpose of this study is to identify the causative factors of metro construction safety accidents, analyze the correlation between accidents and causative factors and assist in developing safety management strategies for improving safety performance in the context of the Chinese construction industry.
Design/methodology/approach
To achieve these objectives, 13 types and 48 causations were determined based on 274 construction safety accidents in China. Then, 204 cause-and-effect relationships among accidents and causations were identified based on data mining. Next, network theory was employed to develop and analyze the metro construction accident causation network (MCACN).
Findings
The topological characteristics of MCACN were obtained, it is both a small-world network and a scale-free network. Controlling critical causative factors can effectively control the occurrence of metro construction accidents. Degree centrality strategy is better than closeness centrality strategy and betweenness centrality strategy.
Research limitations/implications
In practice, it is very difficult to quantitatively identify and determine the importance of different accidents and causative factors. The weights of nodes and edges are failed to be assigned when constructing MCACN.
Practical implications
This study provides a theoretical basis and feasible management reference for construction enterprises in China to control construction risks and reduce safety accidents. More safety resources should be allocated to control critical risks. It is recommended that safety managers implement degree centrality strategy when making safety-related decisions.
Originality/value
This paper establishes the MCACN model based on data mining and network theory, identifies the properties and clarifies the mechanism of metro construction accidents and causations.
... We later proved that using the attributes extracted by the tool to predict safety outcomes was effective and valid [4,5]. We also used the attributes extracted by the tool for unsupervised learning applications, such as clustering and visualization [6], and risk modeling and simulation [7]. ...
In this study, we capitalized on a collective dataset repository of 57k accidents from 9 companies belonging to 3 domains and tested whether models trained on multiple datasets (generic models) predicted safety outcomes better than the company-specific models. We experimented with full generic models (trained on all data), per-domain generic models (construction, electric T&D, oil & gas), and with ensembles of generic and specific models. Results are very positive, with generic models outperforming the company-specific models in most cases while also generating finer-grained, hence more useful, forecasts. Successful generic models remove the needs for training company-specific models, saving a lot of time and resources, and give small companies, whose accident datasets are too limited to train their own models, access to safety outcome predictions. It may still however be advantageous to train specific models to get an extra boost in performance through ensembling with the generic models. Overall, by learning lessons from a pool of datasets whose accumulated experience far exceeds that of any single company, and making these lessons easily accessible in the form of simple forecasts, generic models tackle the holy grail of safety cross-organizational learning and dissemination in the construction industry.
... It has been argued that these industries have reached a significant degree of saturation with respect to traditional safety strategies (Esmaeili and Hallowell, 2012). A contributing factor is that the critical risk-mitigation decisions are still predominantly made by humans, which is often "fraught with numerous biases and misconceptions inherent to human cognition and compounds the likelihood of misdiagnosing the riskiness of a situation" (Tixier et al., 2017). Therefore, it is imperative to consider novel approaches that objectively assess safety risks and optimally direct risk-mitigation efforts. ...
... Safety observations should capture both safe (i.e., positive) circumstances and at-risk or unsafe (i.e., negative) circumstances so as to appropriately characterize the relative frequency of these situations (Grant et al., 2018;Hollnagel, 2012). It is a common practice to group these observations into categories pertaining to work types, areas of focus, or different hazards (Verma et al., 2018;Tixier et al., 2017). ...
... A logical way to define safety risk is via the product of frequency and severity of incidents for every vulnerability (Tixier et al., 2017). We adhere to the same logic but define risk in probabilistic terms. ...
Identifying and mitigating safety risks is paramount in a number of industries. In addition to guidelines and best practices, many industries already have safety management systems (SMSs) designed to monitor and reinforce good safety behaviors. The analytic capabilities to analyze the data acquired through such systems, however, are still lacking in terms of their ability to robustly quantify risks posed by various occupational hazards. Moreover, best practices and modern SMSs are unable to account for dynamically evolving environments/behavioral characteristics commonly found in many industrial settings. This article proposes a method to address these issues by enabling continuous and quantitative assessment of safety risks in a data-driven manner. The backbone of our method is an intuitive hierarchical probabilistic model that explains sparse and noisy safety data collected by a typical SMS. A fully Bayesian approach is developed to calibrate this model from safety data in an online fashion. Thereafter, the calibrated model holds necessary information that serves to characterize risk posed by different safety hazards. Additionally, the proposed model can be leveraged for automated decision making, for instance solving resource allocation problems -- targeted towards risk mitigation -- that are often encountered in resource-constrained industrial environments. The methodology is rigorously validated on a simulated test-bed and its scalability is demonstrated on real data from large maintenance projects at a petrochemical plant.
... In recent years there has been a significant effort to leverage data analytics to assist in decisionmaking that directly improves safety performance (Huang et al., 2018;, in what has been called the era of Safety 4.0 (Wang, 2021). To that end, a number of safety analytics (SA) approaches have been reported in the literature (see, for example, Zhu et al. (2021); Sarkar et al. (2020); Verma et al. (2018); Poh et al. (2018); Tixier et al. (2016Tixier et al. ( , 2017; Kakhki et al. (2019); Cheng et al. (2013)). These studies compare and extend different machine learning methods that attempt to forecast incidents or their severity in different industrial settings. ...
There has been a significant increase in the development of data-driven safety analytics approaches in recent years. In light of these advances it has become imperative to evaluate such approaches in a principled way to determine their merits and limitations. To that end, we propose an evaluation methodology underpinned by a simulated environment that allows for a comprehensive assessment of safety analytics approaches. While assessing those approaches with historical field data is undoubtedly important, such an assessment has limited statistical power because it corresponds to only one realization. The proposed methodology enables validation over a large number of realizations, thereby circumventing the statistical limitations of evaluation on historical data. Moreover, by using a simulated environment one is able to clearly distinguish between the variability in the observed data and differences in performance between safety approaches. A simulated environment does this by comparing the approaches under controlled circumstances, resulting in a fair and systematic evaluation of the potential long-term benefits. We demonstrate the utility of the proposed methodology via a case study that compares a few candidate safety analytics approaches. These approaches differ in how they assimilate field safety data to assess safety risk and suggest mitigative actions. We show that the proposed methodology indeed reveals useful insights and quantifies the relative merits and drawbacks of the different approaches, which would be otherwise difficult to objectively determine in a real-world scenario.
... This variety, combined with technical, financial, and legal implications, makes the choice of the most suitable FPS a non-trivial and impactful decisionmaking. This decision-making is usually unstructured and does not make the best use of the experience of managers (Tixier et al., 2017). ...
The choice of fall protection systems (FPSs) in construction sites is an impactful decision-making due to technical , financial, and legal implications. However, this decision-making is usually unstructured and does not make the best use of the experience of managers. This study addresses this gap by proposing a five-step framework for choosing FPSs. The steps involve: (i) set up a team for choosing the FPS; (ii) define which types of fall hazards will be accounted for and in which construction stages; (iii) select possible FPSs; (iv) choose the best alternative, employing the choosing by advantages approach-alternatives are compared based on factors that have a complexity theory rationale, which frames FPSs as inseparable from the socio-technical system that makes up the construction project; and (v) record the lessons learned. Data sources for applying these steps involve interviews, observations, and documents. This paper presents an application of the framework for the choice between safety nets and façade scaffolds, in the construction of a residential building in Brazil. The framework might support managers in making transparent and theoretically grounded decisions when choosing FPSs, justifying their choice before clients, workers, and regulators.
... The dynamic nature of construction projects places the industry in one of the riskiest sectors with respect to safe project delivery (Asadzadeh et al., 2020;Hallowell, Bhandari, & Alruqi, 2019;Kang & Ryu, 2019;Lingard, Pirzadeh, & Oswald, 2019;Qazi, Quigley, Dickson, & Kirytopoulos, 2016). While technological advancements and continuous safety developments are evolving in the construction industry to achieve zero harm workplace environments, workforces are constantly exposed to different safety risks that result in occupational safety incidents (Cheng, Leu, Cheng, Wu, & Lin, 2012;Hallowell et al., 2019;Tixier, Hallowell, & Rajagopalan, 2017;Winge & Albrechtsen, 2018). The magnitude and implications of safety risk incidents extend beyond construction project performance to the overall economic development of the construction industry (Khodakarami & Abdi, 2014;Lingard, Hallowell, Salas, & Pirzadeh, 2017). ...
The construction sector is vulnerable to safety risk incidents due to its dynamic nature. Although numerous research efforts and technological advancements have focused on addressing workplace injuries, most of the studies perform empirical and deterministic postimpact evaluations on construction project performance. The effective modeling of the safety risk impacts on project performance provides decisionmakers with a valuable tool toward incidents prevention and proper safety risk management. Therefore, this study collected Australian incident records from the construction industry from 2016 onwards and conducted discrete event simulation to quantitatively measure the impact of safety risk incidents on project cost performance. Moreover, this study investigated the correlation between safety risk incidents and the age of injured workers. The findings show a strong correlation between the middle‐aged workforce and the severity of incidents on project cost overruns. The ex‐ante, nondeterministic analysis of safety risk impacts on project performance provides insightful results that will advance safety management theory in the direction of achieving zero harm workplace environments.
... The same could be done for other severity levels, and the data can be aggregated into one risk value (Hallowell and Gambatese 2009a). Previous researchers have quantified safety risk for different units of analysis, including trades (Baradan and Usmen 2006;Everett 1999), tasks (Hallowell and Gambatese 2009a), and fundamental attributes (Tixier et al. 2017), and have deployed a variety of analytical techniques ranging from expert opinion (Hinze et al. 2013a) to kernel density estimators and copulas (Tixier et al. 2017). ...
... The same could be done for other severity levels, and the data can be aggregated into one risk value (Hallowell and Gambatese 2009a). Previous researchers have quantified safety risk for different units of analysis, including trades (Baradan and Usmen 2006;Everett 1999), tasks (Hallowell and Gambatese 2009a), and fundamental attributes (Tixier et al. 2017), and have deployed a variety of analytical techniques ranging from expert opinion (Hinze et al. 2013a) to kernel density estimators and copulas (Tixier et al. 2017). ...
... These are referred to simply as attributes. Using attribute-level data sourced from construction injury reports, Tixier et al. (2017) applied stochastic safety risk generators to objectively simulate risk. ...
Serious injuries and fatalities (SIF) continue to be an enigmatic problem in the construction industry. Researchers have begun to explore new ways of preventing these incidents by developing and testing leading indicators, precursor analysis, and risk assessment supported by data analytics. These recent themes suggest a new paradigm in safety prediction. Aligned with this trajectory, the objectives of this study were to (1) identify a comprehensive list of potential predictors of SIFs in construction, including business factors, project characteristics, and crew demographics; (2) quantitatively prioritize potential predictors; and (3) develop a rank-ordered list of factors that could be tested for predictive validity and practically deployed on site. An expert panel of 22 industry practitioners generated 254 potential predictors of construction SIFs through structured brainstorming. To prioritize these potential predictors, the expert panel rated the extent to which each is measurable, predictive, simple, and actionable. Finally, a weighted sum method and a maximin approach was used to identify the predictors with the greatest practical potential for predicting SIF events, including brand-new concepts that have not yet been considered in the associated safety literature. Most previous research has focused on one specific form of safety prediction at a time (e.g., leading indicators), whereas this research effort is a first step toward a unified model with high feasibility and practical relevance.
... For the sake of identification of the potential fatalities associated with construction activities, Malekitabar et al. (2016) came up with five-level safety drivers influencing either the likelihood or the impact of the accidents occurred on sites. Using kernel density estimators and copulas, Tixier et al. (2017) developed a stochastic-based model for dealing with the identified safety risks. Raviv et al. (2017) investigated into the accidents associated with working in close contact with tower crane. ...
The construction industry has always been infamous due to its staggering numbers of Occupational Health and Safety (OHS)-related injuries, resulting from overlooking all the crucial aspects endangering the involved workers’ lives. Considering this, there has been dearth of a study including all the essential Risk Parameters (RPs) for comprehensively assessing the OHS in the construction industry. Theretofore, a Holistic Occupational Health and Safety Risk Assessment Model (HOHSRAM) is developed in the current study to assess the safety and health of the Construction Workers (CWs’). The developed model is based on the integration of logarithmic fuzzy ANP, interval-valued Pythagorean fuzzy TOPSIS, and grey relational analysis. Based on the application of the developed HOHSRAM to a case of sustainable construction project, the following contributions have been noted; (1) calculating weights related to the safety decision makers having different backgrounds involved in the study using logarithmic-fuzzy-based constrained optimization algorithm, (2) involving the individual biases of the decision makers in the assessment stage, (3) determining all the essential RPs to comprehensively assess the OHS within the construction projects in a systematic way, (4) obtaining the final rankings of the identified safety risks under an interval-valued-Pythagorean fuzzy environment coupled with grey relational analysis. Additionally, it is discerned that the proposed model in this research outperforms the existing assessment methods used in the construction industry, through conducting a comprehensive comparative analysis. The developed HOHSRAM is verified to be beneficial for safety professionals by providing them with an inclusive ranking system, improving the well-being of the involved CWs.
... For instance, Malekitabar et al. [34] investigated the risk of accidents-considering probability and severity-by identifying five-level safety drivers. Tixier et al. [35] developed a model to analyze the safety risks by Kernel density estimators and Copulas, while Raviv et al. [36] especially analyzed accidents that occur in using tower crane. When it comes to the adoption of sustainable approaches in the construction industry, safety requirements need to be met to ensure every possible new safety risk is carefully considered. ...
Occupational Health and Safety (OHS)-related injuries are vexing problems for construction projects in developing countries, mostly due to poor managerial-, governmental-, and technical safety-related issues. Though some studies have been conducted on OHS-associated issues in developing countries, research on this topic remains scarce. A review of the literature shows that presenting a predictive assessment framework through machine learning techniques can add much to the field. As for Malaysia, despite the ongoing growth of the construction sector, there has not been any study focused on OHS assessment of workers involved in construction activities. To fill these gaps, an Ensemble Predictive Safety Risk Assessment Model (EPSRAM) is developed in this paper as an effective tool to assess the OHS risks related to workers on construction sites. The developed EPSRAM is based on the integration of neural networks with fuzzy inference systems. To show the effectiveness of the EPSRAM developed, it is applied to several Malaysian construction case projects. This paper contributes to the field in several ways, through: (1) identifying major potential safety risks, (2) determining crucial factors that affect the safety assessment for construction workers, (3) predicting the magnitude of identified safety risks accurately, and (4) predicting the evaluation strategies applicable to the identified risks. It is demonstrated how EPSRAM can provide safety professionals and inspectors concerned with well-being of workers with valuable information, leading to improving the working environment of construction crew members.
... Meanwhile, [34] and [35] extracted 81 fundamental attributes (or precursors) from injury reports using a tool based on an entirely hand-written lexicon and set of rules [36]. This allowed them respectively to predict safety outcomes with good skill, and to identify interesting combinations of attributes, coined as "safety clashes". ...
In light of the increasing availability of digitally recorded safety reports in the construction industry, it is important to develop methods to exploit these data to improve our understanding of safety incidents and ability to learn from them. In this study, we compare several approaches to automatically learn injury precursors from raw construction accident reports. More precisely, we experiment with two state-of-the-art deep learning architectures for Natural Language Processing (NLP), Convolutional Neural Networks (CNN) and Hierarchical Attention Networks (HAN), and with the established Term Frequency - Inverse Document Frequency representation (TF-IDF) + Support Vector Machine (SVM) approach. For each model, we provide a method to identify (after training) the textual patterns that are, on average, the most predictive of each safety outcome. We show that among those pieces of text, valid injury precursors can be found. The proposed methods can also be used by the user to visualize and understand the models' predictions.
