Application of optimized machine learning techniques for prediction of occupational accidents

Sarkar, Sobhan; Vinay, S.; Raj, Rahul; Maiti, J.; Mitra, Pabitra

doi:10.1016/j.cor.2018.02.021

Cited by 157 publications

(93 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, there are machine learning techniques applied to forecast crime, traffic incidents, traffic flow and speed, occupational accidents, and others. In [5] authors presented a proposal to forecast occupational accidents using Support Vector Machine (SVM) and Multi-Layer Perceptron (MLP) optimized by Genetic Algorithm (GA) and Particle Swarm Optimization (PSO), where the aim was to predict the accident outcomes such as injury and property damage using occupational accident data.…”

Section: State Of Artmentioning

confidence: 99%

Long Short-Term Memory for Predicting Firemen Interventions

Nahuis

Guyeux

Arcolezi

et al. 2019

2019 6th International Conference on Control, Decision and Information Technologies (CoDIT)

View full text Add to dashboard Cite

Many environmental, economic and societal factors are leading fire brigades to be increasingly solicited, and they therefore face an ever-increasing number of interventions, most of the time on constant resource. On the other hand, these interventions are directly related to human activity, which itself is predictable: swimming pool drownings occur in summer while road accidents due to ice storms occur in winter. One solution to improve the response of firefighters in constant resource is therefore to predict their workload, i.e. their number of interventions per hour, based on explanatory variables conditioning human activity. The purpose of this article is to show that these interventions can indeed be predicted, in a nonabsurd way, from state-of-the-art tools such as recurrent long short-term memory neural networks (LSTM). From the list of interventions in the Doubs (France), we show that it is possible to build, from scratch, a neural network capable of reasonably predicting the interventions of 2017 from those of 2012-2016. While the results could be improved, they are already promising and would allow the actions of firefighters with a constant resource to be optimized.

show abstract

Section: State Of Artmentioning

confidence: 99%

Long Short-Term Memory for Predicting Firemen Interventions

Nahuis

Guyeux

Arcolezi

et al. 2019

2019 6th International Conference on Control, Decision and Information Technologies (CoDIT)

View full text Add to dashboard Cite

show abstract

“…Poh et al [18] presented a machine-learning approach to develop leading indicators that classify construction sites by their safety risk. A machine-learning approach using occupational accident data was also used by Sarkar et al [19] to predict occupational accident outcomes, such as injuries, near misses, and property damage. Although the results of the studies mentioned above demonstrate considerable promise, the specificity of the datasets that the researchers used to develop these methods renders the widespread application of these methods difficult in practice for organizations with dissimilar data; in particular, generalization is difficult for datasets related to project performance rather than safety performance.…”

Section: Machine Learning-based Modelsmentioning

confidence: 99%

Leading Safety Indicators: Application of Machine Learning for Safety Performance Measurement

Jafari¹,

Mohamed²,

Pereira³

et al. 2019

Proceedings of the International Symposium on Automation and Robotics in Construction (IAARC)

View full text Add to dashboard Cite

Proactive approaches designed to prevent incidents before they occur are essential for achieving effective safety management. Emerging as an important component of proactive safety management, leading indicators are used to assess and control safety performance. With the aim of reducing the number or severity of worksite accidents, methods capable of predicting future safety performance using leading safety indicators have been developed. However, these methods have been developed for a specific set of leading indicators. This has substantially limited their application in practice, as leading indicators with the greatest impact on safety performance vary considerably between organizations and projects. An approach for predicting accident occurrence on construction sites that can be applied to any combination of leading indicators is proposed to address these limitations. Data used to develop the proposed approach were collected by a construction company from eight construction projects over a period of two years. Feature selection techniques were used to filter the original factors into the most critical subset, which were then used as inputs. Various supervised learning algorithms, namely support vector machine (SVM), logistic regression, and random forest, were then tested to determine which algorithm(s) yielded the highest prediction accuracy. The results demonstrate that the proposed procedure can be used for early recognition of potentially hazardous project characteristics and site conditions regardless of the number or type of leading indicators available within an organization. Research in this area is expected to facilitate the implementation of targeted safety management controls and to improve safety performance.

show abstract

“…SML for image recognition has been proposed and tested for construction surveillance issues (such as concrete quality, on-site worker movement, and construction injury prediction) [12], analysis of pictures of roofs to prevent occupational accidents [26], web image processing to detect road surface cracks [27], and automated on-site detection of workers and heavy equipment [28]. Apart from the system in [12], SML has also been deployed to identify root causes of occupational accidents [29], and has been coupled with the cross-industry standard process for data mining (CRISP-DM) framework to develop on-site safety leading indicators [30]. Moreover, SML has been intertwined with plot analysis to assess key project performance indicators [31], and with deep learning (namely, gradient-based optimization to adjust parameters throughout a multilayered network, based on errors at its output [32]) for the electroencephalography-based recognition of construction workers' stress while performing on-site tasks [33] and the detection of non-certified work on-site [34].…”

Section: Machine Learning Modelling Within the Construction Sectormentioning

confidence: 99%

Building Information Models’ Data for Machine Learning Systems in Construction Management

Kifokeris¹,

Roupé²,

Johansson³

et al. 2019

Proceedings of the Creative Construction Conference 2019

View full text Add to dashboard Cite

Qualitative and quantitative data are important in construction management. However, despite the capabilities of construction informatics, such data and its sources have scarcely been fully and systematically utilized for predictive purposes. Building Information Models (BIM) are such a data source. Within BIM, information structures enabling interoperability and providing utilizable data throughout the various Levels of Development (LODs) of a buildingfor example, Industry Foundation Classes (IFCs)can be fully and meaningfully exploited through data mining, and more particularly, via machine learning. In this paper, the capabilities of the information structures found in IFCs to be used as data sources for developing machine learning predictive models, will be examined. In addition, and by conceptually tying such data with constructability, their suitability for predictingthrough such machine learning modelsthe delivery cost and time overheads of a construction project, will be considered.

show abstract

Application of optimized machine learning techniques for prediction of occupational accidents

Cited by 157 publications

References 42 publications

Long Short-Term Memory for Predicting Firemen Interventions

Long Short-Term Memory for Predicting Firemen Interventions

Leading Safety Indicators: Application of Machine Learning for Safety Performance Measurement

Building Information Models’ Data for Machine Learning Systems in Construction Management

Contact Info

Product

Resources

About